CN112801979B - Scoliosis detection method and system based on uncertainty reasoning - Google Patents
Scoliosis detection method and system based on uncertainty reasoning Download PDFInfo
- Publication number
- CN112801979B CN112801979B CN202110119695.5A CN202110119695A CN112801979B CN 112801979 B CN112801979 B CN 112801979B CN 202110119695 A CN202110119695 A CN 202110119695A CN 112801979 B CN112801979 B CN 112801979B
- Authority
- CN
- China
- Prior art keywords
- uncertainty
- reasoning
- key
- evidence
- module
- 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
- 206010039722 scoliosis Diseases 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 23
- 210000004394 hip joint Anatomy 0.000 claims description 14
- 210000000707 wrist Anatomy 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 210000000988 bone and bone Anatomy 0.000 claims description 6
- 238000012805 post-processing Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 210000001664 manubrium Anatomy 0.000 claims description 4
- 230000001629 suppression Effects 0.000 claims description 4
- 238000011282 treatment Methods 0.000 claims description 4
- 210000001562 sternum Anatomy 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 description 7
- 210000001624 hip Anatomy 0.000 description 4
- 210000000245 forearm Anatomy 0.000 description 3
- 210000002758 humerus Anatomy 0.000 description 3
- 210000003205 muscle Anatomy 0.000 description 3
- 210000000115 thoracic cavity Anatomy 0.000 description 3
- 238000005452 bending Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000399 orthopedic effect Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 208000003251 Pruritus Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 208000022567 adolescent idiopathic scoliosis Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011436 cob Substances 0.000 description 1
- 210000002808 connective tissue Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007803 itching Effects 0.000 description 1
- 201000001119 neuropathy Diseases 0.000 description 1
- 230000007823 neuropathy Effects 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 238000002559 palpation Methods 0.000 description 1
- 210000003049 pelvic bone Anatomy 0.000 description 1
- 210000004197 pelvis Anatomy 0.000 description 1
- 208000033808 peripheral neuropathy Diseases 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000000623 ulna Anatomy 0.000 description 1
Classifications
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
- A61B5/4538—Evaluating a particular part of the muscoloskeletal system or a particular medical condition
- A61B5/4566—Evaluating the spine
-
- 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
- G06T2207/30008—Bone
- G06T2207/30012—Spine; Backbone
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Physical Education & Sports Medicine (AREA)
- Dentistry (AREA)
- Rheumatology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a scoliosis detection method based on uncertainty reasoning, which comprises the following steps: s1: acquiring a back image, and preprocessing the back image; s2: setting each key skeleton point, and extracting two-dimensional position information of each key skeleton point from the preprocessed back image; s3: obtaining initial evidence of uncertainty corresponding to each key skeleton point through geometric calculation; s4: and carrying out uncertainty reasoning by using the initial uncertainty evidence to obtain a final conclusion as a scoliosis detection result. The invention also provides a scoliosis detection system based on uncertainty reasoning, which comprises a man-machine interface module, an image processing module, a key point extraction module, a geometric calculation module, a reasoning module, a knowledge base, a database and an interpretation module. The invention provides a scoliosis detection method and system based on uncertainty reasoning, which solve the problem that the existing scoliosis detection method is not convenient enough.
Description
Technical Field
The invention relates to the technical field of spine detection, in particular to a scoliosis detection method and system based on uncertainty reasoning.
Background
Scoliosis refers to a lateral curvature of a person' S spine, which may be S-shaped or C-shaped in shape. Scoliosis may occur at the cervical, thoracic, lumbar, etc., with thoracic and lumbar vertebrae being the most common. Eighty-five percent of scoliosis is unexplained, the remainder may be secondary to muscle neuropathy or abnormalities in bone and connective tissue. Some people have stable and unchanged scoliosis, and some people have gradual increase with time. Early treatment was found to be effective in preventing scoliosis. For example, adolescent idiopathic scoliosis often causes no obvious clinical symptoms in the early stage of the patients, is not painful and itching, has high concealment at the moment, is often easy to ignore, and misses the optimal treatment opportunity. As age increases, scoliosis increases in magnitude and the difficulty of treatment increases.
The existing scoliosis detection method is diversified, and mainly comprises plumb line detection method, adam type examination, scoliosis degree instrument, muscle group palpation and muscle strength test, bipedal length examination, cobb's angulation method, spine elasticity and skeleton development examination and the like. The lateral curvature of the spine is qualitatively and quantitatively analyzed by comprehensively examining the front and side surfaces of the wrist ulna, the pelvic bones, the cervical vertebrae, the thoracic vertebrae, the lumbar vertebrae, the spine, the left and right pelvis, and the like. However, most detection methods still need to be combined with the method of further checking by orthopedics doctors, the process is complicated, the combination of X-rays and manpower is needed, the detection is not convenient enough, the detection efficiency is low, and the cost is high.
In the prior art, for example, 2021-01-08 issued Chinese patent, a method and a device for detecting scoliosis, with bulletin number of CN109785297B, can obtain the scoliosis condition of a tested person by utilizing images collected by a scanner to perform identification analysis under the non-radiation condition of non-X rays, but does not combine uncertainty reasoning to detect, and the interpretation of detection results is not strong enough.
Disclosure of Invention
The invention provides a scoliosis detection method and a system based on uncertainty reasoning, which are used for overcoming the technical defect that the existing scoliosis detection method is not convenient enough.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a scoliosis detection method based on uncertainty reasoning comprises the following steps:
s1: acquiring a back image, and preprocessing the back image;
s2: setting each key skeleton point, and extracting two-dimensional position information of each key skeleton point from the preprocessed back image;
s3: obtaining initial uncertainty evidence corresponding to each key skeleton point through geometric calculation according to the two-dimensional position information of each key skeleton point;
s4: and carrying out uncertainty reasoning by using the initial uncertainty evidence to obtain a final conclusion as a scoliosis detection result.
Preferably, in step S1, preprocessing the back image includes: the back image was converted to RGB format and the back image was corrected to 256 x 256 in size, and then the gray values at all positions of the R, G, B three-channel gray map of the back image were normalized.
Preferably, the set key skeletal points include: left shoulder inflection point, right shoulder inflection point, left arm wrist, right arm wrist, left elbow, right elbow, top of head, upper neck, manubrium, sacral midpoint, left hip joint and right hip joint.
Preferably, in step S2, extracting two-dimensional position information of each key skeleton point from the preprocessed back image includes the steps of:
s2.1: extracting channel heat maps of key bone points from the preprocessed back image by adopting a convolution neural network based on heat map regression;
s2.2: carrying out post-processing on the confidence coefficient of each channel heat map by utilizing a non-maximum suppression mode;
s2.3: and selecting the maximum confidence coefficient in each channel heat map after post-processing as two-dimensional position information of the corresponding key skeleton point, and mapping the maximum confidence coefficient into a range from-1 to convert the maximum confidence coefficient into the confidence coefficient of the corresponding key skeleton point.
Preferably, the uncertainty initial evidence comprises human body posture distance information, human body posture angle information and evidence credibility;
wherein,,
the human body posture distance information is obtained by calculating the two-dimensional Euclidean distance approximation of adjacent key skeleton points through the Euclidean distance formula;
the human body posture angle information is approximately obtained according to the human body posture distance information through a cosine formula;
evidence credibility is obtained through an uncertainty calculation method.
Preferably, before the uncertainty reasoning, the method further comprises: and calculating the included angle between the back cross section and the shooting direction of the tested person according to the sacrum midpoint, the left hip joint, the right hip joint, the left shoulder inflection point, the right key inflection point and the sternum handle, and correcting the human body posture distance information and the human body posture angle information.
Preferably, in step S4, the uncertainty reasoning includes a combination of evidence uncertainty calculation, uncertainty transfer, and uncertainty conclusion synthesis.
Preferably, in the uncertainty reasoning process, when the number of uncertainty generating rules in the knowledge base cannot obtain a reasoning result or the number of reasoning times reaches a preset upper limit, the reasoning is considered to be abnormal, and abnormal conditions are fed back in a visual mode through a display screen.
Preferably, the step of obtaining the scoliosis detection result further comprises the following steps: sequencing all intermediate conclusions and final conclusions obtained in the uncertainty reasoning process according to the time sequence, and carrying out visual feedback through a display screen in sequence.
The scoliosis detection system based on the uncertainty reasoning is used for realizing the scoliosis detection method based on the uncertainty reasoning and comprises a man-machine interface module, an image processing module, a key point extraction module, a geometric calculation module, a reasoning module, a knowledge base, a database and an interpretation module; wherein,,
the human-machine interface module comprises: the device comprises a camera for acquiring back images, a display screen for performing visualization and a loudspeaker for performing audio feedback;
the image processing module is used for preprocessing the back image;
the key point extraction module is used for setting key skeleton points and extracting two-dimensional position information and corresponding credibility of each key skeleton point from the preprocessed back image;
the geometric calculation module is used for carrying out geometric calculation according to the two-dimensional position information of the key skeleton points to obtain initial evidence of uncertainty;
the reasoning module is used for carrying out uncertainty reasoning on the initial uncertainty evidence according to the uncertainty knowledge in the knowledge base to obtain an intermediate conclusion and a final conclusion, and taking the final conclusion as a scoliosis detection result;
the knowledge base is used for storing uncertainty knowledge related to scoliosis detection; the uncertainty knowledge is expressed in terms of uncertainty-generating rules;
the database is used for storing initial evidence of uncertainty, an intermediate reasoning process, intermediate conclusions, final conclusions and corresponding credibility;
the interpretation module is used for recording each intermediate conclusion and corresponding credibility obtained in the uncertainty reasoning process, converting each intermediate conclusion into a fuzzy conclusion according to different regions according to the credibility, and sequencing the intermediate conclusions and the final conclusions according to a time sequence.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the invention provides a scoliosis detection method and a scoliosis detection system based on uncertainty reasoning, which are characterized in that key skeleton point geometric relation information with credibility is obtained from a back image through geometric calculation, and uncertainty reasoning is carried out on the key skeleton point geometric relation information with credibility and an uncertainty generating rule to obtain a scoliosis detection result, so that the scoliosis detection is realized without carrying out the scoliosis detection under a specific environment or any wearable equipment, the convenience of the scoliosis detection is improved, and the detection cost is reduced.
Drawings
FIG. 1 is a flow chart of the steps performed in the technical scheme of the invention;
FIG. 2 is a schematic diagram of a modular connection according to the present invention;
wherein: 1. a human-machine interface module; 2. an image processing module; 3. a key point extraction module; 4. a geometric calculation module; 5. an inference module; 6. a knowledge base; 7. a database; 8. and an interpretation module.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
for the purpose of better illustrating the embodiments, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the actual product dimensions;
it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
Example 1
As shown in fig. 1, a scoliosis detection method based on uncertainty reasoning includes the following steps:
s1: acquiring a back image, and preprocessing the back image; in actual implementation, acquiring an image of the back of the right upper half body of a human body through a camera;
s2: setting each key skeleton point, and extracting two-dimensional position information of each key skeleton point from the preprocessed back image;
s3: obtaining initial uncertainty evidence corresponding to each key skeleton point through geometric calculation according to the two-dimensional position information of each key skeleton point;
more specifically, the uncertainty initial evidence comprises human body posture distance information, human body posture angle information and evidence credibility; wherein,,
calculating the two-dimensional Euclidean distance approximation of adjacent key skeleton points through the Euclidean distance formula to obtain human body posture distance information;
approximately obtaining human body posture angle information according to human body posture distance information through a cosine formula;
obtaining evidence credibility through an uncertainty calculation method;
in a specific implementation process, the human body posture distance information includes: the left humerus length, the right humerus length, the left forearm length, the right forearm length, the left shoulder inflection point-manubrium distance, the right shoulder inflection point-manubrium distance, the top-upper cervical distance, the upper neck-manubrium distance, the manubrium-sacrum midpoint distance, the left hip joint-sacrum midpoint distance, the right hip joint-sacrum midpoint distance, the left elbow-manubrium distance, the left elbow-sacrum midpoint distance, the left elbow-upper cervical distance, the left elbow-overhead distance, the left arm wrist-manubrium distance, the left arm wrist-sacrum midpoint distance, the left arm wrist-upper cervical distance, the left arm wrist-overhead distance, the right elbow-manubrium distance, the right elbow-sacrum midpoint distance, the right elbow-upper cervical distance, the right arm wrist-overhead distance, the right arm wrist-manubrium distance, the right arm wrist-sacrum midpoint distance, the right arm wrist-upper cervical distance, and the right arm-overhead distance;
the human body posture angle information includes: left shoulder corner, right shoulder corner, left shoulder-manubrium-upper neck corner, right shoulder-manubrium-upper neck corner, top of head-upper neck-manubrium corner, upper neck-manubrium-sacrum midpoint corner, left hip joint-body midline angle, right hip joint-body midline angle, and left shoulder corner-manubrium-right shoulder corner;
s4: carrying out uncertainty reasoning by using initial uncertainty evidence to obtain a final conclusion as a scoliosis detection result;
in actual implementation, uncertainty initial evidence is tried to be subjected to uncertainty matching with uncertainty generating rules in a knowledge base 6 through an inference module 5, and an intermediate conclusion is obtained through uncertainty transfer and uncertainty conclusion synthesis; then transmitting the intermediate conclusion and the initial evidence of the round into a database 7 as the initial evidence of the next round of uncertainty reasoning, and repeatedly carrying out the uncertainty reasoning through a reasoning module 5 until reaching a preset reasoning ending condition to obtain a final conclusion as a scoliosis detection result;
wherein the uncertainty conclusion synthesis algorithm is as follows:
CF 1,2 (H)＝CF 1 (H)+CF 2 (H)-CF 1 (H)CF 2 (H)，CF 1 (H)≥0,CF 2 (H)≥0
CF 1,2 (H)＝CF 1 (H)+CF 2 (H)+CF 1 (H)CF 2 (H)，CF 1 (H)<0,CF 2 (H)<0
CF 1,2 (H)＝(CF 1 (H)+CF 2 (H))/(1-min{CF 1 (H)CF 2 (H) }), other cases
Wherein CF is the confidence level of the corresponding conclusion, and the synthesized conclusion contains all uncertainty information of the sub-conclusion.
More specifically, in step S1, preprocessing the back image includes: the back image was converted to RGB format and the back image size was corrected to 256 x 256, then the gray values at all positions of the R, G, B three channel gray map of the back image were normalized, mapping the gray values from 0 to 255 to the 0 to 1 interval.
More specifically, the key skeletal points set include: left shoulder inflection point, right shoulder inflection point, left arm wrist, right arm wrist, left elbow, right elbow, top of head, upper neck, manubrium, sacral midpoint, left hip joint and right hip joint.
More specifically, in step S2, extracting two-dimensional position information of each key skeleton point from the preprocessed back image includes the steps of:
s2.1: extracting channel heat maps of key bone points from the preprocessed back image by adopting a convolution neural network based on heat map regression; taking the confidence as a value of the heat map;
s2.2: carrying out post-processing on the confidence coefficient of each channel heat map by utilizing a non-maximum suppression mode;
s2.3: and selecting the maximum confidence coefficient in each channel heat map after post-processing as two-dimensional position information of the corresponding key skeleton point, and mapping the maximum confidence coefficient into a range from-1 to convert the maximum confidence coefficient into the confidence coefficient of the corresponding key skeleton point.
More specifically, before making the uncertainty reasoning, the method further comprises: and calculating the included angle between the back cross section and the shooting direction of the tested person according to the sacrum midpoint, the left hip joint, the right hip joint, the left shoulder inflection point, the right key inflection point and the sternum handle, and correcting the human body posture distance information and the human body posture angle information.
More specifically, in step S4, uncertainty reasoning includes combining evidence uncertainty computation, uncertainty delivery, and uncertainty conclusion synthesis.
More specifically, in the uncertainty reasoning process, when the number of uncertainty generating rules in the knowledge base 6 cannot obtain the reasoning result or the number of reasoning times reaches a preset upper limit, the reasoning is considered to be abnormal, and the abnormal condition is fed back in a visual mode through a display screen.
More specifically, the method further comprises the following steps after obtaining the scoliosis detection result: sequencing all intermediate conclusions and final conclusions obtained in the uncertainty reasoning process according to the time sequence, and carrying out visual feedback through a display screen in sequence.
Example 2
As shown in fig. 2, a scoliosis detection system based on uncertainty reasoning is used for implementing the scoliosis detection method based on uncertainty reasoning, and includes a man-machine interface module 1, an image processing module 2, a key point extraction module 3, a geometric calculation module 4, a reasoning module 5, a knowledge base 6, a database 7 and an interpretation module 8; wherein,,
the human interface module 1 comprises: the device comprises a camera for acquiring back images, a display screen for performing visualization and a loudspeaker for performing audio feedback;
the image processing module 2 is used for preprocessing the back image;
the key point extraction module 3 is used for setting key skeleton points and extracting two-dimensional position information and corresponding credibility of each key skeleton point from the preprocessed back image;
the geometric calculation module 4 is used for carrying out geometric calculation according to the two-dimensional position information of the key skeleton points to obtain initial evidence of uncertainty;
the reasoning module 5 is used for carrying out uncertainty reasoning on the initial uncertainty evidence according to the uncertainty knowledge in the knowledge base 6 to obtain an intermediate conclusion and a final conclusion, and taking the final conclusion as a scoliosis detection result;
the knowledge base 6 is used for storing uncertainty knowledge related to scoliosis detection; the uncertainty knowledge is expressed in terms of uncertainty-generating rules; the uncertainty generating rule comprises a precondition of uncertainty knowledge, a conclusion of the uncertainty knowledge and corresponding uncertainty knowledge credibility, wherein the uncertainty knowledge credibility is given by a professional orthopedics doctor; uncertainty knowledge includes: human body double shoulder corner symmetry evaluation, human body midline lateral bending degree evaluation, double shoulder inflection point symmetry evaluation and hand body distance symmetry evaluation; the human body double-shoulder corner symmetry evaluation is based on the credibility of the strict symmetry conclusion of the double-shoulder corners of the tested person, which is obtained by the left shoulder corner, the right shoulder corner, the left shoulder-sternal shank-upper neck corner and the right shoulder-sternal shank-upper neck corner; the human midline lateral bending degree evaluation is based on the reliability that the human midline of the tested person is completely normal conclusion based on the vertex-upper neck-sternal stalk angle, upper neck-sternal stalk-sacrum midpoint angle of the human body; the symmetry evaluation of the double-shoulder inflection point obtains the credibility of the complete normal conclusion of the double-shoulder inflection point of the tested person based on the left-shoulder inflection point-sternum shank-right-shoulder inflection point angle, the right-shoulder inflection point and the left-shoulder inflection point of the human body; the symmetry of the hand distance is based on the length of the humerus and the length of the forearm of the human body, euclidean distance between the key points of the bones of the hand and the key points of the vertical line of the body is evaluated, and the credibility of the conclusion of the complete symmetry of the hand distance of the human body is obtained;
the database 7 is used for storing initial evidence of uncertainty, intermediate reasoning process, intermediate conclusion, final conclusion and corresponding credibility;
the interpretation module 8 is configured to record each intermediate conclusion and the corresponding reliability obtained in the uncertainty reasoning process, convert each intermediate conclusion into a fuzzy conclusion according to different regions according to the reliability, and sort the intermediate conclusion and the final conclusion according to a time sequence.
It is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (7)
1. The scoliosis detection method based on uncertainty reasoning is characterized by comprising the following steps of:
s1: acquiring a back image, and preprocessing the back image;
s2: setting each key skeleton point, and extracting two-dimensional position information of each key skeleton point from the preprocessed back image, wherein the two-dimensional position information comprises the following steps:
s2.1: extracting channel heat maps of key bone points from the preprocessed back image by adopting a convolution neural network based on heat map regression;
s2.2: carrying out post-processing on the confidence coefficient of each channel heat map by utilizing a non-maximum suppression mode;
s2.3: selecting the maximum confidence coefficient in each channel heat map after post-treatment as two-dimensional position information of the corresponding key skeleton points, and mapping the maximum confidence coefficient into a range from-1 to convert the maximum confidence coefficient into the confidence coefficient of the corresponding key skeleton points;
wherein the key skeletal points include: left shoulder inflection point, right shoulder inflection point, left arm wrist, right arm wrist, left elbow, right elbow, top of head, upper neck, manubrium, sacral midpoint, left hip joint and right hip joint; s3: obtaining initial uncertainty evidence corresponding to each key skeleton point through geometric calculation according to the two-dimensional position information of each key skeleton point; the uncertainty initial evidence comprises human body posture distance information, human body posture angle information and evidence credibility;
wherein,,
the human body posture distance information is obtained by calculating the two-dimensional Euclidean distance approximation of adjacent key skeleton points through the Euclidean distance formula;
the human body posture angle information is approximately obtained according to the human body posture distance information through a cosine formula;
the evidence credibility is obtained through an uncertainty calculation method;
s4: and carrying out uncertainty reasoning by using the initial uncertainty evidence to obtain a final conclusion as a scoliosis detection result.
2. The method for detecting scoliosis based on uncertainty reasoning according to claim 1, wherein in step S1, preprocessing the back image includes: the back image was converted to RGB format and the back image was corrected to 256 x 256 in size, and then the gray values at all positions of the R, G, B three-channel gray map of the back image were normalized.
3. The method for detecting scoliosis based on uncertainty reasoning of claim 1, further comprising, prior to performing the uncertainty reasoning: and calculating the included angle between the back cross section and the shooting direction of the tested person according to the sacrum midpoint, the left hip joint, the right hip joint, the left shoulder inflection point, the right key inflection point and the sternum handle, and correcting the human body posture distance information and the human body posture angle information.
4. The scoliosis detection method according to claim 1, wherein in step S4, the uncertainty reasoning includes a combination of evidence uncertainty calculation, uncertainty transfer and uncertainty conclusion synthesis.
5. The scoliosis detection method based on uncertainty reasoning according to claim 1, wherein in the uncertainty reasoning process, when the number of uncertainty generating rules in the knowledge base cannot obtain a reasoning result or the number of reasoning times reaches a preset upper limit, the reasoning is considered to be abnormal, and abnormal conditions are fed back in a visual mode through a display screen.
6. The method for detecting scoliosis based on uncertainty reasoning according to claim 1, wherein after obtaining the scoliosis detection result, further comprises: sequencing all intermediate conclusions and final conclusions obtained in the uncertainty reasoning process according to the time sequence, and carrying out visual feedback through a display screen in sequence.
7. The scoliosis detection system based on uncertainty reasoning is characterized by comprising a man-machine interface module, an image processing module, a key point extraction module, a geometric calculation module, a reasoning module, a knowledge base, a database and an interpretation module; wherein,,
the human-machine interface module comprises: the device comprises a camera for acquiring back images, a display screen for performing visualization and a loudspeaker for performing audio feedback;
the image processing module is used for preprocessing the back image;
the key point extraction module is used for setting key skeleton points and extracting two-dimensional position information and corresponding credibility of each key skeleton point from the preprocessed back image;
wherein,,
the key skeletal points include: left shoulder inflection point, right shoulder inflection point, left arm wrist, right arm wrist, left elbow, right elbow, top of head, upper neck, manubrium, sacral midpoint, left hip joint and right hip joint;
the extracting the two-dimensional position information and the corresponding credibility of each key skeleton point from the preprocessed back image comprises the following steps:
extracting channel heat maps of key bone points from the preprocessed back image by adopting a convolution neural network based on heat map regression;
carrying out post-processing on the confidence coefficient of each channel heat map by utilizing a non-maximum suppression mode;
selecting the maximum confidence coefficient in each channel heat map after post-treatment as two-dimensional position information of the corresponding key skeleton points, and mapping the maximum confidence coefficient into a range from-1 to convert the maximum confidence coefficient into the confidence coefficient of the corresponding key skeleton points;
the geometric calculation module is used for carrying out geometric calculation according to the two-dimensional position information of the key skeleton points to obtain initial evidence of uncertainty; the uncertainty initial evidence comprises human body posture distance information, human body posture angle information and evidence credibility;
wherein,,
the human body posture distance information is obtained by calculating the two-dimensional Euclidean distance approximation of adjacent key skeleton points through the Euclidean distance formula;
the human body posture angle information is approximately obtained according to the human body posture distance information through a cosine formula;
the evidence credibility is obtained through an uncertainty calculation method; the reasoning module is used for carrying out uncertainty reasoning on the initial uncertainty evidence according to the uncertainty knowledge in the knowledge base to obtain an intermediate conclusion and a final conclusion, and taking the final conclusion as a scoliosis detection result;
the knowledge base is used for storing uncertainty knowledge related to scoliosis detection; the uncertainty knowledge is expressed in terms of uncertainty-generating rules;
the database is used for storing initial evidence of uncertainty, an intermediate reasoning process, intermediate conclusions, final conclusions and corresponding credibility;
the interpretation module is used for recording each intermediate conclusion and corresponding credibility obtained in the uncertainty reasoning process, converting each intermediate conclusion into a fuzzy conclusion according to different regions according to the credibility, and sequencing the intermediate conclusions and the final conclusions according to a time sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110119695.5A CN112801979B (en) | 2021-01-28 | 2021-01-28 | Scoliosis detection method and system based on uncertainty reasoning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110119695.5A CN112801979B (en) | 2021-01-28 | 2021-01-28 | Scoliosis detection method and system based on uncertainty reasoning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112801979A CN112801979A (en) | 2021-05-14 |
| CN112801979B true CN112801979B (en) | 2023-09-05 |
Family
ID=75812489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110119695.5A Active CN112801979B (en) | 2021-01-28 | 2021-01-28 | Scoliosis detection method and system based on uncertainty reasoning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801979B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139962B (en) * | 2021-05-26 | 2021-11-30 | 北京欧应信息技术有限公司 | System and method for scoliosis probability assessment |
| CN115346660B (en) * | 2022-08-17 | 2023-09-19 | 广东工业大学 | Markov blanket model-based spine disease auxiliary diagnosis method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084161A (en) * | 2019-04-17 | 2019-08-02 | 中山大学 | A kind of rapid detection method and system of skeleton key point |
| CN110458831A (en) * | 2019-08-12 | 2019-11-15 | 深圳市智影医疗科技有限公司 | A kind of scoliosis image processing method based on deep learning |
| CN110495889A (en) * | 2019-07-04 | 2019-11-26 | 平安科技（深圳）有限公司 | Postural assessment method, electronic device, computer equipment and storage medium |
| CN111374670A (en) * | 2020-05-01 | 2020-07-07 | 上海健康医学院 | Intelligent detection device and detection method for scoliosis of human body |
-
2021
- 2021-01-28 CN CN202110119695.5A patent/CN112801979B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084161A (en) * | 2019-04-17 | 2019-08-02 | 中山大学 | A kind of rapid detection method and system of skeleton key point |
| CN110495889A (en) * | 2019-07-04 | 2019-11-26 | 平安科技（深圳）有限公司 | Postural assessment method, electronic device, computer equipment and storage medium |
| CN110458831A (en) * | 2019-08-12 | 2019-11-15 | 深圳市智影医疗科技有限公司 | A kind of scoliosis image processing method based on deep learning |
| CN111374670A (en) * | 2020-05-01 | 2020-07-07 | 上海健康医学院 | Intelligent detection device and detection method for scoliosis of human body |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112801979A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112734757B (en) | Spine X-ray image cobb angle measuring method | |
| CN112801979B (en) | Scoliosis detection method and system based on uncertainty reasoning | |
| Robinson et al. | Variation between experienced observers in the interpretation of accident and emergency radiographs. | |
| CN108320288B (en) | Data processing method for idiopathic scoliosis image | |
| CN110613480B (en) | Fetus ultrasonic dynamic image detection method and system based on deep learning | |
| US20100231605A1 (en) | Medical image processing device and medical image processing program | |
| US7167581B2 (en) | Medical image processing method and apparatus for discriminating body parts | |
| EP1551296B1 (en) | Method, code, and system for assaying joint deformity | |
| CN113674257A (en) | Method, device and equipment for measuring scoliosis angle and storage medium | |
| CN114287915A (en) | Noninvasive scoliosis screening method and system based on back color image | |
| Xie et al. | Automatically measuring the Cobb angle and screening for scoliosis on chest radiograph with a novel artificial intelligence method | |
| JP2017198697A (en) | Image processing program, recording medium, image processing device, and image processing method | |
| Makhdoomi et al. | Development of Scoliotic Spine Severity Detection using Deep Learning Algorithms | |
| CN110801204B (en) | Balance detection method based on human body frame | |
| US20230169644A1 (en) | Computer vision system and method for assessing orthopedic spine condition | |
| US8116545B2 (en) | Method and system for analysis of bone density | |
| CN114391862A (en) | Big data CT image report generation-based remote processing method and equipment and computer storage medium | |
| CN108596877A (en) | Rib cage CT data analysis systems | |
| Subsol et al. | 3d image processing for the study of the evolution of the shape of the human skull: presentation of the tools and preliminary results | |
| Ikwuezunma et al. | Case of the missing vertebra: a report of a radiographic stitching error in a scoliosis patient | |
| US20210213684A1 (en) | Construction method for customization of modular bone plates based on additive manufacturing and a construction system thereof | |
| Koompairojn et al. | Computer-aided diagnosis of lumbar stenosis conditions | |
| US20240173059A1 (en) | Device for helping to bend surgical rods | |
| CN115644904A (en) | Osteoporosis centrum re-fracture prediction system based on CT image deep learning | |
| Porto et al. | Comparison of patient position and midline lumbar neuraxial access via statistical model registration to ultrasound |
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 |