CN118052745B - Gynecological cervical image enhancement processing method - Google Patents
Gynecological cervical image enhancement processing method Download PDFInfo
- Publication number
- CN118052745B CN118052745B CN202410451068.5A CN202410451068A CN118052745B CN 118052745 B CN118052745 B CN 118052745B CN 202410451068 A CN202410451068 A CN 202410451068A CN 118052745 B CN118052745 B CN 118052745B
- Authority
- CN
- China
- Prior art keywords
- pixel point
- sliding window
- probability
- cervical image
- pixel
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 78
- 230000002792 vascular Effects 0.000 claims abstract description 38
- 238000012216 screening Methods 0.000 claims abstract 2
- 238000000034 method Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 description 8
- 210000003679 cervix uteri Anatomy 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000006496 vascular abnormality Effects 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
Classifications
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- 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
- G06T2207/10024—Color 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Probability & Statistics with Applications (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to a gynecological cervical image enhancement processing method, which comprises the following steps: acquiring cervical images; obtaining an R ratio according to three channel values of pixel points in the cervical image; acquiring a plurality of sliding windows; screening suspected blood vessel pixel points according to the R ratio in the sliding window; obtaining the probability of existence of blood vessels according to the R ratio of the suspected blood vessel pixel points; obtaining the probability that the pixel point is a vascular pixel point according to the R ratio; obtaining probability weights according to the number of suspected blood vessel pixel points in the sliding window; obtaining final probability according to the probability of existence of the blood vessel, the probability of the pixel point being the blood vessel pixel point and the probability weight; obtaining an enhanced R channel value according to the R channel value and the final probability of the pixel point; and obtaining the enhanced cervical image according to the enhanced R channel value. According to the invention, the gynecological cervical image is enhanced by calculating the probability that each pixel point in the cervical image is a vascular pixel point.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a gynecological cervical image enhancement processing method.
Background
Gynecological cervical examinations are an important preventive medical measure, and periodic gynecological cervical examinations help to find potential health problems early, providing an opportunity for timely treatment, thereby protecting female health and reducing risk of illness. In gynecological cervical images, blood flow in the cervical region is assessed by observing the vascular state, observing vascular abnormalities, or guiding treatment or surgery is required. By performing enhancement operation on the gynecological cervical image, the gynecological cervical image provides more detailed vascular structure information, is helpful for doctors to evaluate the blood supply condition of tumors, discover potential vascular abnormalities and provide more accurate navigation for treatment or operation, thereby ensuring the accuracy and safety of diagnosis and treatment.
When the linear enhancement method is used for enhancing the gynecological cervical image, the enhancement effect depends on the enhancement degree of the pixel points, and when the enhancement degree is selected improperly, the blood vessels in the enhancement image are not obvious, so that the gynecological cervical image enhancement effect is reduced.
Disclosure of Invention
The invention provides a gynecological cervical image enhancement processing method, which aims to solve the existing problems.
The invention relates to a gynecological cervical image enhancement processing method which adopts the following technical scheme:
an embodiment of the present invention provides a gynecological cervical image enhancement processing method, which includes the following steps:
acquiring an RGB (red green blue) cervical image; obtaining the R ratio of each pixel point in the cervical image according to the RGB three-channel value of each pixel point in the cervical image;
sliding windows are established to slide on the cervical image, so that a plurality of sliding windows are obtained; in each sliding window, a plurality of suspected blood vessel pixel points are screened out according to the R ratio of the pixel points; obtaining the vessel existence probability of each sliding window according to the R duty ratio of all the suspected vessel pixel points;
Obtaining the probability that each pixel point in each sliding window is a vascular pixel point according to the R ratio of each pixel point in each sliding window;
Obtaining probability weights of each sliding window where each pixel is located to each pixel according to the number of suspected blood vessel pixels in each sliding window where each pixel is located in the cervical image;
Obtaining the final probability of each pixel point in the cervical image as a blood vessel pixel point according to the blood vessel existence probability of each sliding window in the cervical image, the probability of each pixel point in each sliding window as a blood vessel pixel point and the probability weight of each sliding window where each pixel point is located to each pixel point;
Obtaining an R channel value after each pixel point is enhanced according to the R channel value of each pixel point in the cervical image and the final probability that each pixel point is a vascular pixel point; and obtaining the reinforced cervical image according to the reinforced R channel value of each pixel point in the cervical image.
Further, the sliding window is established to slide on the cervical image to obtain a plurality of sliding windows, and the method comprises the following specific steps:
On the cervical image, starting from the upper left corner, moving a sliding window with the size of n x n along the horizontal direction and the vertical direction pixel by pixel until the sliding window traverses the whole cervical image to obtain a plurality of sliding windows; wherein n is a preset sliding window side length.
Further, the obtaining the R ratio of each pixel point in the cervical image according to the RGB three-channel value of each pixel point in the cervical image includes the following specific steps:
in the cervical image, calculating the sum of the R channel value, the G channel value and the B channel value of any pixel point, dividing the R channel value of any pixel point by the quotient of the sum, and recording the quotient as the R duty ratio of any pixel point.
Further, in each sliding window, a plurality of suspected blood vessel pixel points are screened out according to the R ratio of the pixel points, which comprises the following specific steps:
In any sliding window, based on the R ratio of each pixel point, all the pixel points in the sliding window are clustered into two class clusters by using a k-means algorithm, the average value of the R ratios of all the pixel points in the two class clusters is calculated respectively, and all the pixel points in the class cluster with the largest average value of the R ratios are marked as suspected blood vessel pixel points.
Further, the obtaining the probability of the existence of the blood vessel in each sliding window according to the R ratio of all the suspected blood vessel pixel points comprises the following specific steps:
And calculating absolute values of differences of average values of R duty ratios of all pixel points in the two class clusters, and recording normalized values of the absolute values as the probability of blood vessels in any sliding window.
Further, the obtaining the probability that each pixel point in each sliding window is a vascular pixel point according to the R ratio of each pixel point in each sliding window includes the following specific calculation modes:
In the method, in the process of the invention, The probability that the s pixel point in the t sliding window is a vascular pixel point; /(I)The number of pixels in the t sliding window is the number; /(I)To get/>And a maximum value of 0; /(I)R duty ratio of the s pixel point in the t sliding window; /(I)R duty ratio of the (R) pixel point in the t sliding window.
Further, according to the number of suspected vascular pixels in each sliding window where each pixel is located in the cervical image, the probability weight of each sliding window where each pixel is located to each pixel is obtained, which comprises the following specific steps:
In the cervical image, counting the number of the suspected blood vessel pixels in each sliding window containing the ith pixel point, calculating the sum value of the number of the suspected blood vessel pixels in all the sliding windows containing the ith pixel point, dividing the number of the suspected blood vessel pixels in the q-th sliding window containing the ith pixel point by the quotient value of the sum value, and recording the quotient value of the number of the suspected blood vessel pixels in the q-th sliding window containing the ith pixel point to the probability weight of the ith pixel point.
Further, the final probability that each pixel point in the cervical image is a blood vessel pixel point is obtained according to the probability that the blood vessel exists in each sliding window in the cervical image, the probability that each pixel point in each sliding window is a blood vessel pixel point, and the probability weight of each sliding window where each pixel point is located to each pixel point, which comprises the following specific calculation modes:
In the method, in the process of the invention, The final probability that the ith pixel point in the cervical image is a vascular pixel point; /(I)The number of sliding windows containing the ith pixel point; /(I)Probability weights of the ith pixel point for the (q) th sliding window containing the ith pixel point; /(I)The existence vessel probability of the (q) th sliding window containing the (i) th pixel point; /(I)The probability that the ith pixel point is a vascular pixel point in the (q) th sliding window containing the ith pixel point.
Further, the method for obtaining the enhanced R channel value of each pixel point according to the R channel value of each pixel point in the cervical image and the final probability that each pixel point is a vascular pixel point comprises the following specific steps:
calculate 255 minus And then calculate the difference and/>And/>, the product of saidThe upward rounding value of the sum value is recorded as the enhanced R channel value of the ith pixel point in the cervical image; said/>R channel value of the ith pixel point in the cervical image; said/>The i-th pixel point in the cervical image is the final probability of the blood vessel pixel point.
Further, the method for obtaining the enhanced cervical image according to the enhanced R channel value of each pixel point in the cervical image comprises the following specific steps:
and replacing the R channel value of each pixel point in the cervical image with the reinforced R channel value corresponding to each pixel point to obtain the reinforced cervical image.
The technical scheme of the invention has the beneficial effects that: according to the invention, the probability that each pixel point in each sliding window is a vascular pixel point is obtained through the R ratio of each pixel point in each sliding window, the probability that the pixel point needs to be enhanced is preliminarily judged, and a preliminary basis is provided for enhancing the gynecological cervical image; according to the number of the suspected vascular pixels in each sliding window where each pixel is located in the cervical image, the probability weight of each sliding window where each pixel is located to each pixel is obtained, the weight calculated by the probability that a plurality of sliding windows containing the pixels are vascular pixels is judged, and the enhancement effect of the gynecological cervical image is improved; according to the probability of the existence of the blood vessel of each sliding window in the cervical image, the probability that each pixel point in each sliding window is a blood vessel pixel point and the probability weight of each sliding window where each pixel point is located to each pixel point, the final probability that each pixel point in the cervical image is the blood vessel pixel point is obtained, the probability that each pixel point in the cervical image is the blood vessel pixel point is judged more accurately, and the gynecological cervical image enhancement effect is better. The gynecological cervical image is enhanced by the accurate and credible final probability, so that the gynecological cervical enhanced image with better enhancement effect is obtained.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart showing steps of a gynecological cervical image enhancement method according to the present invention;
fig. 2 is a schematic view of a gynecological cervix according to the present embodiment;
Fig. 3 is a schematic view of another gynecological cervix according to the present embodiment.
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 specific implementation, structure, characteristics and effects of a gynecological cervical image enhancement processing method according to the invention with reference to the accompanying drawings and preferred embodiments. 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.
The following specifically describes a specific scheme of the gynecological cervical image enhancement processing method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a gynecological cervical image enhancement processing method according to an embodiment of the invention is shown, the method includes the following steps:
Step S001: acquiring an RGB (red green blue) cervical image; and obtaining the R ratio of each pixel point in the cervical image according to the RGB three-channel value of each pixel point in the cervical image.
Specifically, the gynecological endoscope is used for collecting RGB-format cervical images, and gray scale images of the cervical images are shown in fig. 2 and 3.
In the cervical image, the color of the blood vessel region is more biased to red than that of the other tissue region, so that the ratio of the R value of the pixel point of the blood vessel region in the RGB three channels is larger than that of the pixel point of the other tissue region in the RGB three channels.
Specifically, in the cervical image, the calculation mode of the R ratio of the ith pixel point is as follows:
In the method, in the process of the invention, R duty ratio of the ith pixel point; /(I)R channel value of the ith pixel point; /(I)The G channel value of the ith pixel point; /(I)The B-channel value for the i-th pixel.
According to the method, the R ratio of each pixel point in the cervical image is obtained.
Step S002: sliding windows are established to slide on the cervical image, so that a plurality of sliding windows are obtained; in each sliding window, a plurality of suspected blood vessel pixel points are screened out according to the R ratio of the pixel points; and obtaining the vessel existence probability of each sliding window according to the R duty ratio of all the suspected vessel pixel points.
Specifically, on the cervical image, starting from the upper left corner, moving a sliding window with the size of n x n along the horizontal direction and the vertical direction pixel by pixel until the sliding window traverses the whole cervical image, and obtaining a plurality of sliding windows.
The preset sliding window side length n in this embodiment is 10, which is described as an example, and other values may be set in other embodiments, which is not limited in this embodiment.
It should be noted that, since the blood vessel is relatively small, the area distribution in all sliding windows is divided into two cases: 1. the sliding window comprises a blood vessel region and other tissue regions; 2. the sliding window includes only other tissue regions inside. Therefore, in any sliding window, if the sliding window includes a blood vessel region and other tissue regions, the R ratio of the blood vessel pixel points is much larger than that of the other tissue regions, when the pixels in the sliding window are clustered into two types by using a clustering algorithm, the pixel points with larger average R ratio may be the blood vessel pixel points, and the pixel points with smaller average R ratio may be the other tissue region pixel points. If the sliding window only comprises other tissue areas, when the pixel points in the sliding window are clustered into two types by using a clustering algorithm, the two types of pixel points have no great difference with the average R ratio. Therefore, the probability of the existence of the blood vessel region in any sliding window can be judged.
Specifically, in any sliding window, all pixel points in the sliding window are clustered into two class clusters by using a k-means algorithm based on the R ratio of each pixel point, the average value of the R ratios of all the pixel points in the two class clusters is calculated respectively, and all the pixel points in the class cluster with the largest average value of the R ratios are marked as suspected blood vessel pixel points. And calculating absolute values of differences of average values of R duty ratios of all pixel points in the two class clusters, and recording normalized values of all the absolute values as the probability of existence of blood vessels of the sliding window. UsingAnd (5) carrying out normalization processing on the linear normalization function.
According to the method, the probability of the existence of blood vessels in each sliding window in the cervical image is obtained.
Step S003: and obtaining the probability that each pixel point in each sliding window is a vascular pixel point according to the R ratio of each pixel point in each sliding window.
It should be noted that, the image is linearly enhanced only by the existence vessel probability of the sliding window, and the adaptive enhancement degree is not given to each pixel point in the sliding window, so that the enhancement effect of the cervical image is poor. The R ratio of the vascular pixel points is larger than the R ratio of other tissue pixel points, and because the blood vessels are thinner, the number of the vascular pixel points is much smaller than that of the other tissue pixel points in the sliding window, so that the probability that any one pixel point is the vascular pixel point is judged by utilizing the R ratio of any one pixel point and the R ratio of other pixel points in the sliding window.
Specifically, the calculation mode of the probability that the s pixel point in the t sliding window is a vascular pixel point is as follows:
In the method, in the process of the invention, The probability that the s pixel point in the t sliding window is a vascular pixel point; /(I)The number of pixels in the t sliding window is the number; /(I)To get/>And a maximum value of 0; /(I)R duty ratio of the s pixel point in the t sliding window; /(I)R duty ratio of the (R) pixel point in the t sliding window.
According to the method, the probability that each pixel point in each sliding window is a vascular pixel point is obtained.
Step S004: and obtaining the probability weight of each sliding window where each pixel is located to each pixel according to the number of the suspected blood vessel pixels in each sliding window where each pixel is located in the cervical image.
Note that, since the probability that each pixel is a blood vessel pixel is obtained by using a sliding window method, there are cases where a part of pixels exist in a plurality of sliding windows. For any pixel point in the cervical image, the expression degree of the probability that the pixel point is a blood vessel pixel point is different in different sliding windows, specifically, if the number of the blood vessel pixel points in the sliding window containing the pixel point is small, the probability that the pixel point is the blood vessel pixel point is larger; if there are more vascular pixels in the sliding window containing the pixels, the probability that the pixels are vascular pixels is smaller, so that the probability weight of each sliding window to the ith pixel is calculated according to the difference of clustering results of the pixels in each sliding window containing the ith pixel in the cervical image.
Specifically, the calculation mode of the probability weight of the ith pixel point by the qth sliding window containing the ith pixel point is as follows:
In the method, in the process of the invention, Representing probability weights of the ith sliding window containing the ith pixel point to the ith pixel point; /(I)Representing the number of suspected vascular pixels in the (q) th sliding window containing the (i) th pixel; /(I)Is the number of sliding windows containing the ith pixel point.
According to the method, the probability weight of each sliding window where each pixel point is located on the pixel point is obtained.
Step S005: and obtaining the final probability that each pixel point in the cervical image is a blood vessel pixel point according to the blood vessel probability of each sliding window in the cervical image, the probability that each pixel point in each sliding window is a blood vessel pixel point and the probability weight of each sliding window where each pixel point is located to each pixel point.
The probability weight of the ith sliding window containing the ith pixel point to the ith pixel point reflects the calculation weight of the final probability of the ith sliding window to the ith pixel point being a blood vessel pixel point. The probability of existence of the blood vessel of the t sliding window is used as the reliability of the probability that the s pixel point in the t sliding window is the blood vessel pixel point, so that the final probability that any pixel point in the cervical image is the blood vessel pixel point can be accurately judged.
Specifically, the calculation mode of the final probability that the ith pixel point in the cervical image is a vascular pixel point is as follows:
In the method, in the process of the invention, The final probability that the ith pixel point in the cervical image is a vascular pixel point; /(I)The number of sliding windows containing the ith pixel point; /(I)Probability weights of the ith pixel point for the (q) th sliding window containing the ith pixel point; /(I)The existence vessel probability of the (q) th sliding window containing the (i) th pixel point; /(I)The probability that the ith pixel point is a vascular pixel point in the (q) th sliding window containing the ith pixel point.
According to the method, the final probability that each pixel point in the cervical image is a vascular pixel point is obtained.
Step S006: obtaining an R channel value after each pixel point is enhanced according to the R channel value of each pixel point in the cervical image and the final probability that each pixel point is a vascular pixel point; and obtaining the reinforced cervical image according to the reinforced R channel value of each pixel point in the cervical image.
When the cervical image is enhanced, the enhancement is mainly performed on the blood vessel pixel points in the cervical image, so that the greater the final probability that any one pixel point in the cervical image is the blood vessel pixel point, the greater the enhancement degree of the any one pixel point. Because the R channel value of the blood vessel pixel point is larger, the R channel value of the blood vessel pixel point is mainly further enhanced in order to enhance the color contrast of the blood vessel region and other tissue regions.
Specifically, the calculation mode of the enhanced R channel value of the ith pixel point in the cervical image is as follows:
In the method, in the process of the invention, The enhanced R channel value of the ith pixel point in the cervical image; /(I)R channel value of the ith pixel point in the cervical image; /(I)Is the maximum value of the R channel of the pixel point; /(I)The final probability that the ith pixel point in the cervical image is a vascular pixel point; /(I)As a round-up function.
According to the method, the enhanced R channel value of each pixel point in the cervical image is obtained. And replacing the R channel value of each pixel point in the cervical image with the reinforced R channel value corresponding to each pixel point to obtain the reinforced cervical image.
The present invention has been completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (6)
1. A gynecological cervical image enhancement processing method, which is characterized by comprising the following steps:
acquiring an RGB (red green blue) cervical image; obtaining the R ratio of each pixel point in the cervical image according to the RGB three-channel value of each pixel point in the cervical image;
sliding windows are established to slide on the cervical image, so that a plurality of sliding windows are obtained; in each sliding window, a plurality of suspected blood vessel pixel points are screened out according to the R ratio of the pixel points; obtaining the vessel existence probability of each sliding window according to the R duty ratio of all the suspected vessel pixel points;
Obtaining the probability that each pixel point in each sliding window is a vascular pixel point according to the R ratio of each pixel point in each sliding window;
According to the R ratio of each pixel point in each sliding window, the probability that each pixel point in each sliding window is a vascular pixel point is obtained, and the specific calculation method comprises the following steps:
In the method, in the process of the invention, The probability that the s pixel point in the t sliding window is a vascular pixel point; /(I)The number of pixels in the t sliding window is the number; /(I)To get/>And a maximum value of 0; /(I)R duty ratio of the s pixel point in the t sliding window; /(I)R duty ratio of the R pixel point in the t sliding window;
Obtaining probability weights of each sliding window where each pixel is located to each pixel according to the number of suspected blood vessel pixels in each sliding window where each pixel is located in the cervical image;
According to the number of suspected blood vessel pixel points in each sliding window where each pixel point is located in the cervical image, the probability weight of each sliding window where each pixel point is located to each pixel point is obtained, and the method comprises the following specific steps:
Counting the number of the suspected blood vessel pixels in each sliding window containing the ith pixel point in the cervical image, calculating the sum value of the number of the suspected blood vessel pixels in all the sliding windows containing the ith pixel point, dividing the number of the suspected blood vessel pixels in the q-th sliding window containing the ith pixel point by the quotient value of the sum value, and recording the quotient value of the number of the suspected blood vessel pixels in the q-th sliding window containing the ith pixel point to the ith pixel point as the probability weight of the q-th sliding window containing the ith pixel point;
Obtaining the final probability of each pixel point in the cervical image as a blood vessel pixel point according to the blood vessel existence probability of each sliding window in the cervical image, the probability of each pixel point in each sliding window as a blood vessel pixel point and the probability weight of each sliding window where each pixel point is located to each pixel point;
The final probability that each pixel point in the cervical image is a blood vessel pixel point is obtained according to the existence blood vessel probability of each sliding window in the cervical image, the probability that each pixel point in each sliding window is a blood vessel pixel point and the probability weight of each sliding window where each pixel point is located to each pixel point, and the specific calculation method comprises the following steps:
In the method, in the process of the invention, The final probability that the ith pixel point in the cervical image is a vascular pixel point; /(I)The number of sliding windows containing the ith pixel point; /(I)Probability weights of the ith pixel point for the (q) th sliding window containing the ith pixel point; The existence vessel probability of the (q) th sliding window containing the (i) th pixel point; /(I) The probability that the ith pixel point is a vascular pixel point in the (q) th sliding window containing the ith pixel point;
Obtaining an R channel value after each pixel point is enhanced according to the R channel value of each pixel point in the cervical image and the final probability that each pixel point is a vascular pixel point; obtaining an enhanced cervical image according to the enhanced R channel value of each pixel point in the cervical image;
The method for obtaining the R channel value after the enhancement of each pixel point according to the R channel value of each pixel point in the cervical image and the final probability that each pixel point is a vascular pixel point comprises the following specific steps:
calculate 255 minus And then calculate the difference and/>And/>, the product of saidThe upward rounding value of the sum value is recorded as the enhanced R channel value of the ith pixel point in the cervical image; said/>R channel value of the ith pixel point in the cervical image; said/>The i-th pixel point in the cervical image is the final probability of the blood vessel pixel point.
2. The gynecological cervical image enhancement processing method according to claim 1, wherein the step of creating sliding windows to slide on the cervical image to obtain a plurality of sliding windows comprises the following specific steps:
On the cervical image, starting from the upper left corner, moving a sliding window with the size of n x n along the horizontal direction and the vertical direction pixel by pixel until the sliding window traverses the whole cervical image to obtain a plurality of sliding windows; wherein n is a preset sliding window side length.
3. The gynecological cervical image enhancement processing method according to claim 1, wherein the obtaining the R ratio of each pixel point in the cervical image according to the RGB three-channel value of each pixel point in the cervical image comprises the following specific steps:
in the cervical image, calculating the sum of the R channel value, the G channel value and the B channel value of any pixel point, dividing the R channel value of any pixel point by the quotient of the sum, and recording the quotient as the R duty ratio of any pixel point.
4. The gynecological cervical image enhancement processing method according to claim 1, wherein the step of screening out a plurality of suspected blood vessel pixels in each sliding window according to the R ratio of the pixels comprises the following specific steps:
In any sliding window, based on the R ratio of each pixel point, all the pixel points in the sliding window are clustered into two class clusters by using a k-means algorithm, the average value of the R ratios of all the pixel points in the two class clusters is calculated respectively, and all the pixel points in the class cluster with the largest average value of the R ratios are marked as suspected blood vessel pixel points.
5. The gynecological cervical image enhancement processing method according to claim 4, wherein the obtaining the probability of existence of blood vessels in each sliding window according to the R ratio of all the suspected blood vessel pixels comprises the following specific steps:
And calculating absolute values of differences of average values of R duty ratios of all pixel points in the two class clusters, and recording normalized values of the absolute values as the probability of blood vessels in any sliding window.
6. The gynecological cervical image enhancement processing method according to claim 1, wherein the obtaining the enhanced cervical image according to the enhanced R-channel value of each pixel point in the cervical image comprises the following specific steps:
and replacing the R channel value of each pixel point in the cervical image with the reinforced R channel value corresponding to each pixel point to obtain the reinforced cervical image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410451068.5A CN118052745B (en) | 2024-04-16 | 2024-04-16 | Gynecological cervical image enhancement processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410451068.5A CN118052745B (en) | 2024-04-16 | 2024-04-16 | Gynecological cervical image enhancement processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118052745A CN118052745A (en) | 2024-05-17 |
| CN118052745B true CN118052745B (en) | 2024-06-18 |
Family
ID=91046956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410451068.5A Active CN118052745B (en) | 2024-04-16 | 2024-04-16 | Gynecological cervical image enhancement processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118052745B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335267A (en) * | 2019-07-05 | 2019-10-15 | 华侨大学 | A kind of cervical lesions method for detecting area |
| CN117523235A (en) * | 2024-01-02 | 2024-02-06 | 大连壹致科技有限公司 | A patient wound intelligent identification system for surgical nursing |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117557460B (en) * | 2024-01-12 | 2024-03-29 | 济南科汛智能科技有限公司 | Angiography image enhancement method |
| CN117830308B (en) * | 2024-03-05 | 2024-05-10 | 西安交通大学医学院第一附属医院 | Intelligent contrast analysis method for angiography before and after interventional operation |
| CN117853386B (en) * | 2024-03-08 | 2024-05-28 | 陕西省人民医院(陕西省临床医学研究院) | Tumor image enhancement method |
-
2024
- 2024-04-16 CN CN202410451068.5A patent/CN118052745B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335267A (en) * | 2019-07-05 | 2019-10-15 | 华侨大学 | A kind of cervical lesions method for detecting area |
| CN117523235A (en) * | 2024-01-02 | 2024-02-06 | 大连壹致科技有限公司 | A patient wound intelligent identification system for surgical nursing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118052745A (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115359052B (en) | Medical image enhancement method based on clustering algorithm | |
| CN110751636B (en) | Fundus image retinal arteriosclerosis detection method based on improved coding and decoding network | |
| CN113420826B (en) | Liver focus image processing system and image processing method | |
| CN116503392B (en) | Follicular region segmentation method for ovarian tissue analysis | |
| CN110415219B (en) | Medical image processing method and device based on depth segmentation network, equipment and storage medium | |
| CN110991254B (en) | Ultrasonic image video classification prediction method and system | |
| CN110880366A (en) | Medical image processing system | |
| CN117934474B (en) | Gastrointestinal microscopy image enhancement processing method | |
| CN115908449A (en) | 2.5D medical CT image segmentation method and device based on improved UNet model | |
| CN115035127A (en) | Retinal vessel segmentation method based on generative confrontation network | |
| CN116912255A (en) | Follicular region segmentation method for ovarian tissue analysis | |
| CN114066846A (en) | CTP non-acute occlusion ischemia assessment method and system based on deep learning | |
| CN118052745B (en) | Gynecological cervical image enhancement processing method | |
| CN112634308B (en) | Nasopharyngeal carcinoma target area and organ-at-risk delineating method based on different receptive fields | |
| CN113160256B (en) | MR image placenta segmentation method for multitasking countermeasure model | |
| CN117830308B (en) | Intelligent contrast analysis method for angiography before and after interventional operation | |
| WO2022047627A1 (en) | Deep learning prediction method and application thereof | |
| CN113130050A (en) | Medical information display method and system | |
| CN114764855A (en) | Intelligent cystoscope tumor segmentation method, device and equipment based on deep learning | |
| CN116228767B (en) | X-ray lung tumor image processing method based on computer vision | |
| CN118037803A (en) | Gynaecology and obstetrics's disease medical treatment big data management system | |
| CN116739988A (en) | Deep learning cerebral hemorrhage classification method based on multi-difficulty course learning | |
| CN117934497A (en) | Intracranial hematoma segmentation method based on CNN and attention mechanism | |
| Dandan et al. | A multi-model organ segmentation method based on abdominal ultrasound image | |
| CN116416452A (en) | Lung adenocarcinoma invasive intelligent classification system based on two-stage deep learning model |
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 |