CN114081471B - Scoliosis cobb angle measuring method based on three-dimensional image and multilayer perception - Google Patents
Scoliosis cobb angle measuring method based on three-dimensional image and multilayer perception Download PDFInfo
- Publication number
- CN114081471B CN114081471B CN202111334839.5A CN202111334839A CN114081471B CN 114081471 B CN114081471 B CN 114081471B CN 202111334839 A CN202111334839 A CN 202111334839A CN 114081471 B CN114081471 B CN 114081471B
- Authority
- CN
- China
- Prior art keywords
- dimensional
- spine
- dimensional image
- points
- coordinate system
- 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 35
- 239000011436 cob Substances 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000008447 perception Effects 0.000 title claims abstract description 14
- 239000013598 vector Substances 0.000 claims abstract description 44
- 238000005070 sampling Methods 0.000 claims abstract description 34
- 239000011159 matrix material Substances 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 7
- 238000000691 measurement method Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 description 10
- 238000005452 bending Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 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
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1071—Measuring physical dimensions, e.g. size of the entire body or parts thereof measuring angles, e.g. using goniometers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0463—Neocognitrons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- General Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Surgery (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Dentistry (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a scoliosis cobb angle measuring method based on three-dimensional images and multilayer perception, which comprises the following steps: s1, acquiring an original three-dimensional image of the back of a human body by using a depth camera; s2, equidistant sampling is carried out on the back image of the human body to be measured and the back image is projected on a three-dimensional coronal plane coordinate system to obtain a three-dimensional image; s3, performing transverse cutting treatment to obtain a back transverse section profile containing a sampling point sequence; constructing a multi-layer perceptron to extract spinal points and spinal midlines and calculate algorithm vectors; an n-dimensional real symmetric matrix is constructed, included angles between every two algorithm vectors are calculated, and the maximum included angle is taken as a scoliosis cobb angle. According to the invention, an original three-dimensional image of the back of a human body is obtained through a depth camera and projected on a three-dimensional coronal plane coordinate system to obtain a three-dimensional image, a multi-layer perceptron is constructed and trained, spinal points are extracted through the multi-layer perceptron to obtain a spinal midline, and then normal vectors of the spinal points relative to the spinal midline are calculated to obtain a scoliosis cobb angle.
Description
Technical Field
The invention relates to the field of scoliosis detection and treatment, in particular to a scoliosis cobb angle measurement method based on three-dimensional images and multilayer perception.
Background
Scoliosis is also known as scoliosis and is characterized by multiple occurrences. In recent years, the occurrence of scoliosis in people is increasing year by year, and the work and the life of people are affected to a certain extent. Thus, spinal column testing has found considerable application. Scoliosis detection the current common method is scoliosis ruler, adams forward bending test. However, due to the defects of low manual detection efficiency, high labor intensity, easy error and the like, the scoliosis detection is urgently required to perform artificial intelligence and data processing at present when the machine vision is continuously developed.
Extraction of the spine curve and calculation of cobb angle are critical to the basic lateral curvature detection system. Traditional scoliosis extraction can have a number of drawbacks. First, the methods such as measuring the rotation angle of the trunk by using the scoliosis ruler, the Adams forward bending test and the like have large workload, and when a large number of people are subjected to general investigation, the manual detection becomes quite tedious, the efficiency is very low, and doctors can possibly cause erroneous judgment and misjudgment due to fatigue. Second, the X-ray adopted in scoliosis detection has a certain amount of radioactivity, and has a certain influence on human health. The harmless detection newly developed abroad has very high price, which is difficult for common patients in common hospitals to use, so that the development of the harmless reliable and high-efficiency detection method can bring great improvement to the problem of spine detection.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide a measuring method for scoliosis cobb angles based on three-dimensional images and multi-layer perception, which is characterized in that original three-dimensional images of the back of a human body are obtained through a depth camera and projected on a three-dimensional coronal plane coordinate system to obtain three-dimensional images, a multi-layer perception machine is constructed and trained, spinal points are extracted through the multi-layer perception machine to obtain spinal midlines, normal vectors of the spinal points relative to the spinal midlines are calculated, and the scoliosis cobb angles are obtained.
The aim of the invention is achieved by the following technical scheme:
a scoliosis cobb angle measuring method based on three-dimensional images and multilayer perception comprises the following steps:
s1, acquiring an original three-dimensional image of the back of a human body to be measured by using a depth camera;
s2, carrying out normalized interpolation processing on the original three-dimensional image obtained in the step S1, equidistantly sampling the back image of the human body to be measured and projecting the back image on a three-dimensional coronal plane coordinate system to obtain a three-dimensional image with regular and fixed sampling points;
s3, transversely cutting the three-dimensional image obtained in the step S2 by adopting a plurality of planes to obtain a series of back cross section contours, wherein each back cross section contour correspondingly comprises a sampling point sequence;
s4, carrying out symmetry analysis on the sampling point sequence of each back cross section contour obtained in the step S3, obtaining candidate points of the spine midline on each back cross section contour, and selecting the best candidate point as a marked spine point;
s5, constructing a multi-layer perceptron, wherein the multi-layer perceptron performs marking spine point training on the steps S3 and S4, and the trained multi-layer perceptron can accurately find spine points in sampling point sequences of all back cross section outlines;
s6, inputting the three-dimensional image in the step S2 through a multi-layer perceptron and outputting to obtain a spine point on the three-dimensional image;
s7, performing curve fitting on the spine points located on the three-dimensional coronal plane coordinate system to obtain a spine midline, and calculating the normal vector of the spine points located on the three-dimensional coronal plane coordinate system relative to the spine midline;
s8, constructing an n-dimensional real symmetric matrix by using the normal vectors obtained in the step S7, calculating the included angles between every two normal vectors, and taking two normal vectors forming the maximum included angles, wherein the maximum included angles are scoliosis cobb angles.
In order to better realize the invention, the method of the step S8 of the invention comprises the following steps:
s81, constructing an n-dimensional real symmetric matrix by utilizing n normal vectors obtained in the step S7, wherein n is the number of spine points on a three-dimensional coronal plane coordinate system;
s82, calculating included angles between every two n normal vectors, taking two normal vectors forming the maximum included angle, wherein the spine points corresponding to the two normal vectors forming the maximum included angle are the positions of the upper end cone and the lower end cone on the spine midline, and the maximum included angle is the scoliosis cobb angle.
In order to better realize the invention, the method of the step S7 of the invention comprises the following steps:
s71, performing polynomial curve fitting on discrete spine points located on a three-dimensional coronal plane coordinate system to obtain a spine centerline curve S (y);
s72, calculating the normal vector at the ith spinal column point asWhere i=1, 2,..n.
In order to better realize the invention, the method of the step S2 of the invention comprises the following steps:
s21, projecting an original three-dimensional image on a three-dimensional coronal plane coordinate system, and selecting a rectangular region of interest in the three-dimensional coronal plane coordinate system, wherein the region of interest comprises a complete spine;
s22, performing Delaunay triangulation on points on an original three-dimensional image of the region of interest in the three-dimensional coronal plane coordinate system, and performing nearest neighbor interpolation processing on required sampling points;
s23, equidistant sampling of the region of interest is carried out in a three-dimensional coronal plane coordinate system, and a three-dimensional image with regular and fixed sampling points is obtained.
Preferably, in step S21 of the present invention, the region of interest may be selected for positioning using the upper left corner coordinate and the lower right corner coordinate.
Compared with the prior art, the invention has the following advantages:
(1) According to the invention, an original three-dimensional image of the back of a human body is obtained through a depth camera and projected on a three-dimensional coronal plane coordinate system to obtain a three-dimensional image, a multi-layer perceptron is constructed and trained, spinal points are extracted through the multi-layer perceptron to obtain a spinal midline, and then normal vectors of the spinal points relative to the spinal midline are calculated to obtain a scoliosis cobb angle.
(2) According to the method, firstly, an interested region is selected according to a projection frame on a coronal plane, the interested region is equidistantly divided, nearest neighbor interpolation is carried out at a required sampling point according to a division result, then transverse cutting is carried out on a three-dimensional image to obtain a plurality of profile sequences, a spinal column candidate point is proposed by symmetry analysis of a discrete sequence, an optimal point is selected as a marked spinal column point, a multi-layer perceptron MLP is further constructed, training is carried out by using the marked data to realize automatic extraction of a spinal column center line, finally, a real symmetrical matrix describing a spinal lateral bending included angle is constructed according to the extracted spinal column point and the spinal column center line, and the positions of an upper end cone and a lower end cone and cobb angle are obtained through maximum value search.
(3) Compared with the traditional scoliosis cobb angle measurement modes such as a scoliosis ruler, an X-ray image and the like, the method has the characteristics of high efficiency, high automation, no radioactivity and the like, the multi-layer perceptron MLP is used for extracting the spine point characteristics, the robustness is better, and the discrete sequence symmetry analysis is used as an auxiliary means in the labeling process, so that the labeling efficiency and accuracy are greatly improved.
Drawings
FIG. 1 is a schematic diagram of a scoliosis cobb angle measurement method according to an embodiment;
FIG. 2 is an exemplary diagram of a three-dimensional image in a three-dimensional coronal plane coordinate system in an embodiment;
FIG. 3 is an exemplary view of a portion of a cross-cut back section profile area in an embodiment.
Detailed Description
The invention is further illustrated by the following examples:
examples
As shown in fig. 1 to 3, a measuring method of scoliosis cobb angle based on three-dimensional image and multilayer perception comprises the following steps:
s1, acquiring an original three-dimensional image of the back of the human body to be measured by adopting a depth camera.
S2, carrying out normalized interpolation processing on the original three-dimensional image obtained in the step S1, equidistantly sampling the back image of the human body to be measured, and projecting the back image of the human body to be measured on a three-dimensional coronal plane coordinate system to obtain a three-dimensional image with regular and fixed sampling points.
According to one embodiment of the present embodiment, the step S2 method includes the following:
s21, projecting an original three-dimensional image on a three-dimensional coronal plane coordinate system, and selecting a rectangular region of interest (preferably, the region of interest can be positioned and selected by adopting an upper left corner coordinate and a lower right corner coordinate) in the three-dimensional coronal plane coordinate system, wherein the region of interest comprises a complete spine.
S22, performing Delaunay triangulation on points on an original three-dimensional image of the region of interest in the three-dimensional coronal plane coordinate system, and performing nearest neighbor interpolation processing on required sampling points.
S23, equidistant sampling of the region of interest is carried out in a three-dimensional coronal plane coordinate system, and a three-dimensional image with regular and fixed sampling points is obtained (fig. 2 shows a three-dimensional image in the three-dimensional coronal plane coordinate system by way of example).
S3, performing transverse cutting on the three-dimensional image obtained in the step S2 by adopting m planes to obtain a series of back cross section profiles (m back cross section profiles), wherein each back cross section profile corresponds to a sequence containing sampling points (the sequence of sampling points in the embodiment is discrete sampling points), and fig. 3 illustrates one back cross section profile (the back cross section profile corresponds to the sequence containing sampling points).
S4, carrying out symmetry analysis on the sampling point sequence of each back cross section contour obtained in the step S3, obtaining candidate points of the spine midline on each back cross section contour, and selecting the best candidate point as a marked spine point.
According to one embodiment of the present embodiment, step S4 may employ the following method:
s41: polynomial curve fitting is carried out on the discrete sampling point sequence to obtain a curve S (x);
s42: defining the normal vector of each sampling point on the curve as
S43: defining a function N (x) =n (x+σ) +n (x- σ) to describe the normal vector distribution in the vicinity of point x on curve S (x);
s44: unitizing N (x), i.e., N (x) =n (x)/norm (N (x));
s45: let the point x be in s 0 For the normal distribution in the neighborhood of the radius, N (x) is averaged to obtain
S46: let point x be s 0 For the difference between each normal vector and the average value of the normal vectors in the neighborhood of the radius, the difference definition index is:the smaller the index value is, the higher the symmetry of the curve in the neighborhood of the point x is;
s47: find all points on curve S (x) that make index take a minimum: x is x 1 ,x 2 ,x 3 .. determining the nearest sampling points to the points in the contour sequence as spinal candidate points, and selecting the best candidate point as the labeled spinal point;
s48: and repeating the steps S41 to S47 until the marking of the spinal points of the sampling point sequence of the m back cross section outlines is completed.
S5, constructing a multi-layer perceptron, wherein the multi-layer perceptron performs marking spine point training on the steps S3 and S4, and the trained multi-layer perceptron can accurately find spine points in sampling point sequences of all back cross section outlines.
According to one embodiment of the present embodiment, the following method may be adopted in step S5:
the multi-layer perceptron is constructed, the multi-layer perceptron comprises 4 hidden layer neurons, the number of the 4 hidden layer neurons of the multi-layer perceptron is 64, 32 and 32 respectively, the dimension of input data is m multiplied by n, the dimension of output data is m multiplied by 1, the trained multi-layer perceptron can realize quick finding out of the spine points in the cross section outlines of the backs by utilizing the marking data obtained in the step S4 with enough quantity.
S6, inputting the three-dimensional image in the step S2 through a multi-layer perceptron and outputting to obtain the spine point on the three-dimensional image.
And S7, performing curve fitting on the spine points located on the three-dimensional coronal plane coordinate system to obtain a spine midline, and calculating the normal vector of the spine points located on the three-dimensional coronal plane coordinate system relative to the spine midline.
According to one embodiment of the present embodiment, the method of step S7 includes the following:
s71, performing polynomial curve fitting on discrete spine points located on a three-dimensional coronal plane coordinate system to obtain a spine midline curve S (y).
S72, calculating the normal vector at the ith spinal column point asWhere i=1, 2,..n.
S8, constructing an n-dimensional real symmetric matrix by using the normal vectors obtained in the step S7, calculating the included angles between every two normal vectors, and taking two normal vectors forming the maximum included angles, wherein the maximum included angles are scoliosis cobb angles.
According to one embodiment of the present embodiment, the method of step S8 includes the following:
s81, constructing an n-dimensional real symmetric matrix by utilizing n normal vectors obtained in the step S7, wherein n is the number of spinal points on a three-dimensional coronal plane coordinate system.
S82, calculating included angles between every two n normal vectors, taking two normal vectors forming the maximum included angle, wherein the spine points corresponding to the two normal vectors forming the maximum included angle are the positions of the upper end cone and the lower end cone on the spine midline, and the maximum included angle is the scoliosis cobb angle.
According to one embodiment of the present embodiment, step S8 may employ the following method (step S8 may be combined with steps S1 to S7 to form a separate embodiment):
s81, constructing an n-dimensional real symmetric matrix (the n-dimensional real symmetric matrix is used for describing the inner product relationship between normal vectors related to two spinal points) by using the n normal vectors obtained in the step S7, wherein n is the number of the spinal points on the three-dimensional coronal plane coordinate system.
S82, calculating 2 norms of elements in the A to obtain a matrix B:
s83, defining a matrix C, wherein elements in the corresponding positions of the matrix C are elements in the A divided by elements in the B, and performing inverse cosine on the matrix C to obtain an included angle between every two normal vectors;
s84, searching the maximum value in the column or row direction in C to obtain an index vector C max An angle vector d corresponding to the index position max Wherein c max The i element of (2) represents the normal vector sequence number with the largest included angle with the i normal vector, sequence number [ i, j ]]The corresponding spinal points are the corresponding positions of the upper end cone and the lower end cone on the spinal midline;
s85, diagonal vector d max Searching the maximum value, and obtaining an angle value which is the cobb angle to be measured. The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (5)
1. A scoliosis cobb angle measuring method based on three-dimensional images and multilayer perception is characterized in that: the method comprises the following steps:
s1, acquiring an original three-dimensional image of the back of a human body to be measured by using a depth camera;
s2, carrying out normalized interpolation processing on the original three-dimensional image obtained in the step S1, equidistantly sampling the back image of the human body to be measured and projecting the back image on a three-dimensional coronal plane coordinate system to obtain a three-dimensional image with regular and fixed sampling points;
s3, transversely cutting the three-dimensional image obtained in the step S2 by adopting a plurality of planes to obtain a series of back cross section contours, wherein each back cross section contour correspondingly comprises a sampling point sequence;
s4, carrying out symmetry analysis on the sampling point sequence of each back cross section contour obtained in the step S3, obtaining candidate points of the spine midline on each back cross section contour, and selecting the best candidate point as a marked spine point;
s5, constructing a multi-layer perceptron, wherein the multi-layer perceptron performs marking spine point training on the steps S3 and S4, and the trained multi-layer perceptron can accurately find spine points in sampling point sequences of all back cross section outlines;
s6, inputting the three-dimensional image in the step S2 through a multi-layer perceptron and outputting to obtain a spine point on the three-dimensional image;
s7, performing curve fitting on the spine points located on the three-dimensional coronal plane coordinate system to obtain a spine midline, and calculating the normal vector of the spine points located on the three-dimensional coronal plane coordinate system relative to the spine midline;
s8, constructing an n-dimensional real symmetric matrix by using the normal vectors obtained in the step S7, calculating the included angles between every two normal vectors, and taking two normal vectors forming the maximum included angles, wherein the maximum included angles are scoliosis cobb angles.
2. The scoliosis cobb angle measurement method based on three-dimensional images and multi-layer perception according to claim 1, wherein: the step S8 method comprises the following steps:
s81, constructing an n-dimensional real symmetric matrix by utilizing n normal vectors obtained in the step S7, wherein n is the number of spine points on a three-dimensional coronal plane coordinate system;
s82, calculating included angles between every two n normal vectors, taking two normal vectors forming the maximum included angle, wherein the spine points corresponding to the two normal vectors forming the maximum included angle are the positions of the upper end cone and the lower end cone on the spine midline, and the maximum included angle is the scoliosis cobb angle.
3. The scoliosis cobb angle measurement method based on three-dimensional images and multi-layer perception according to claim 1, wherein: the step S7 method comprises the following steps:
s71, performing polynomial curve fitting on discrete spine points located on a three-dimensional coronal plane coordinate system to obtain a spine centerline curve S (y);
s72, calculating the normal vector at the ith spinal column point asWhere i=1, 2,..n.
4. The scoliosis cobb angle measurement method based on three-dimensional images and multi-layer perception according to claim 1, wherein: the step S2 method comprises the following steps:
s21, projecting an original three-dimensional image on a three-dimensional coronal plane coordinate system, and selecting a rectangular region of interest in the three-dimensional coronal plane coordinate system, wherein the region of interest comprises a complete spine;
s22, performing Delaunay triangulation on points on an original three-dimensional image of the region of interest in the three-dimensional coronal plane coordinate system, and performing nearest neighbor interpolation processing on required sampling points;
s23, equidistant sampling of the region of interest is carried out in a three-dimensional coronal plane coordinate system, and a three-dimensional image with regular and fixed sampling points is obtained.
5. The method for measuring scoliosis cobb angle based on three-dimensional image and multi-layer perception according to claim 4, wherein the method comprises the following steps: in step S21, the region of interest may be selected by using the upper left corner coordinate and the lower right corner coordinate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111334839.5A CN114081471B (en) | 2021-11-11 | 2021-11-11 | Scoliosis cobb angle measuring method based on three-dimensional image and multilayer perception |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111334839.5A CN114081471B (en) | 2021-11-11 | 2021-11-11 | Scoliosis cobb angle measuring method based on three-dimensional image and multilayer perception |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114081471A CN114081471A (en) | 2022-02-25 |
CN114081471B true CN114081471B (en) | 2024-02-09 |
Family
ID=80300166
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111334839.5A Active CN114081471B (en) | 2021-11-11 | 2021-11-11 | Scoliosis cobb angle measuring method based on three-dimensional image and multilayer perception |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114081471B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114903518A (en) * | 2022-04-14 | 2022-08-16 | 深圳市第二人民医院(深圳市转化医学研究院) | Intelligent scoliosis Cobb angle measurement method based on three-dimensional ultrasound |
CN114983459A (en) * | 2022-06-21 | 2022-09-02 | 济南大学 | Interactive measuring system and method for Cobb angle of three-dimensional spine model |
CN115272588B (en) * | 2022-09-27 | 2022-12-30 | 广州辉博信息技术有限公司 | Human body spine fitting method and system based on depth image and electronic equipment |
CN116485793B (en) * | 2023-06-16 | 2023-09-15 | 中国医学科学院北京协和医院 | Teenager scoliosis orthopedic operation effect prediction method |
CN117731244B (en) * | 2024-02-19 | 2024-05-10 | 天津医科大学总医院 | Scoliosis risk early warning system based on infrared thermal imaging |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107481228A (en) * | 2017-07-28 | 2017-12-15 | 电子科技大学 | Human body back scoliosis angle measurement method based on computer vision |
CN109785297A (en) * | 2018-12-25 | 2019-05-21 | 韩山师范学院 | A kind of detection method and device of scoliosis |
CN109903277A (en) * | 2019-02-25 | 2019-06-18 | 电子科技大学 | A kind of scoliosis detection method based on polynomial curve fitting |
CN111317580A (en) * | 2020-02-17 | 2020-06-23 | 温州医科大学附属第二医院、温州医科大学附属育英儿童医院 | Vertebral stabilization system and method |
CN112233083A (en) * | 2020-10-13 | 2021-01-15 | 沈阳先进医疗设备技术孵化中心有限公司 | Spine detection method and device, electronic equipment and storage medium |
CN112274164A (en) * | 2020-07-29 | 2021-01-29 | 深圳市智影医疗科技有限公司 | Scoliosis prediction method, scoliosis prediction device, electronic device, and storage medium |
CN112734757A (en) * | 2021-03-29 | 2021-04-30 | 成都成电金盘健康数据技术有限公司 | Spine X-ray image cobb angle measuring method |
WO2021114622A1 (en) * | 2020-06-08 | 2021-06-17 | 平安科技(深圳)有限公司 | Spinal-column curvature measurement method, apparatus, computer device, and storage medium |
CN113223072A (en) * | 2021-03-31 | 2021-08-06 | 首都医科大学附属北京朝阳医院 | Method and system for measuring vertebral column Cobb angle |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9020235B2 (en) * | 2010-05-21 | 2015-04-28 | Siemens Medical Solutions Usa, Inc. | Systems and methods for viewing and analyzing anatomical structures |
US10874460B2 (en) * | 2017-09-29 | 2020-12-29 | K2M, Inc. | Systems and methods for modeling spines and treating spines based on spine models |
US11877801B2 (en) * | 2019-04-02 | 2024-01-23 | Medicrea International | Systems, methods, and devices for developing patient-specific spinal implants, treatments, operations, and/or procedures |
-
2021
- 2021-11-11 CN CN202111334839.5A patent/CN114081471B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107481228A (en) * | 2017-07-28 | 2017-12-15 | 电子科技大学 | Human body back scoliosis angle measurement method based on computer vision |
CN109785297A (en) * | 2018-12-25 | 2019-05-21 | 韩山师范学院 | A kind of detection method and device of scoliosis |
CN109903277A (en) * | 2019-02-25 | 2019-06-18 | 电子科技大学 | A kind of scoliosis detection method based on polynomial curve fitting |
CN111317580A (en) * | 2020-02-17 | 2020-06-23 | 温州医科大学附属第二医院、温州医科大学附属育英儿童医院 | Vertebral stabilization system and method |
WO2021114622A1 (en) * | 2020-06-08 | 2021-06-17 | 平安科技(深圳)有限公司 | Spinal-column curvature measurement method, apparatus, computer device, and storage medium |
CN112274164A (en) * | 2020-07-29 | 2021-01-29 | 深圳市智影医疗科技有限公司 | Scoliosis prediction method, scoliosis prediction device, electronic device, and storage medium |
CN112233083A (en) * | 2020-10-13 | 2021-01-15 | 沈阳先进医疗设备技术孵化中心有限公司 | Spine detection method and device, electronic equipment and storage medium |
CN112734757A (en) * | 2021-03-29 | 2021-04-30 | 成都成电金盘健康数据技术有限公司 | Spine X-ray image cobb angle measuring method |
CN113223072A (en) * | 2021-03-31 | 2021-08-06 | 首都医科大学附属北京朝阳医院 | Method and system for measuring vertebral column Cobb angle |
Non-Patent Citations (1)
Title |
---|
龚星衡.基于深度相机-虚拟现实设备混合颈椎活动度测量方法.2021,全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN114081471A (en) | 2022-02-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114081471B (en) | Scoliosis cobb angle measuring method based on three-dimensional image and multilayer perception | |
US11551341B2 (en) | Method and device for automatically drawing structural cracks and precisely measuring widths thereof | |
CN110599528A (en) | Unsupervised three-dimensional medical image registration method and system based on neural network | |
US8050473B2 (en) | Segmentation method using an oriented active shape model | |
CN111223133A (en) | Registration method of heterogeneous images | |
CN115496746A (en) | Method and system for detecting surface defects of plate based on fusion of image and point cloud data | |
CN112802019B (en) | Leke typing method based on spine AIS image | |
CN109785370A (en) | A kind of weak texture image method for registering based on space time series model | |
Shi et al. | Circular grid pattern based surface strain measurement system for sheet metal forming | |
CN114170212A (en) | False positive detection method and system based on small lung nodule in CT image | |
CN111339967A (en) | Pedestrian detection method based on multi-view graph convolution network | |
CN117372433B (en) | Thickness parameter control method, device, equipment and storage medium | |
CN109064511B (en) | Method and device for measuring height of center of gravity of human body and related equipment | |
CN114612412A (en) | Processing method of three-dimensional point cloud data, application of processing method, electronic device and storage medium | |
CN113947583A (en) | Weld joint nondestructive testing method based on deep learning two-dimensional time sequence image | |
CN112598629B (en) | Tooth arrangement abnormality positioning auxiliary system based on artificial intelligence | |
CN114219753A (en) | Power equipment surface defect detection method based on deep learning and terminal | |
CN116518868B (en) | Deformation measurement method, device, equipment and storage medium based on artificial intelligence | |
CN116630204B (en) | Remote sensing image online analysis processing system | |
CN105809657A (en) | Angular point detection method and device | |
CN109615603B (en) | Method for extracting laser stripes based on task-driven visual attention model | |
CN116385347A (en) | Deformation analysis-based visual inspection method for aircraft skin curved surface pattern | |
CN115424009A (en) | Automatic reading method for pointer instrument data based on Yolact network | |
CN114445419A (en) | Lung segment segmentation method, device and system based on bronchial topological structure | |
Saha et al. | Classification of surface geometry behavior of cultural heritage surfaces based on monitoring change |
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 |