CN113870098A - Automatic Cobb angle measurement method based on spinal layered reconstruction - Google Patents
Automatic Cobb angle measurement method based on spinal layered reconstruction Download PDFInfo
- Publication number
- CN113870098A CN113870098A CN202111053719.8A CN202111053719A CN113870098A CN 113870098 A CN113870098 A CN 113870098A CN 202111053719 A CN202111053719 A CN 202111053719A CN 113870098 A CN113870098 A CN 113870098A
- Authority
- CN
- China
- Prior art keywords
- image
- vertebra
- spine
- cobb angle
- sagittal
- 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.)
- Pending
Links
- 239000011436 cob Substances 0.000 title claims abstract description 33
- 238000000691 measurement method Methods 0.000 title claims description 12
- 210000000988 bone and bone Anatomy 0.000 claims abstract description 35
- 230000011218 segmentation Effects 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000013135 deep learning Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 210000000115 thoracic cavity Anatomy 0.000 claims description 13
- 229910052751 metal Inorganic materials 0.000 claims description 9
- 239000002184 metal Substances 0.000 claims description 9
- 238000002591 computed tomography Methods 0.000 claims description 8
- 238000003384 imaging method Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 239000003814 drug Substances 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 210000001015 abdomen Anatomy 0.000 claims description 2
- 210000000038 chest Anatomy 0.000 claims description 2
- 210000004705 lumbosacral region Anatomy 0.000 description 5
- 238000005259 measurement Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 206010039722 scoliosis Diseases 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 208000000875 Spinal Curvatures Diseases 0.000 description 2
- 210000003484 anatomy Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 241000276425 Xiphophorus maculatus Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 229910052791 calcium Inorganic materials 0.000 description 1
- 239000011575 calcium Substances 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- QTCANKDTWWSCMR-UHFFFAOYSA-N costic aldehyde Natural products C1CCC(=C)C2CC(C(=C)C=O)CCC21C QTCANKDTWWSCMR-UHFFFAOYSA-N 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- ISTFUJWTQAMRGA-UHFFFAOYSA-N iso-beta-costal Natural products C1C(C(=C)C=O)CCC2(C)CCCC(C)=C21 ISTFUJWTQAMRGA-UHFFFAOYSA-N 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 210000001562 sternum Anatomy 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/08—Projecting images onto non-planar surfaces, e.g. geodetic screens
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a method for automatically measuring a Cobb angle based on spinal layered reconstruction, which comprises the following steps: (1) inputting a cross section CT sequence image, preprocessing DICOM original data, reconstructing a superposed sagittal image in a layering manner, selecting a sagittal range of a spine by adopting a template matching method, and then selecting a middle one-third position interval to reconstruct a bone coronal image; (2) training a vertebra segmentation model based on a bone coronal map based on a deep learning network, detecting and segmenting each vertebra of a spine by adopting the model, and optimizing an intervertebral space by threshold processing; (3) extracting the central point of each vertebra, and performing curve fitting on the central point set by using a sextic polynomial to obtain a spine curve; (4) the Cobb angle is iteratively found by calculating the curvature between each feature point in the spine curve.
Description
Technical Field
The invention relates to the field of medical artificial intelligence, and particularly provides a Cobb angle automatic measurement method based on spinal layered reconstruction.
Background
In recent years, medical imaging technology and artificial intelligence technology are rapidly developed, computed tomography is widely applied to clinical diagnosis, deep learning and intelligent medical study on spinal lesions based on CT scanning have extremely important practical significance and research value, and the artificial intelligence technology is used for processing and analyzing medical image data to provide powerful assistance for modern medical diagnosis.
When the scoliosis is clinically judged, the Cobb angle is a common research object, and the size of the Cobb angle can accurately reflect the severity of the scoliosis of a human body. At present, the measurement mode of the Cobb angle is mainly manual measurement, firstly, upper and lower vertebrae with the most obvious concave side of lateral curvature are searched in a spine image to serve as upper and lower end plates, then straight lines passing through the upper and lower end plates are drawn manually, and finally, an angle between the two straight lines is measured by adopting a protractor to serve as the Cobb angle. The position of each vertebral segment is positioned with high precision in a transverse position CT sequence image, the spinal curvature characteristics are automatically judged, and the Cobb angle is calculated, so that the method has great significance for medical researches such as scoliosis.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide an automatic Cobb angle measurement method based on spinal layered reconstruction, aiming at the defects in the prior art, and specifically comprising the following steps:
(1) inputting a cross-sectional CT sequence image, preprocessing DICOM (digital imaging and communications in medicine) original data, reconstructing a superposed sagittal image in a layering manner, selecting a sagittal range of a spinal column by adopting a template matching method, and then selecting a part of middle position to reconstruct a bone coronal image;
(2) training a vertebra segmentation model based on a bone coronal map based on a deep learning network, detecting and segmenting each vertebra of a spine by adopting the model, and optimizing an intervertebral space by threshold processing;
(3) extracting the central point of each vertebra, and performing curve fitting on the central point set by using a polynomial to obtain a spine curve;
(4) the Cobb angle is iteratively found by calculating the curvature between each feature point in the spine curve.
Further, the specific implementation manner of the step (1) is as follows;
(11) the CT sequence image refers to a transverse position CT sequence image obtained by performing CT examination on the chest and abdomen, at least comprises a thoracic vertebra and a majority of lumbar vertebrae, and has a relatively complete spine shape;
(12) sequencing the sequence images according to the time sequence of CT scanning according to the header file label field INSTANCENTENUMBER of the CT sequence images;
(13) carrying out gray value statistics according to DICOM image data to determine a gray value threshold of a bone region and a gray value threshold of a metal object, and eliminating the influence of the metal object possibly existing through threshold definition;
(14) determining an effective DICOM image data range, setting a traversal range, and eliminating the influence generated by a bed plate of a CT machine tool;
(15) based on the steps, each DICOM image is processed in a traversing mode according to the CT scanning sequence, effective data of a skeleton part are extracted, and a skeleton sagittal view is reconstructed in a three-dimensional mode, wherein the skeleton sagittal view is actually the projection of the three-dimensional data on a certain plane;
(16) taking thoracic vertebra and lumbar vertebra regions of a spine in any skeleton sagittal image as characteristic templates, and binarizing the generated skeleton sagittal image and the characteristic templates;
(17) performing multi-scale template matching on the binarized feature template and the bone coronal view, and drawing a rectangular frame on a matching area;
(18) returning to the x0 abscissa of the central point of the rectangle to obtain the sagittal range of the spine;
(19) and (4) selecting a position interval of middle third of the sagittal range of the spinal column according to x0 to reconstruct a bone coronal view.
Further, the pixel gray value threshold value for distinguishing the bone area and the metal object in the step (13) is obtained
4. The automatic measurement method of Cobb angle based on spinal column layered reconstruction as claimed in claim 2, characterized in that: in step (14), the image size is 512 × 512, and when the portion larger than 450 in the y-axis direction contains the bed plate and almost no valid pixel information, the traversal range of the y-axis is set to be 0-450.
Further, the concrete implementation manner of training the vertebra segmentation model based on the bone coronal map in the step (2) is as follows;
(21) acquiring a plurality of skeleton coronal graphs based on layered reconstruction as training set pictures;
(22) marking the training set picture by taking each vertebra of the bone coronal graph as an ROI to generate a training label picture;
(23) training based on a deep learning U-Net network, and adjusting training parameters to obtain a vertebra segmentation model based on a bone coronal map;
(24) carrying out vertebra segmentation by using the trained model and storing segmentation results;
(25) and optimizing the intervertebral space by using threshold processing to obtain a binary vertebra segmentation image, and storing a result.
Further, the concrete implementation manner of extracting the central point in the step (3) and performing curve fitting is as follows;
(31) extracting the outline of the binary vertebra segmentation image;
(32) extracting the central point of each contour, namely the central point of each vertebral segment, by using the first moment;
(33) and carrying out curve fitting on the central point of the spine by using a polynomial to obtain a fitted curve of the spine.
Further, the specific implementation process of calculating the Cobb angle according to the curvature in the step (4) is as follows;
(41) calculating a first derivative of the fitted spine curve at each central point to obtain curvatures of different central points;
(42) iteratively calculating included angles between tangent lines of different central points according to the curvatures of the different central points, namely the slopes of the tangent lines;
(43) and judging the size of the included angle, wherein the largest included angle is the Cobb angle.
The invention has the beneficial effects that: the automatic Cobb angle measuring method based on the spinal layered reconstruction automatically and accurately finds out each segment of the vertebral column without manual assistance, judges the spinal curvature characteristics and calculates the Cobb angle, thereby facilitating the subsequent medical research and analysis aiming at the scoliosis.
Drawings
FIG. 1 is a flow chart of the automatic measurement of Cobb angle of the present invention.
Fig. 2 is a template for multi-scale template matching.
Fig. 3 is a result of multi-scale template matching.
Fig. 4 is a reconstructed bone coronal view.
FIG. 5 is a schematic view of the thoracic and lumbar regions;
FIG. 6 is a schematic diagram illustrating the traversal range in step 4 according to the embodiment;
FIG. 7 is a multi-planar sample of a medical image;
FIG. 8 is a schematic cross-sectional view;
FIG. 9 is a schematic sagittal view.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the accompanying drawings.
In the prior art, most of the prior arts aim at automatic measurement of Cobb angle of an X-ray image, and the X-ray image is planar imaging. The invention is mainly characterized in that the method comprises the step of reconstructing a sagittal image according to a CT image, as shown in figure 3 (side surface), and reconstructing a three-dimensional coronal image of a spine according to the sagittal image, as shown in figure 4 (front surface), wherein the coronal image is an overlapped coronal image of the CT image and is formed by overlapping a plurality of coronal images (the problem that the spine cannot be effectively identified by overlapping the sternum and the ribs in X-ray imaging can be completely overcome), so that the method not only comprises a clear vertebral segment and is beneficial to segmentation, but also removes the interference of factors such as bone organs and the like. And finally, performing unet segmentation on the coronal image to obtain each spinal column block, thereby taking a central point and obtaining a cobb angle through curve fitting.
As shown in fig. 1, an automatic Cobb angle measurement method based on spinal layered reconstruction includes the following steps:
(1) inputting a cross-sectional CT sequence image, preprocessing DICOM (digital imaging and communications in medicine) original data, reconstructing a superposed sagittal image in a layering manner, selecting a sagittal range of a spinal column by adopting a template matching method, and then selecting a middle third position to reconstruct a bone coronal image;
(2) training a vertebra segmentation model based on a bone coronal map based on a deep learning network, detecting and segmenting each vertebra of a spine by adopting the model, and optimizing an intervertebral space by threshold processing;
(3) extracting the central point of each vertebra, and performing curve fitting on the central point set by using a polynomial to obtain a spine curve;
(4) the Cobb angle is iteratively found by calculating the curvature between each feature point in the spine curve.
The method for reconstructing the bone coronal view based on the cross-sectional position CT sequence image in a layering way in the step (1) comprises the following steps:
(11) the CT sequence image refers to a transverse position CT sequence image obtained by performing a thoracoabdominal CT examination, at least comprises a thoracic vertebra and a majority of lumbar vertebrae, and contains a relatively complete spine shape.
The thoracic vertebra is mainly characterized by having a costal notch with ribs connected thereto. The lumbar spine is characterized by a large vertebral body, a platy spinous process, no rib bone connected with the spinous process, two sides of a thoracic vertebra T12 connected with the rib, and only transverse processes on two sides of a lumbar vertebra part connected with no rib. Accordingly, the thoracic vertebra T12 and the lumbar vertebra L1 can be characterized to divide thoracic and lumbar regions, and as shown in fig. 5, only the thoracic and lumbar regions including most of the thoracic and lumbar regions show the entire spine, thereby judging the degree of curvature of the spine.
(12) Sequencing the sequence images according to the time sequence of CT scanning according to the header file label field INSTANCENTENUMBER of the CT sequence images;
(13) carrying out gray value statistics according to DICOM image data to determine a gray value threshold of a bone region and a gray value threshold of a metal object, and eliminating the influence of the metal object possibly existing through threshold definition;
the threshold value of the normal range of each non-human tissue is general>1800, the range of human bone and calcium is approximately 1200-1800 when the reconstructed pixel threshold is taken
When the method is used, a sagittal view or a coronal view of the bone can be generated after the influence of the metal foreign bodies is eliminated.
(14) Determining an effective DICOM image data range, setting a traversal range, and eliminating the influence generated by a bed plate of a CT machine tool;
setting the pixel range of the reconstruction region, wherein the size of the image is 512 x 512, traversing all pixel points of the image, but the part of the image with the y-axis direction larger than 450 comprises a CT bed plate and does not influence the generation of a bone coronal view or a sagittal view, so that the y-axis traversal range is set to be 0-450, as shown in FIG. 6.
(15) Based on the steps, each DICOM image is processed in a traversing mode according to the CT scanning sequence, effective data of a skeleton part are extracted, and a skeleton sagittal diagram is reconstructed in a three-dimensional mode (the reconstruction of the sagittal diagram is actually the projection of the three-dimensional data on a certain plane);
(16) taking thoracic vertebra and lumbar vertebra regions of a spine in any skeleton sagittal image as characteristic templates, and binarizing the generated skeleton sagittal image and the characteristic templates;
as shown in FIG. 7, the sagittal plane is a longitudinal section dividing the human body into left and right parts, and the horizontal direction of the anatomy can be seen when the section is perpendicular to the ground plane; the coronal plane is a longitudinal section that divides the body into anterior and posterior parts, and the anterior and posterior aspects of the anatomy can be seen in the section, which is perpendicular to the sagittal plane and the horizontal plane. The cross section refers to a cross section dividing a human body into an upper part and a lower part, as shown in fig. 8, the acquired image data are CT cross section data and are three-dimensional data, and when multi-plane reconstruction is performed, three-dimensional gray data are directly projected and displayed on a two-dimensional plane according to different directions, so that a tomographic image at any angle can be generated, and the specific implementation method is as follows: the mean pixel value is calculated from the effective data, and the coronal plane is generated by y-axis projection and the sagittal plane is generated by x-axis projection. When generating the bone coronal view or the sagittal view, the pixel threshold value of (3) is adopted 1200 and 1800, and other useless pixel values are removed, and the generated sagittal view is shown in FIG. 9.
(17) Performing multi-scale template matching on the binarized feature template and the bone coronal view, and drawing a red rectangular frame on a matching area;
(18) returning to the x0 abscissa of the central point of the rectangle to obtain the sagittal range of the spine;
(19) and (4) selecting a position interval of middle third of the sagittal range of the spinal column according to x0 to reconstruct a bone coronal view.
The reconstructed coronal view is shown in fig. 4, with a selected one-third area corresponding to the inner small rectangular box in fig. 3 and the area in cross section corresponding to the transverse rectangular box in fig. 8.
The method for training the vertebra segmentation model based on the bone coronal map and performing vertebra segmentation in the step (2) comprises the following steps of:
(21) acquiring a plurality of skeleton coronal graphs based on layered reconstruction as training set pictures;
(22) marking the training set picture by taking each vertebra of the bone coronal graph as an ROI to generate a training label picture;
(23) training based on a deep learning U-Net network, and adjusting training parameters to obtain a vertebra segmentation model based on a bone coronal map;
(24) carrying out vertebra segmentation by using the trained model and storing segmentation results;
(25) and optimizing the intervertebral space by using threshold processing to obtain a binary vertebra segmentation image, and storing a result.
The method for extracting the central point to perform curve fitting in the step (3) comprises the following steps:
(31) extracting the outline of the binary vertebra segmentation image;
(32) extracting the central point of each contour, namely the central point of each vertebral segment, by using the first moment;
(33) and carrying out curve fitting on the central point of the spine by using a polynomial to obtain a fitted curve of the spine.
The method for solving the Cobb angle according to the curvature in the step (4) comprises the following steps:
(41) calculating a first derivative of the fitted spine curve at each central point to obtain curvatures of different central points;
(42) iteratively calculating included angles between tangent lines of different central points according to the curvatures of the different central points, namely the slopes of the tangent lines;
(43) and judging the size of the included angle, wherein the largest included angle is the Cobb angle.
The technical solutions, procedures and advantages of the present invention are clearly illustrated in the above description, and it is obvious for those skilled in the art that the present invention is not limited by the above embodiments, and the above described embodiments and descriptions are only the technical solutions and principles of the present invention, not all of which are represented, and the modifications of the corresponding algorithms performed by the present invention are within the scope of the claims of the present invention, and the experimental results of the present invention are realized in a unique form, and the scope of the present invention is defined by the appended claims and the equivalent elements.
Claims (7)
1. A Cobb angle automatic measurement method based on spinal layered reconstruction is characterized by comprising the following steps:
(1) inputting a cross-sectional CT sequence image, preprocessing DICOM (digital imaging and communications in medicine) original data, reconstructing a superposed sagittal image in a layering manner, selecting a sagittal range of a spinal column by adopting a template matching method, and then selecting a part of middle position to reconstruct a bone coronal image;
(2) training a vertebra segmentation model based on a bone coronal map based on a deep learning network, detecting and segmenting each vertebra of a spine by adopting the model, and optimizing an intervertebral space by threshold processing;
(3) extracting the central point of each vertebra, and performing curve fitting on the central point set by using a polynomial to obtain a spine curve;
(4) the Cobb angle is iteratively found by calculating the curvature between each feature point in the spine curve.
2. The automatic measurement method of Cobb angle based on spinal column layered reconstruction as claimed in claim 1, characterized in that: the specific implementation manner of the step (1) is as follows;
(11) the CT sequence image refers to a transverse position CT sequence image obtained by performing CT examination on the chest and abdomen, at least comprises a thoracic vertebra and a majority of lumbar vertebrae, and has a relatively complete spine shape;
(12) sequencing the sequence images according to the time sequence of CT scanning according to the header file label field INSTANCENTENUMBER of the CT sequence images;
(13) carrying out gray value statistics according to DICOM image data to determine a gray value threshold of a bone region and a gray value threshold of a metal object, and eliminating the influence of the metal object possibly existing through threshold definition;
(14) determining an effective DICOM image data range, setting a traversal range, and eliminating the influence generated by a bed plate of a CT machine tool;
(15) based on the steps, each DICOM image is processed in a traversing mode according to the CT scanning sequence, effective data of a skeleton part are extracted, and a skeleton sagittal view is reconstructed in a three-dimensional mode, wherein the skeleton sagittal view is actually the projection of the three-dimensional data on a certain plane;
(16) taking thoracic vertebra and lumbar vertebra regions of a spine in any skeleton sagittal image as characteristic templates, and binarizing the generated skeleton sagittal image and the characteristic templates;
(17) performing multi-scale template matching on the binarized feature template and the bone coronal view, and drawing a rectangular frame on a matching area;
(18) returning to the x0 abscissa of the central point of the rectangle to obtain the sagittal range of the spine;
(19) and (4) selecting a position interval of middle third of the sagittal range of the spinal column according to x0 to reconstruct a bone coronal view.
3. The method of claim 2, wherein the method for automatically measuring the Cobb angle based on the spinal layered reconstructionCharacterized in that: and (13) obtaining the threshold value of the pixel gray value for distinguishing the bone area and the metal object
4. The automatic measurement method of Cobb angle based on spinal column layered reconstruction as claimed in claim 2, characterized in that: in step (14), the image size is 512 × 512, and when the portion larger than 450 in the y-axis direction contains the bed plate and almost no valid pixel information, the traversal range of the y-axis is set to be 0-450.
5. The automatic measurement method of Cobb angle based on spinal column layered reconstruction as claimed in claim 1, characterized in that: the concrete implementation mode of training the vertebra segmentation model based on the bone coronal view in the step (2) is as follows;
(21) acquiring a plurality of skeleton coronal graphs based on layered reconstruction as training set pictures;
(22) marking the training set picture by taking each vertebra of the bone coronal graph as an ROI to generate a training label picture;
(23) training based on a deep learning U-Net network, and adjusting training parameters to obtain a vertebra segmentation model based on a bone coronal map;
(24) carrying out vertebra segmentation by using the trained model and storing segmentation results;
(25) and optimizing the intervertebral space by using threshold processing to obtain a binary vertebra segmentation image, and storing a result.
6. The automatic measurement method of Cobb angle based on spinal column layered reconstruction as claimed in claim 1, characterized in that: the concrete implementation mode of extracting the central point in the step (3) and carrying out curve fitting is as follows;
(31) extracting the outline of the binary vertebra segmentation image;
(32) extracting the central point of each contour, namely the central point of each vertebral segment, by using the first moment;
(33) and carrying out curve fitting on the central point of the spine by using a polynomial to obtain a fitted curve of the spine.
7. The automatic measurement method of Cobb angle based on spinal column layered reconstruction as claimed in claim 1, characterized in that: the specific implementation process of solving the Cobb angle according to the curvature in the step (4) is as follows;
(41) calculating a first derivative of the fitted spine curve at each central point to obtain curvatures of different central points;
(42) iteratively calculating included angles between tangent lines of different central points according to the curvatures of the different central points, namely the slopes of the tangent lines;
(43) and judging the size of the included angle, wherein the largest included angle is the Cobb angle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111053719.8A CN113870098A (en) | 2021-09-09 | 2021-09-09 | Automatic Cobb angle measurement method based on spinal layered reconstruction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111053719.8A CN113870098A (en) | 2021-09-09 | 2021-09-09 | Automatic Cobb angle measurement method based on spinal layered reconstruction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113870098A true CN113870098A (en) | 2021-12-31 |
Family
ID=78995137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111053719.8A Pending CN113870098A (en) | 2021-09-09 | 2021-09-09 | Automatic Cobb angle measurement method based on spinal layered reconstruction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870098A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115797698A (en) * | 2022-12-13 | 2023-03-14 | 北京大学第三医院（北京大学第三临床医学院） | Skeletal vector homeostatic parameter detection system |
| CN117257455A (en) * | 2023-11-21 | 2023-12-22 | 中国人民解放军总医院第一医学中心 | Lumbar operation fixing rod pre-bending method and device |
| CN117426920A (en) * | 2023-06-14 | 2024-01-23 | 溧阳市中医医院 | Orthopedic spine rehabilitation omnibearing correction system |
-
2021
- 2021-09-09 CN CN202111053719.8A patent/CN113870098A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115797698A (en) * | 2022-12-13 | 2023-03-14 | 北京大学第三医院（北京大学第三临床医学院） | Skeletal vector homeostatic parameter detection system |
| CN115797698B (en) * | 2022-12-13 | 2023-07-14 | 北京大学第三医院（北京大学第三临床医学院） | Bone sagittal balance parameter detection system |
| CN117426920A (en) * | 2023-06-14 | 2024-01-23 | 溧阳市中医医院 | Orthopedic spine rehabilitation omnibearing correction system |
| CN117426920B (en) * | 2023-06-14 | 2024-04-05 | 溧阳市中医医院 | Orthopedic spine rehabilitation omnibearing correction system |
| CN117257455A (en) * | 2023-11-21 | 2023-12-22 | 中国人民解放军总医院第一医学中心 | Lumbar operation fixing rod pre-bending method and device |
| CN117257455B (en) * | 2023-11-21 | 2024-02-20 | 中国人民解放军总医院第一医学中心 | Lumbar operation fixing rod pre-bending method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108053400B (en) | Image processing method and device | |
| JP7162793B2 (en) | Spine Imaging System Based on Ultrasound Rubbing Technology and Navigation/Localization System for Spine Surgery | |
| WO2021017297A1 (en) | Artificial intelligence-based spine image processing method and related device | |
| US7831079B2 (en) | Segmentation of anatomic structures using navigation table | |
| CN113870098A (en) | Automatic Cobb angle measurement method based on spinal layered reconstruction | |
| CN110363765B (en) | Osteoporosis parameter automatic measurement method based on CT image | |
| US20070242869A1 (en) | Processing and measuring the spine in radiographs | |
| US20120143090A1 (en) | Assessment of Spinal Anatomy | |
| JP6170284B2 (en) | Image processing program, recording medium, image processing apparatus, and image processing method | |
| JP2014009945A (en) | Image processing program, recording medium, image processing device, and image processing method | |
| CN111374712B (en) | Ultrasonic imaging method and ultrasonic imaging equipment | |
| CN111493918B (en) | Automatic positioning method, application method and equipment for observation plane of lumbar vertebra CT image | |
| CN106780491B (en) | Initial contour generation method adopted in segmentation of CT pelvic image by GVF method | |
| CN113643176A (en) | Rib display method and device | |
| CN111325754B (en) | Automatic lumbar vertebra positioning method based on CT sequence image | |
| WO2017203316A1 (en) | Method for creating a composite cephalometric image | |
| Le Bras et al. | 3D detailed reconstruction of vertebrae with low dose digital stereoradiography | |
| CN107408301B (en) | Segmentation of objects in image data using channel detection | |
| JP2017198697A (en) | Image processing program, recording medium, image processing device, and image processing method | |
| Kumar et al. | Improving visibility of stereo-radiographic spine reconstruction with geometric inferences | |
| WO2020136303A1 (en) | Method for identifying bone images | |
| Zrimec et al. | 3D modelling and visualization of the human lung | |
| Song et al. | A novel iterative matching scheme based on homography method for X-ray image | |
| Hay et al. | Spine curve modeling for quantitative analysis of spinal curvature | |
| Kodym et al. | Skullbreak dataset: An open dataset for training and validation of skull reconstruction models |
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 |