CN118383800B - Intelligent ultrasonic inspection method and system for same-direction operation - Google Patents
Intelligent ultrasonic inspection method and system for same-direction operation Download PDFInfo
- Publication number
- CN118383800B CN118383800B CN202410831346.XA CN202410831346A CN118383800B CN 118383800 B CN118383800 B CN 118383800B CN 202410831346 A CN202410831346 A CN 202410831346A CN 118383800 B CN118383800 B CN 118383800B
- Authority
- CN
- China
- Prior art keywords
- target
- pixel point
- region
- gray
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000007689 inspection Methods 0.000 title claims abstract description 38
- 230000011218 segmentation Effects 0.000 claims abstract description 15
- 238000002604 ultrasonography Methods 0.000 claims abstract description 13
- 230000002708 enhancing effect Effects 0.000 claims abstract description 9
- 239000004575 stone Substances 0.000 claims description 50
- 238000010606 normalization Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 230000002596 correlated effect Effects 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000002194 synthesizing effect Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 15
- 210000001519 tissue Anatomy 0.000 description 14
- 230000006870 function Effects 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 210000000988 bone and bone Anatomy 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 210000001953 common bile duct Anatomy 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 210000000626 ureter Anatomy 0.000 description 1
- 210000003932 urinary bladder Anatomy 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Clinical applications
- A61B8/0833—Clinical applications involving detecting or locating foreign bodies or organic structures
- A61B8/085—Clinical applications involving detecting or locating foreign bodies or organic structures for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5269—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving detection or reduction of artifacts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radiology & Medical Imaging (AREA)
- General Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Vascular Medicine (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention relates to the field of medical ultrasonic inspection, in particular to an intelligent ultrasonic inspection method and system operated in the same direction. Firstly, carrying out region segmentation on an ultrasonic image of a human body part to be detected to obtain a plurality of initial calculus regions, and obtaining a first judgment parameter of a target region according to the difference of pixel point gray values between the target region and a background region and the difference of pixel point gray values between the target region and other initial calculus regions; the method comprises the steps of (1) making a connection line of a target area edge pixel point to a selected central pixel point, obtaining a second judgment parameter of the target area according to the distribution of gray values of all pixel points in a preset window of each pixel point on the connection line in the connection line direction, and selectively enhancing an initial calculus area by combining the first judgment parameter and the second judgment parameter to obtain an enhanced image; and performing co-operative ultrasound inspection based on the enhanced image. The invention can improve the enhancement effect of the ultrasonic image and the accuracy of the same-direction operation ultrasonic examination.
Description
Technical Field
The invention relates to the field of medical ultrasonic inspection, in particular to an intelligent ultrasonic inspection method and system operated in the same direction.
Background
The same-direction operation ultrasonic inspection is an inspection method for performing real-time synchronous operation by utilizing an ultrasonic technology, has particularly wide application in the field of stone treatment, can perform related operation, such as guiding a needle or a catheter to a stone position while observing ultrasonic images, and reduces the risk of accidentally injuring surrounding tissue structures, so that the quality of the ultrasonic images plays an important role in the same-direction operation ultrasonic inspection.
In the related art, generally, the ultrasonic image for checking the calculus is subjected to overall enhancement treatment, so that the performance characteristics of the calculus in the ultrasonic image are improved, but the ultrasonic checking of the calculus is influenced by bones in human tissues, meanwhile, the density distribution of the calculus is uneven, the degree of reflection of ultrasonic waves by different parts is different, partial shadows exist around the calculus area in the ultrasonic image, the ultrasonic image is directly subjected to overall enhancement, and the final image enhancement effect is reduced, so that the accuracy of the ultrasonic checking of the same-direction operation is reduced.
Disclosure of Invention
In order to solve the technical problem that the effect of enhancing a final image is reduced when the ultrasonic image is directly enhanced as a whole, thereby reducing the accuracy of the same-direction operation ultrasonic inspection, the invention aims to provide an intelligent same-direction operation ultrasonic inspection method and system, and the adopted technical scheme is as follows:
The invention provides an intelligent ultrasonic inspection method for same-direction operation, which comprises the following steps:
Acquiring an ultrasonic image of a human body part to be detected; performing region segmentation on the ultrasonic image to obtain different initial stone regions;
Taking any one initial calculus region as a target region, and obtaining a first judgment parameter of the target region according to the difference of pixel gray values between the target region and the background regions except all the initial calculus regions and the difference of pixel gray values between the target region and the other initial calculus regions except the target region;
Selecting a central pixel point of a target area based on a gray value, taking a connection line of any pixel point on the edge of the target area and the central pixel point as a target line segment, wherein the direction of the target line segment is the direction that the pixel point on the edge of the target area points to the central pixel point, taking any pixel point on the target line segment as the target pixel point, and obtaining a second judgment parameter of the target area according to the distribution of gray values of all the pixel points in the direction of the target line segment in a preset window of the target pixel point; selectively enhancing an initial calculus region in the ultrasonic image by combining the first judging parameter and the second judging parameter to obtain an enhanced image;
and performing the same-direction operation ultrasonic examination on the human body part to be detected based on the enhanced image.
Further, the obtaining the first determination parameter of the target area includes:
Based on the gray level of the pixel points, analyzing the gray level of the whole pixel points in each initial calculus region to obtain the whole gray level of each initial calculus region, and simultaneously analyzing the gray level of the whole pixel points in the background region except all initial calculus regions to obtain the whole gray level of the background region;
obtaining a first gray scale difference parameter of the target region according to the difference of the integral gray scale values between the target region and the background region;
And obtaining a first judging parameter of the target area according to the first gray level difference parameter of the target area and the difference of the whole gray level values between the target area and other initial stone areas except the target area.
Further, the obtaining the first determination parameter of the target area according to the first gray scale difference parameter of the target area and the difference of the overall gray scale value between the target area and other initial stone areas except the target area includes:
Obtaining a second gray level difference parameter of the target area according to the difference of the integral gray level values between the target area and other initial stone areas except the target area;
performing negative correlation mapping on the second gray level difference parameter to obtain a gray level similarity parameter of a target area;
And integrating the first gray scale difference parameter and the gray scale similarity parameter of the target area to obtain a first judgment parameter of the target area.
Further, the selecting the center pixel point of the target area based on the gray value includes:
and taking the pixel point corresponding to the minimum value of the gray value in the target area as the central pixel point of the target area.
Further, the obtaining the second determination parameter of the target area according to the distribution of gray values of each pixel point in the direction of the target line segment within the preset window of the target pixel point includes:
In a preset window of target pixel points, a group of pixel points parallel to the target line segment are used as a column of pixel points of the preset window, and a group of pixel points perpendicular to the target line segment are used as a row of pixel points of the preset window;
Selecting any pixel point in a preset window as a pixel point to be analyzed, selecting a pixel point with the smallest gray value difference with the pixel point to be analyzed from the pixel points in the next row of the pixel point to be analyzed in the direction of a target line segment as a reference pixel point of the pixel point to be analyzed, and obtaining a distance difference value of the pixel point to be analyzed according to the difference between the serial number of the column of the pixel point to be analyzed and the serial number of the column of the reference pixel point;
in the direction of the target line segment, according to the difference of gray values between the pixel point to be analyzed and the next pixel point, obtaining the gray change value of the pixel point to be analyzed;
obtaining local distribution characteristic values of target pixel points according to the distribution of the distance difference values and the distribution of the gray scale change values of all the pixel points in a preset window;
and synthesizing the local distribution characteristic values of all the pixel points on the connecting line of all the pixel points and the central pixel point on the edge of the target area to obtain a second judgment parameter of the target area.
Further, the obtaining the local distribution characteristic value of the target pixel point according to the distribution of the distance difference values and the distribution of the gray scale variation values of all the pixel points in the preset window includes:
Taking the variance of the distance difference values of all the pixel points in the preset window as the distance difference confusion of the target pixel point, and taking the variance of the gray level change values of all the pixel points in the preset window as the gray level difference confusion of the target pixel point;
Obtaining a local distribution characteristic value of a target pixel point, wherein the local distribution characteristic value is positively correlated with the distance difference chaos, the local distribution characteristic value is negatively correlated with the gray level difference chaos, and the local distribution characteristic value is a numerical value after normalization processing.
Further, the selectively enhancing the initial stone region in the ultrasound image by combining the first determination parameter and the second determination parameter, and obtaining the enhanced image includes:
Synthesizing the first judging parameter and the second judging parameter of the target area to obtain the calculus possibility of the target area;
and in the ultrasonic image, carrying out contrast enhancement on the initial calculus region with the calculus possibility larger than a preset threshold value, and obtaining an enhanced image.
Further, performing the co-operative ultrasonic examination on the human body part to be detected based on the enhanced image includes:
and analyzing the distribution condition of stones in the human body part to be detected based on the enhanced image, and performing the same-direction operation ultrasonic examination.
Further, two edges of the preset window are parallel to the target line segment.
The invention also provides a system for the same-direction operation intelligent ultrasonic inspection, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes any one step of the same-direction operation intelligent ultrasonic inspection method when executing the computer program.
The invention has the following beneficial effects:
According to the invention, the situation that the skeleton in the human tissue influences the ultrasonic examination of the calculus is considered, partial shadow exists around the calculus region in the ultrasonic image, the effect of enhancing the final image is reduced, and thus the accuracy of the same-direction operation ultrasonic examination is reduced, therefore, the method and the device firstly carry out region segmentation on the ultrasonic image of the human body part to be detected, initially obtain the region representing the calculus, consider that the gray scale of the region representing the calculus in the ultrasonic image is higher, the gray scale difference with the gray scale of the background region is larger, and meanwhile the gray scale between the regions representing the calculus is similar, and reflect the difference condition between the target region and the background region and other initial calculus regions through the acquired first judging parameters, and simultaneously reflect the possibility that the target region is the calculus region in the ultrasonic image, and consider the characteristic that the gray scale value of the pixel point in the calculus region in the ultrasonic image is gradually changed inwards, firstly carry out connection on the edge pixel point and the center pixel point of the target region, analyze the characteristic of the pixel point in the preset window in the direction of the target pixel point, and further enhance the accuracy of the image by combining the acquired first judging parameters with the second judging parameters, thereby enhancing the accuracy of the calculus region is higher, and further enhance the accuracy of the image is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for intelligent ultrasonic inspection in a co-directional operation according to one embodiment of the present invention;
FIG. 2 is a flowchart of a method for acquiring a first determination parameter of a target area according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for obtaining a second determination parameter of a target area according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a preset window of a target pixel point on a target line segment according to an embodiment of the present invention;
Fig. 5 is a schematic view of an ultrasonic image of a human body part to be measured according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of the method and the system for intelligent ultrasonic inspection in the same direction operation according to the invention by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
An embodiment of a method and a system for intelligent ultrasonic inspection by same-direction operation are provided:
The following specifically describes a specific scheme of the method and system for intelligent ultrasonic inspection by the same-direction operation provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for intelligent ultrasonic inspection with unidirectional operation according to an embodiment of the present invention is shown, where the method includes:
Step S1: acquiring an ultrasonic image of a human body part to be detected; and (3) carrying out region segmentation on the ultrasonic image to obtain different initial calculus regions.
The invention provides a method for performing synchronous operation in real time by utilizing an ultrasonic technology, which is particularly widely applied in the field of stone treatment, and can perform related operation, such as guiding a needle or a catheter to a stone position, while observing ultrasonic images, so as to reduce the risk of injuring surrounding tissue structures by mistake, therefore, the quality of the ultrasonic images plays an important role in the ultrasonic inspection in the same direction, the ultrasonic images for checking the stones are generally subjected to image enhancement processing in the related technology, the performance characteristics of the stones in the ultrasonic images are improved, so that the accuracy of the ultrasonic inspection in the same direction is improved, but because the density of the stones is too high, the density distribution is not uniform, the degree of reflection of the ultrasonic waves by different parts is different, partial shadow exists around the stone region in the ultrasonic images, and the ultrasonic images are directly and integrally enhanced, so that the effect of final image enhancement is reduced, and the accuracy of the ultrasonic inspection in the same direction operation is reduced.
The embodiment of the invention firstly uses an ultrasonic inspection instrument to collect ultrasonic images of a human body part to be detected, wherein the human body part to be detected is a position where stones are easy to occur, such as kidney, ureter, common bile duct, bladder and the like, and the stones are reflected to a large degree by the ultrasonic images due to the fact that the density of the stones relative to human tissues is large, so that the stones are usually represented as a highlight area in the ultrasonic images, wherein the ultrasonic images are usually gray-scale images, please refer to fig. 5, and fig. 5 is a schematic diagram of the ultrasonic images of the human body part to be detected, wherein the highlight area is a possible stone area according to one embodiment of the invention.
Because the contrast of the original ultrasonic image is lower, the image quality is poor, the subsequent ultrasonic inspection of the same-direction operation is not facilitated, the ultrasonic image is required to be enhanced, partial shadows exist around the calculus region in the ultrasonic image due to the fact that the density distribution of the calculus is uneven and the reflection degree of the ultrasonic wave is different at different positions, bones existing in human tissues are similar to the calculus, and are all highlight regions, if the ultrasonic image is directly enhanced integrally, the final enhancement effect is reduced, the subsequent identification and inspection of the calculus region in the ultrasonic image are not facilitated, therefore, the embodiment of the invention firstly carries out region segmentation on the ultrasonic image to initially obtain different initial calculus regions, and then can analyze the initial calculus regions based on the gray scale expression characteristics in the calculus regions, thereby realizing the selective enhancement of the initial calculus regions, improving the final image enhancement effect and further improving the accuracy of the lith ultrasonic inspection of the same-direction operation.
Preferably, in an embodiment of the present invention, an ultrasound image is input into a semantic segmentation neural network after training, and a plurality of different initial calculus areas are obtained after the semantic segmentation neural network is processed, where training the semantic segmentation neural network mainly uses a large number of ultrasound image samples of a human body part to be tested, and manually marks the calculus areas in the image samples, and training the semantic segmentation neural network by using a large number of obtained samples, where a loss function used in the training process is a mean square error loss function, and other loss functions, such as a cross entropy loss function, may also be adopted, and the semantic segmentation neural network and the training process thereof are technical means well known to those skilled in the art, and are not described herein.
In other embodiments of the present invention, the region segmentation of the ultrasound image may be achieved by setting seed points in the ultrasound image based on a region growing algorithm, which is a technical means well known to those skilled in the art and will not be described herein.
So far, the ultrasonic image of the human body part to be detected is acquired, and the ultrasonic image is subjected to region segmentation, so that a plurality of initial calculus regions are obtained.
Step S2: and taking any one initial calculus region as a target region, and obtaining a first judgment parameter of the target region according to the difference of pixel gray values between the target region and the background regions except all the initial calculus regions and the difference of pixel gray values between the target region and the other initial calculus regions except the target region.
Because the density of the calculus is larger than that of human tissues, when the ultrasonic waves encounter the calculus, strong reflection can occur, a region with higher brightness is shown in an ultrasonic image, namely a region with higher gray value, and human tissues with lower density are shown in an ultrasonic image, namely a region with lower gray value, so that the difference of pixel gray values between the calculus region and a background region which is shown as human tissues except for the calculus region is larger, and meanwhile, the brightness of different calculus regions is smaller, therefore, the embodiment of the invention takes any one initial calculus region as a target region, analyzes the difference of pixel gray values between the target region and a background region except for all initial calculus regions, and analyzes the difference of pixel gray values between the target region and other initial calculus regions except for the target region, reflects the difference of pixel gray values between the target region and the background region and other initial calculus regions through the acquired first judgment parameters, and simultaneously reflects the possibility that the target region is the calculus region in the ultrasonic image, thereby facilitating the subsequent enhancement of the selectivity of the initial calculus region based on the first judgment parameters, improving the accuracy of the identification of the ultrasonic image, and further improving the accuracy of the ultrasonic image inspection.
Preferably, in one embodiment of the present invention, the method for acquiring the first determination parameter of the target area specifically includes:
referring to fig. 2, a flowchart of a method for acquiring a first determination parameter of a target area according to an embodiment of the invention is shown.
Step S201: because the gray scale performance between the calculus region and the background region representing the human tissue has larger difference, and the gray scale performance between different calculus regions is more similar, the gray scale level of the whole pixel point in each initial calculus region can be analyzed based on the gray scale value of the pixel point, the whole gray scale value of each initial calculus region is obtained, meanwhile, the whole gray scale level of the whole pixel point in the background region except all initial calculus regions is analyzed, the whole gray scale value of the background region is obtained, the whole performance level of the pixel point gray scale values in the initial calculus region and the background region is reflected through the whole gray scale value, and the gray scale difference between the target region and the background region and other initial calculus regions is analyzed based on the whole gray scale value.
In one embodiment of the present invention, the average value of the gray values of all pixels in each initial calculus region may be used as the overall gray value of each initial calculus region, and the average value of the gray values of all pixels in the background region except for all initial calculus regions may be used as the overall gray value of the background region.
In other embodiments of the present invention, the overall gray level of each region may be analyzed by a median, for example, the median of the gray values of all pixels in each initial calculus region may be used as the overall gray value of each initial calculus region, and the median of the gray values of all pixels in the background region except for all initial calculus regions may be used as the overall gray value of the background region.
Step S202: according to the difference of the whole gray values between the target area and the background area, a first gray difference parameter of the target area is obtained, and the larger the first gray difference parameter is, the larger the gray expression difference between the target area and the background area is, the greater the possibility that the target area is a real calculus area is.
In one embodiment of the present invention, the absolute value of the difference of the overall gray value between the target area and the background area may be used as the first gray difference parameter of the target area.
Step S203: considering that the gray level representation difference between the stone region and the background region is larger, and meanwhile, different stone regions are all represented as highlight regions, the gray level representation between the different stone regions is similar, so that the first judgment parameter of the target region can be obtained according to the first gray level difference parameter of the target region and the difference of the whole gray level values between the target region and each other initial stone region except the target region, the larger the first judgment parameter is, the larger the gray level representation difference between the target region and the background region except all the initial stone regions is, and the gray level representation between the target region and the other initial stone regions is similar, and the probability that the target region is a real stone region is further increased.
Preferably, the method for acquiring the first determination parameter of the target area in one embodiment of the present invention further includes:
And obtaining a second gray level difference parameter of the target area according to the difference of the whole gray level values between the target area and other initial stone areas except the target area.
In one embodiment of the present invention, the absolute value of the difference between the average value of the overall gray values of all the initial calculus regions and the overall gray value of the target region may be used as the second gray difference parameter of the target region.
In other embodiments of the present invention, the absolute value of the difference between the overall gray value of the target area and each other initial stone area except the target area may be used as the overall gray difference between the target area and each other initial stone area, and the average value of the overall gray differences between the target area and all other initial stone areas may be used as the second gray difference parameter of the target area.
The smaller the second gray level difference parameter is, the more similar the gray level performance between the target area and other initial calculus areas is, the greater the possibility that the target area is a real calculus area is, so that the second gray level difference parameter of the target area can be subjected to negative correlation mapping to obtain the gray level similarity parameter of the target area, and the larger the gray level similarity parameter is, the more similar the gray level performance between the target area and other initial calculus areas is.
Wherein the negative correlation mapping may utilize, for example, a natural indexThe negative exponential function, the inverse proportion function, the linear function, or the like are realized without limitation and description herein.
The larger the first gray scale difference parameter and the gray scale similarity parameter of the target area, the more likely the target area is a region representing a calculus, so that the first gray scale difference parameter and the gray scale similarity parameter of the target area can be integrated to obtain the first judgment parameter of the target area, and the larger the first judgment parameter, the greater the possibility that the target area is the calculus.
In one embodiment of the invention, the first gray scale difference parameter and the gray scale similarity parameter of the target area can be multiplied to realize the combination of the first gray scale difference parameter and the gray scale similarity parameter, so as to obtain the first judgment parameter of the target area.
In one embodiment of the invention, the first gray scale difference parameter and the gray scale similarity parameter of the target area can be added to realize the combination of the first gray scale difference parameter and the gray scale similarity parameter, so as to obtain the first judgment parameter of the target area.
In one embodiment of the present invention, the expression of the first determination parameter may specifically be, for example:
wherein, A first discrimination parameter representing a target area; representing the overall gray value of the target region; representing the overall gray value of the background area except for all initial stone areas; Represent the first Overall gray values for the individual initial stone regions; representing the number of initial stone regions; Expressed in natural index An exponential function of the base; A first gray scale difference parameter representing a target region; a second gray scale difference parameter representing a target region; and the gray scale similarity parameter of the target area is represented.
Thus, the first discrimination parameters of the target area are obtained, and then the first discrimination parameters of each initial calculus area can be obtained in the same manner.
Step S3: selecting a central pixel point of a target area based on the gray value, taking a connection line of any one pixel point on the edge of the target area and the central pixel point as a target line segment, wherein the direction of the target line segment is the direction that the pixel point on the edge of the target area points to the central pixel point, taking any one pixel point on the target line segment as the target pixel point, and obtaining a second judgment parameter of the target area according to the gray value distribution of each pixel point in the direction of the target line segment in a preset window of the target pixel point; and combining the first judging parameter and the second judging parameter to selectively enhance the initial calculus region in the ultrasonic image, thereby obtaining an enhanced image.
Because the brightness expression characteristics of bones in human tissues in an ultrasonic image are similar to those of a calculus region, the first judgment parameters obtained through the steps are not enough to accurately reflect the possibility that the target region is the calculus region, and therefore the target region is required to be analyzed by combining other gray expression characteristics of the calculus region, the difference of the intensity distribution of the same calculus region, which causes the difference of the degree of reflection of ultrasonic waves at different positions, causes the gray value of pixel points in the calculus region to be gradually reduced inwards, and the embodiment of the invention performs calculation analysis on the second judgment parameters of the target region based on the characteristic that the gray value of the pixel points in the calculus region gradually reduces inwards, and then the initial calculus region can be enhanced by combining the first judgment parameters and the second judgment parameters selectively, so that the final image enhancement effect and the accuracy of the same-direction operation ultrasonic inspection are improved.
Since the gray value of the pixel point in the calculus region has the characteristic of gradually decreasing toward the inside, the central pixel point of the target region can be selected firstly based on the gray value, and the pixel point with the smallest gray value in the target region is selected as the central pixel point of the target region in one embodiment of the invention.
After the central pixel point of the target area is selected, in order to analyze the gradual change characteristics of the gray values of the pixel points in the target area, the pixel points on the edge of the target area and the central pixel point can be connected, meanwhile, in order to facilitate subsequent analysis, one connecting line which is arbitrarily selected is taken as a target line segment, one pixel point is arbitrarily selected as the target pixel point on the target line segment, the direction of the target line segment is specified to be the direction that the pixel point on the edge of the target area points to the central pixel point, a preset window is set for the target pixel point, and the size of the preset window is set as followsThe size of the preset window may also be set by an operator according to a specific implementation scenario, and is not limited herein, so that in the preset window of the target pixel, the distribution characteristics of the gray values of each pixel in the direction of the target line segment are analyzed, and the obtained second determination parameter reflects the similarity degree of the distribution characteristics of the gray values of the pixel in the target area and the stone area, that is, the possibility that the target area is the stone area, from another aspect, where in order to analyze the distribution of the gray values of the pixel in the direction of the target line segment in the preset window, two sides of the preset window set in the embodiment of the present invention are parallel to the target line segment, and the other two sides are perpendicular to the target line segment, referring to fig. 4, fig. 4 is a schematic diagram of the preset window of the target pixel on the target line segment provided in one embodiment of the present invention.
Preferably, in one embodiment of the present invention, the method for acquiring the second determination parameter of the target area specifically includes:
referring to fig. 3, a flowchart of a method for acquiring a second determination parameter of a target area according to an embodiment of the invention is shown.
Step S301: because two edges of the preset window are parallel to the target line segment, in order to facilitate the follow-up accurate analysis of the distribution of the gray values of the pixels in the preset window in the direction of the target line segment, the definition of the pixels in the preset window in the row and the pixels in the column is needed again, in the preset window of the target pixel, a group of pixels parallel to the target line segment are used as a column of pixels in the preset window, a group of pixels perpendicular to the target line segment are used as a row of pixels in the preset window, namely, a row of pixels in the preset window are perpendicular to the target line segment, a column of pixels are parallel to the target line segment, and each row and each column in the preset window corresponds to a serial number.
Step S302: in order to make the analysis clearer, any pixel point in the preset window can be used as the pixel point to be analyzed, the gray value of the pixel point in the calculus area is not in equivalent gradual change in the gradual change process from outside to inside due to uneven density distribution of calculus, so that the gray value of the pixel point in the preset window is not in equivalent change in the direction of a target line segment, the gray value of each row of pixel point in the preset window is larger in difference, therefore, in the direction of the target line segment, the pixel point with the smallest gray value difference with the pixel point to be analyzed can be selected from the next row of pixel points to be analyzed, and can be used as the reference pixel point of the pixel point to be analyzed, and according to the difference between the serial number of the column of the pixel point to be analyzed and the serial number of the column of the reference pixel point, the distance difference value of the pixel point to be analyzed is larger, the distance between the column of the pixel point to be analyzed and the column of the reference pixel point is further, and the gray value of each row of the pixel point to be analyzed can be obtained based on the chaotic distribution characteristic of the distance difference value of all the pixel points in the preset window.
In one embodiment of the present invention, the gray value difference between the pixel point of the next row of the pixel point to be analyzed and the pixel point to be analyzed can be represented by the absolute value of the difference between the gray values of the two gray values, and the absolute value of the difference between the serial number of the column of the pixel point to be analyzed and the serial number of the column of the reference pixel point can be used as the distance difference value of the pixel point to be analyzed.
Step S303: the gray value of the pixel point in the calculus region has the characteristic of gradual change in the interior of the image, so that the gray change value of the pixel point to be analyzed can be obtained according to the difference of the gray value between the pixel point to be analyzed and the next pixel point in the direction of the target line segment, the obtained gray change value reflects the change amount of the gray value of the pixel point to be analyzed in the direction of the target line segment, and the gradual change characteristic of the gray value of the pixel point in the preset window in the direction of the target line segment can be analyzed subsequently based on the distribution characteristic of the gray change values of all the pixel points in the preset window.
In one embodiment of the present invention, the absolute value of the difference value of the gray value between the pixel to be analyzed and the next pixel in the direction of the target line segment can be used as the gray change value of the pixel to be analyzed.
It should be noted that, due to the boundary problem, the pixel point in the next line of the pixel point in the last line of the preset window does not belong to the preset window, so that the pixel point in the last line of the preset window cannot calculate the distance difference value and the gray scale change value, at this time, the boundary of the preset window can be expanded, and the pixel point in one line of the preset window is expanded, so that the distance difference value and the gray scale change value of the pixel point in the last line of the preset window can be calculated, where the expanded pixel point does not really belong to the preset window, and is only performed for conveniently calculating the distance difference value and the gray scale change value of the pixel point in the last line.
Step S304: the more chaotic the distribution of the distance difference values of all the pixel points in the preset window is, the larger the difference of the gray values of the pixel points in each row in the preset window is, the more obvious the gradual change feature of the gray values of the pixel points in the preset window in the direction of the target line segment is, meanwhile, the more consistent the distribution of the distance difference values of all the pixel points in the preset window is, the more consistent the gray value change degree of the pixel points in the preset window in the direction of the target line segment is, the more obvious the gradual change feature of the gray values of the pixel points in the preset window is, so that the distribution of the distance difference values and the gray change value of the pixel points in the preset window can be analyzed, the local gray gradual change degree of the target pixel points is reflected through the obtained local distribution feature value, and the subsequent calculation and analysis of the second judgment parameters of the target area are facilitated.
Preferably, in an embodiment of the present invention, the method for obtaining the local distribution characteristic value of the target pixel point includes:
Taking the variance of the distance difference values of all the pixel points in the preset window as the distance difference confusion of the target pixel point, and taking the variance of the gray level change values of all the pixel points in the preset window as the gray level difference confusion of the target pixel point; in other embodiments of the present invention, standard deviations of distance difference values and gray scale change values of all pixel points in a preset window may also be calculated, so as to obtain a distance difference confusion degree and a gray scale difference confusion degree of a target pixel point.
Obtaining a local distribution characteristic value of the target pixel point, wherein the local distribution characteristic value is positively correlated with the distance difference chaos, the local distribution characteristic value is negatively correlated with the gray level difference chaos, and the local distribution characteristic value is a numerical value after normalization processing. The expression of the local distribution feature value may specifically be, for example:
wherein, Representing local distribution characteristic values of target pixel points; the distance difference confusion of the target pixel points is represented; the gray level difference confusion of the target pixel points is represented, and the gray level change values of all the pixel points in the preset window are not identical because the gradual change characteristics of the gray level values of the pixel points in the calculus region are not equivalent changes, so that the gray level difference confusion of the target pixel points is represented ;Representing the normalization function.
In the process of obtaining the local distribution characteristic value of the target pixel point, the local distribution characteristic valueThe larger the gradient feature of gray values of pixel points of the local part of the target pixel points in the direction of the target line segment is, the more obvious the gradient feature of gray values of pixel points of the local part of the target pixel points in the direction of the target line segment is, and the second judgment parameter of the target region can be calculated and analyzed based on the local distribution feature values of all the pixel points on the connecting line between the edge pixel points and the central pixel point of the target region, wherein the distance difference confusion degreeThe larger the difference value distribution of the distance difference values of all the pixel points in the preset window is, the more the difference of the gray values of the pixel points in each row in the preset window is, and the more obvious the gray gradient characteristics in the target line segment direction in the preset window are, the local distribution characteristic values areThe larger the grey scale difference clutterThe smaller the distance difference value distribution of all the pixel points in the preset window is, the more consistent the gray value change degree of the pixel points in the preset window in the direction of the target line section is, and the more obvious the gray gradual change characteristic in the preset window in the direction of the target line section is, the local distribution characteristic value isThe larger and using normalization function to characterize local distributionIs limited atWithin the range.
In one embodiment of the present invention, the normalization process may specifically be, for example, maximum and minimum normalization processes, and the normalization in the subsequent steps may be performed by using the maximum and minimum normalization processes, and in other embodiments of the present invention, other normalization methods, for example, logarithmic normalization methods, may be selected according to a specific range of values, which will not be described herein.
Step S305: the local distribution characteristic value of each pixel point on each connecting line of the pixel point on the edge of the target area and the central pixel point can be obtained through the same method, and the larger the local distribution characteristic value is, the more obvious the gradual change of the gray value of the local pixel point in the connecting line direction is, so that the local distribution characteristic values of all the pixel points on all the connecting lines can be integrated to obtain a second judging parameter of the target area, the larger the second judging parameter is, the more obvious the characteristic that the gray value of the pixel point in the target area gradually changes to the inside is, and the more the possibility that the target area is a calculus area is further shown.
In one embodiment of the invention, the accumulated values of the local distribution characteristic values of all the pixel points on all the connecting lines can be normalized to obtain the second judgment parameters of the target area, so that the integration of the local distribution characteristic values of all the pixel points on all the connecting lines is realized.
In other embodiments of the present invention, an average value of local distribution feature values of all pixel points on all the connection lines may also be used as the second determination parameter of the target area, so as to implement the integration of the local distribution feature values of all the pixel points on all the connection lines.
The expression of the second determination parameter of the target region may specifically be, for example:
wherein, A second determination parameter indicating a target area; A first pixel point between the pixel point representing the edge of the target area and the central pixel point The first line on the strip connection lineLocal distribution characteristic values of the pixel points; The number of the connecting lines between the pixel points at the edge of the target area and the central pixel point is represented, namely the number of the pixel points at the edge of the target area; A first pixel point between the pixel point representing the edge of the target area and the central pixel point The number of pixel points on the strip connection line; representing the normalization function.
In the process of acquiring the second judging parameter of the target area, the local distribution characteristic value of each pixel point on the connecting lineThe larger the target area, the more obvious the characteristic that the gray value of the pixel point gradually changes to the inside is, and the more likely the target area is a calculus area is, the second judgment parameter is thatThe larger, and using normalization function to characterize local distributionIs limited atAnd in the range, the subsequent calculation and analysis are convenient.
The second judging parameters of each initial calculus region can be obtained through the same method, at the moment, each initial calculus region corresponds to one first judging parameter and one second judging parameter, and the two first judging parameters and the second judging parameters reflect the possibility that the target region is the calculus region from different angles, so that in order to solve the problem that the existing image enhancement algorithm directly enhances the ultrasonic image as a whole to cause poor enhancement effect, the embodiment of the invention selectively enhances the initial calculus region in the ultrasonic image by combining the first judging parameters and the second judging parameters, thereby realizing enhancement of the calculus region in the ultrasonic image only, obtaining an enhanced image with better quality, avoiding the influence of original shadow parts of human bones and the ultrasonic image on the identification of the calculus region in the enhanced image, leading to higher identification degree of the calculus region in the enhanced image, and being convenient for improving the accuracy of subsequent co-operative ultrasonic inspection.
Preferably, the method for acquiring the enhanced image in one embodiment of the present invention specifically includes:
the first judging parameter and the second judging parameter of the target area are integrated, the possibility of the calculus of the target area is obtained, and the larger the possibility of the calculus is, the more the target area is likely to be the calculus area.
In one embodiment of the invention, the product value of the first judging parameter and the second judging parameter can be normalized to obtain the calculus possibility of the target area, so that the first judging parameter and the second judging parameter are integrated.
In other embodiments of the present invention, the sum of the first decision parameter and the second decision parameter may be normalized to obtain the likelihood of the calculus in the target area, so as to integrate the first decision parameter and the second decision parameter.
The greater the calculus likelihood, the more likely the target region is the calculus region, so that the contrast enhancement can be performed on the initial calculus region with the calculus likelihood greater than the preset threshold in the ultrasonic image to obtain an enhanced image, wherein the initial calculus region with the calculus likelihood greater than the preset threshold can be regarded as the calculus region, so that the contrast enhancement is performed only on the calculus region in the ultrasonic image, the image enhancement effect is improved, the preset threshold is set to 0.8, the specific value of the preset threshold can also be set by an implementer according to the specific implementation scene, the limitation is omitted, the contrast enhancement can be performed by using, for example, histogram equalization, which is a technical means well known to those skilled in the art, and the description is omitted here.
Step S4: and performing co-directional operation ultrasonic examination on the human body part to be detected based on the enhanced image.
Because the identification degree of the calculus region in the enhanced image is higher, the distribution condition of the calculus of the human body part to be detected can be observed more clearly through the enhanced image, so that the same-direction operation ultrasonic inspection can be performed on the human body part to be detected based on the enhanced image, and the accuracy of the same-direction operation ultrasonic inspection is improved.
Preferably, in one embodiment of the present invention, the distribution of stones in the body part to be measured can be analyzed based on the enhanced image, and a co-operative ultrasound examination can be performed, for example, by observing the enhanced image, guiding a needle or catheter to a specific stone location, and reducing the risk of injuring surrounding tissues by mistake.
One embodiment of the present invention provides a co-operating intelligent ultrasound examination system, which includes a memory, a processor, and a computer program, where the memory is configured to store a corresponding computer program, the processor is configured to run the corresponding computer program, and the computer program is configured to implement the methods described in steps S1 to S4 when running in the processor.
In summary, in the embodiment of the present invention, an ultrasound image of a human body part to be measured is first obtained; performing region segmentation on the ultrasonic image to obtain different initial stone regions; taking any one initial calculus region as a target region, and obtaining a first judgment parameter of the target region according to the difference of pixel gray values between the target region and the background regions except all the initial calculus regions and the difference of pixel gray values between the target region and the other initial calculus regions except the target region; selecting a central pixel point of a target area based on the gray value, taking a connection line of any one pixel point on the edge of the target area and the central pixel point as a target line segment, wherein the direction of the target line segment is the direction that the pixel point on the edge of the target area points to the central pixel point, taking any one pixel point on the target line segment as the target pixel point, and obtaining a second judgment parameter of the target area according to the gray value distribution of each pixel point in the direction of the target line segment in a preset window of the target pixel point; selectively enhancing an initial calculus region in the ultrasonic image by combining the first judging parameter and the second judging parameter to obtain an enhanced image; and performing co-directional operation ultrasonic examination on the human body part to be detected based on the enhanced image.
An embodiment of an image enhancement method for co-operating ultrasound inspection:
In the ultrasonic detection of stones operated in the same direction, the quality requirement on ultrasonic images is generally higher, the ultrasonic images for detecting the stones are generally subjected to overall enhancement treatment in the related technology, so that the performance characteristics of the stones in the ultrasonic images are improved, but because bones in human tissues can influence the ultrasonic detection of the stones, the density distribution of the stones is not uniform, the degree of reflection of the ultrasonic waves by different parts is different, partial shadows exist around the stones in the ultrasonic images, the overall enhancement of the ultrasonic images is directly carried out, the final image enhancement effect is reduced, and the enhanced image quality cannot reach the ideal effect.
To solve this problem, the present embodiment provides an image enhancement method for co-operating ultrasonic inspection, including:
Step S1: acquiring an ultrasonic image of a human body part to be detected; and (3) carrying out region segmentation on the ultrasonic image to obtain different initial calculus regions.
Step S2: and taking any one initial calculus region as a target region, and obtaining a first judgment parameter of the target region according to the difference of pixel gray values between the target region and the background regions except all the initial calculus regions and the difference of pixel gray values between the target region and the other initial calculus regions except the target region.
Step S3: selecting a central pixel point of a target area based on the gray value, taking a connection line of any one pixel point on the edge of the target area and the central pixel point as a target line segment, wherein the direction of the target line segment is the direction that the pixel point on the edge of the target area points to the central pixel point, taking any one pixel point on the target line segment as the target pixel point, and obtaining a second judgment parameter of the target area according to the gray value distribution of each pixel point in the direction of the target line segment in a preset window of the target pixel point; and combining the first judging parameter and the second judging parameter to selectively enhance the initial calculus region in the ultrasonic image, thereby obtaining an enhanced image.
The steps S1 to S3 are already described in detail in the embodiment of the method and the system for intelligentized ultrasonic inspection in the same direction, and are not described herein again.
The beneficial effects brought by the embodiment are as follows: according to the invention, the situation that the skeleton in the human tissue influences the ultrasonic examination of the calculus is considered, partial shadow exists around the calculus region in the ultrasonic image, the effect of enhancing the final image is reduced, and the accuracy of the same-direction operation ultrasonic examination is reduced, so that the region of the ultrasonic image of the human body to be detected is firstly segmented, the region representing the calculus is initially obtained, the gray scale of the region representing the calculus in the ultrasonic image is considered to be higher, the gray scale difference with the gray scale of the background region is larger, the gray scale between the regions representing the calculus is similar, the acquired first judging parameter reflects the difference condition between the target region and the background region and other initial calculus regions, the possibility that the target region is the calculus region in the ultrasonic image is reflected, the pixel point gray scale value in the calculus region in the ultrasonic image is considered to be gradually changed inwards, the edge pixel point and the center pixel point of the target region are firstly connected, the distribution characteristic of the pixel point gray scale value in the preset window in the direction of the target pixel point is analyzed, the second judging parameter is acquired, the second judging parameter is more reflected from the first judging parameter, the image is more than the first judging parameter, the image is more high, the quality of the calculus is further enhanced, and the image is more difficult to be more important, and the image quality is more important, and the image is more important, and the quality is better, and the image is better can be judged.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. A method of intelligent ultrasonic inspection in a co-directional operation, the method comprising:
Acquiring an ultrasonic image of a human body part to be detected; performing region segmentation on the ultrasonic image to obtain different initial stone regions;
Taking any one initial calculus region as a target region, and obtaining a first judgment parameter of the target region according to the difference of pixel gray values between the target region and the background regions except all the initial calculus regions and the difference of pixel gray values between the target region and the other initial calculus regions except the target region;
Selecting a central pixel point of a target area based on a gray value, taking a connection line of any pixel point on the edge of the target area and the central pixel point as a target line segment, wherein the direction of the target line segment is the direction that the pixel point on the edge of the target area points to the central pixel point, taking any pixel point on the target line segment as the target pixel point, and obtaining a second judgment parameter of the target area according to the distribution of gray values of all the pixel points in the direction of the target line segment in a preset window of the target pixel point; selectively enhancing an initial calculus region in the ultrasonic image by combining the first judging parameter and the second judging parameter to obtain an enhanced image;
and performing the same-direction operation ultrasonic examination on the human body part to be detected based on the enhanced image.
2. The method of claim 1, wherein obtaining the first decision parameter for the target region comprises:
Based on the gray level of the pixel points, analyzing the gray level of the whole pixel points in each initial calculus region to obtain the whole gray level of each initial calculus region, and simultaneously analyzing the gray level of the whole pixel points in the background region except all initial calculus regions to obtain the whole gray level of the background region;
obtaining a first gray scale difference parameter of the target region according to the difference of the integral gray scale values between the target region and the background region;
And obtaining a first judging parameter of the target area according to the first gray level difference parameter of the target area and the difference of the whole gray level values between the target area and other initial stone areas except the target area.
3. The method according to claim 2, wherein obtaining the first determination parameter of the target region according to the first gray scale difference parameter of the target region and the difference of the overall gray scale value between the target region and the initial stone region other than the target region comprises:
Obtaining a second gray level difference parameter of the target area according to the difference of the integral gray level values between the target area and other initial stone areas except the target area;
performing negative correlation mapping on the second gray level difference parameter to obtain a gray level similarity parameter of a target area;
And integrating the first gray scale difference parameter and the gray scale similarity parameter of the target area to obtain a first judgment parameter of the target area.
4. The method for intelligent ultrasound inspection by co-operation according to claim 1, wherein selecting the center pixel of the target region based on the gray value comprises:
and taking the pixel point corresponding to the minimum value of the gray value in the target area as the central pixel point of the target area.
5. The method for intelligent ultrasonic inspection according to claim 1, wherein obtaining the second determination parameter of the target region according to the distribution of gray values of each pixel point in the direction of the target line segment within the preset window of the target pixel point comprises:
In a preset window of target pixel points, a group of pixel points parallel to the target line segment are used as a column of pixel points of the preset window, and a group of pixel points perpendicular to the target line segment are used as a row of pixel points of the preset window;
Selecting any pixel point in a preset window as a pixel point to be analyzed, selecting a pixel point with the smallest gray value difference with the pixel point to be analyzed from the pixel points in the next row of the pixel point to be analyzed in the direction of a target line segment as a reference pixel point of the pixel point to be analyzed, and obtaining a distance difference value of the pixel point to be analyzed according to the difference between the serial number of the column of the pixel point to be analyzed and the serial number of the column of the reference pixel point;
in the direction of the target line segment, according to the difference of gray values between the pixel point to be analyzed and the next pixel point, obtaining the gray change value of the pixel point to be analyzed;
obtaining local distribution characteristic values of target pixel points according to the distribution of the distance difference values and the distribution of the gray scale change values of all the pixel points in a preset window;
and synthesizing the local distribution characteristic values of all the pixel points on the connecting line of all the pixel points and the central pixel point on the edge of the target area to obtain a second judgment parameter of the target area.
6. The method according to claim 5, wherein obtaining the local distribution characteristic value of the target pixel point according to the distribution of the distance difference values and the distribution of the gray scale variation values of all the pixel points in the preset window comprises:
Taking the variance of the distance difference values of all the pixel points in the preset window as the distance difference confusion of the target pixel point, and taking the variance of the gray level change values of all the pixel points in the preset window as the gray level difference confusion of the target pixel point;
Obtaining a local distribution characteristic value of a target pixel point, wherein the local distribution characteristic value is positively correlated with the distance difference chaos, the local distribution characteristic value is negatively correlated with the gray level difference chaos, and the local distribution characteristic value is a numerical value after normalization processing.
7. The method of claim 1, wherein the combining the first decision parameter and the second decision parameter to selectively enhance the initial stone region in the ultrasound image, the obtaining an enhanced image comprises:
Synthesizing the first judging parameter and the second judging parameter of the target area to obtain the calculus possibility of the target area;
and in the ultrasonic image, carrying out contrast enhancement on the initial calculus region with the calculus possibility larger than a preset threshold value, and obtaining an enhanced image.
8. The method for performing intelligent ultrasonic examination in a same direction as in claim 1, wherein performing ultrasonic examination in a same direction on a human body part to be detected based on the enhanced image comprises:
and analyzing the distribution condition of stones in the human body part to be detected based on the enhanced image, and performing the same-direction operation ultrasonic examination.
9. The method of claim 1, wherein the predetermined window has two sides parallel to the target line segment.
10. A co-operating intelligent ultrasound examination system comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1-9 when the computer program is executed by the processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410831346.XA CN118383800B (en) | 2024-06-26 | 2024-06-26 | Intelligent ultrasonic inspection method and system for same-direction operation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410831346.XA CN118383800B (en) | 2024-06-26 | 2024-06-26 | Intelligent ultrasonic inspection method and system for same-direction operation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118383800A CN118383800A (en) | 2024-07-26 |
CN118383800B true CN118383800B (en) | 2024-08-27 |
Family
ID=91999644
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410831346.XA Active CN118383800B (en) | 2024-06-26 | 2024-06-26 | Intelligent ultrasonic inspection method and system for same-direction operation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118383800B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118781140B (en) * | 2024-09-13 | 2024-12-13 | 中国医学科学院阜外医院 | Artificial intelligence-based heart ultrasonic image segmentation method and system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113096116A (en) * | 2021-04-28 | 2021-07-09 | 东南大学 | Automatic detection method for performance of medical ultrasonic equipment based on gray scale image |
CN114126709A (en) * | 2019-07-16 | 2022-03-01 | 阿普劳德医疗公司 | System and method for biomineralization using microbubbles |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100562291C (en) * | 2006-11-08 | 2009-11-25 | 沈阳东软医疗系统有限公司 | A kind of at CT treatment of picture device, method and system |
US20140236488A1 (en) * | 2013-02-19 | 2014-08-21 | Mindways Software, Inc. | Computed Tomography Calibration Systems and Methods |
US11813110B2 (en) * | 2018-06-05 | 2023-11-14 | Vanderbilt University | Advanced ultrasound imaging techniques for kidney stone detection and characterization |
CN114240937B (en) * | 2022-02-24 | 2022-05-27 | 武汉烽火凯卓科技有限公司 | A method and system for detecting kidney stones based on CT slices |
CN117853413A (en) * | 2023-12-06 | 2024-04-09 | 复旦大学 | Bile duct calculus identification system based on deep neural network |
CN118071754B (en) * | 2024-04-24 | 2024-07-19 | 胜利油田中心医院 | Thyroid ultrasound image data processing method |
CN118172380B (en) * | 2024-05-16 | 2024-08-02 | 大连杰伍科技有限公司 | Orthopedics leg bone intelligent recognition segmentation method based on local threshold |
-
2024
- 2024-06-26 CN CN202410831346.XA patent/CN118383800B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114126709A (en) * | 2019-07-16 | 2022-03-01 | 阿普劳德医疗公司 | System and method for biomineralization using microbubbles |
CN113096116A (en) * | 2021-04-28 | 2021-07-09 | 东南大学 | Automatic detection method for performance of medical ultrasonic equipment based on gray scale image |
Also Published As
Publication number | Publication date |
---|---|
CN118383800A (en) | 2024-07-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI501754B (en) | An image recognition system and method of | |
CN104657984A (en) | Automatic extraction method of three-dimensional breast full-volume image regions of interest | |
CN110880177A (en) | Image identification method and device | |
CN118383800B (en) | Intelligent ultrasonic inspection method and system for same-direction operation | |
CN116503392B (en) | Follicular region segmentation method for ovarian tissue analysis | |
CN112508884B (en) | Comprehensive detection device and method for cancerous region | |
CN111784701B (en) | Ultrasonic image segmentation method and system combining boundary feature enhancement and multi-scale information | |
CN105488781A (en) | Dividing method based on CT image liver tumor focus | |
US20230225702A1 (en) | Real-time image analysis for vessel detection and blood flow differentiation | |
TWI624807B (en) | Iterative analysis of medical images | |
CN118197610B (en) | Auxiliary identification method and system for herpetic neuralgia based on structural magnetic resonance | |
KR20040009255A (en) | Apparatus and method for recognizing organ from ultrasound image signal | |
RU2668699C1 (en) | Intellectual method of diagnostics and detection of neoplasms in lungs | |
KR20220061076A (en) | Target data prediction method using correlation information based on multi medical image | |
US20210251601A1 (en) | Method for ultrasound imaging and related equipment | |
CN112308065B (en) | Method, system and electronic equipment for identifying characteristics in ultrasonic image | |
CN111640126B (en) | Artificial intelligent diagnosis auxiliary method based on medical image | |
CN114699106A (en) | Ultrasonic image processing method and equipment | |
Ma et al. | Glomerulus extraction by using genetic algorithm for edge patching | |
CN109948655A (en) | A multi-level-based detection method for endoscopic surgical instruments | |
CN111275719B (en) | Calcification false positive recognition method, device, terminal and medium and model training method and device | |
CN117392040A (en) | Standard section identification method, system, device and storage medium | |
JP2023112416A (en) | Image processing apparatus, image processing method, and program | |
US11983884B2 (en) | Tumoral mass detection system based on magnetic resonance imaging | |
CN118115415B (en) | Ultrasonic image optimization processing method and system based on artificial intelligence |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |