CN116452499A - Lumbar vertebra instability and slipping diagnosis system based on Unet network - Google Patents

Lumbar vertebra instability and slipping diagnosis system based on Unet network Download PDF

Info

Publication number
CN116452499A
CN116452499A CN202310225252.3A CN202310225252A CN116452499A CN 116452499 A CN116452499 A CN 116452499A CN 202310225252 A CN202310225252 A CN 202310225252A CN 116452499 A CN116452499 A CN 116452499A
Authority
CN
China
Prior art keywords
lumbar
points
instability
key point
network
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
Application number
CN202310225252.3A
Other languages
Chinese (zh)
Inventor
李晓磊
马端蔚
张伟
宋然
程吉禹
丛润民
冯世庆
周恒星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong University
Original Assignee
Shandong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shandong University filed Critical Shandong University
Priority to CN202310225252.3A priority Critical patent/CN116452499A/en
Publication of CN116452499A publication Critical patent/CN116452499A/en
Pending legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
    • A61B6/505—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of bone
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
    • 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
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10116—X-ray image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • G06V2201/033—Recognition of patterns in medical or anatomical images of skeletal patterns
    • 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
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Medical Informatics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Artificial Intelligence (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Pathology (AREA)
  • Surgery (AREA)
  • Optics & Photonics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Software Systems (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computing Systems (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Orthopedic Medicine & Surgery (AREA)
  • Dentistry (AREA)
  • Databases & Information Systems (AREA)
  • Quality & Reliability (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The invention provides a lumbar instability and slippage diagnosis system based on a Unet network, which relates to the technical field of medical image analysis, and comprises a model training module, a model training module and a model training module, wherein the model training module is used for constructing a training data set and a key point positioning model; the key point positioning module acquires two medical image images of overstretching position and overstretching position of a patient to be identified, respectively inputs the two medical image images into the key point positioning model, and outputs thermodynamic diagrams of two positioning key points; the offset calculation module is used for calculating offset distances and angles of the overstretched vertebrae and the overstretched vertebrae respectively based on thermodynamic diagrams of the positioning key points; the result judging module outputs a diagnosis result according to the offset distance difference value and the angle difference value of the relative positions between the overstretching position and the overstretching position; the invention uses neural network and deep learning technology to diagnose the inputted lumbar vertebra medical image, and the diagnosis result is outputted by program to automatically and intelligently diagnose whether the patient has lumbar instability and slipping, and the severity of the illness is given.

Description

Lumbar vertebra instability and slipping diagnosis system based on Unet network
Technical Field
The invention belongs to the technical field of medical image analysis, and particularly relates to a lumbar instability and slippage diagnosis system based on a Unet network.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The lumbar vertebrae of a normal person are orderly arranged, and if one of the lumbar vertebrae slides forward relative to the adjacent lumbar vertebrae due to congenital or acquired reasons, the lumbar vertebrae slip is the lumbar vertebrae slip. Lumbar instability refers to the condition that the lumbar vertebra may be misplaced, pain may occur during movement, and is an early disorder of slipping, and slipping may occur if instability is not controlled.
The existing method is not only used for diagnosing diseases but also used for judging the severity, relies on manual experience summary, is unstable in accuracy, consumes more energy, is high in diagnosis cost, is more critical to low in efficiency, and is difficult to find a balance between accuracy and efficiency, so that the overall effect of lumbar instability and slippage diagnosis is poor.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a lumbar instability and slippage diagnosis system based on a Unet network, which uses a neural network and a deep learning technology to diagnose an input lumbar part medical image, outputs a diagnosis result through a program, automatically and intelligently diagnoses whether a patient has lumbar instability and slippage and gives the severity of the symptoms.
To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
the first aspect of the invention provides a lumbar instability and slippage diagnosis system based on a Unet network;
a lumbar instability and slippage diagnostic system based on a Unet network, comprising:
model training module: constructing a training data set and a key point positioning model based on a Unet network, and training the model;
and the key point positioning module is used for: acquiring two medical image images of overstretching position and overstretching position of a patient to be identified, respectively inputting the two medical image images into a trained key point positioning model, positioning and outputting thermodynamic diagrams of two positioning key points;
and an offset calculation module: calculating offset distances and angles of the overstretched position vertebrae and the overstretched position vertebrae respectively based on thermodynamic diagrams of the positioning key points;
and a result judging module: and outputting a diagnosis result according to the offset distance difference and the angle difference of the relative positions between the overstretching position and the overstretching position.
Further, the medical image is a lumbar vertebra DR image, and the key point is a lumbar vertebra point.
Further, the key point positioning model modifies an output layer of the Unet network based on the Unet network;
the key point positioning model is input into a lumbar vertebra DR image and output into a thermodynamic diagram for positioning key points of lumbar vertebra bones.
Further, in the key point positioning model, the input size of the network maintains the size of n×3×512×512 of the original network, and the output is changed to n×1×512×512, where N is the number of input images.
The dimension of the network output is 1, and all key points share one dimension.
Further, the training data set specifically includes:
marking lumbar vertebra bone points in the DR image by a medical imaging professional;
preprocessing the marked DR image and converting the DR image into a thermodynamic diagram format;
and training the model by taking the DR image as an input and taking the thermodynamic diagram of the positioning key point as an output.
Further, the offset calculation module comprises a key point searching unit, a key point sorting unit, an offset distance calculation unit and an angle calculation unit.
Further, the key point searching unit searches 22 points with the largest thermodynamic value in the thermodynamic diagram output from the key point positioning model as key points.
Further, the key point ordering unit orders according to the coordinate positions of the key points from top to bottom and from left to right.
Further, after the offset distance calculating unit obtains the 22 ordered points, respectively making a vertical line from the i, i=4, 8,12 and 16 point positions to the right vertebra point position connecting line of the lower layer, and making a vertical line to the vertebra point of the upper layer when i=22; the distances from the points of i=4, 8,12,16 to the drop foot are then calculated.
Further, the angle calculating unit calculates the included angles of the lower lumbar vertebra and the next upper lumbar vertebra respectively.
The one or more of the above technical solutions have the following beneficial effects:
the invention uses neural network and deep learning technology to diagnose the inputted lumbar vertebra medical image, and the diagnosis result is outputted by program to automatically and intelligently diagnose whether the patient has lumbar instability and slipping, and the severity of the illness is given.
According to the invention, key points in the lumbar DR image are identified through the Unet network, whether lumbar instability and slipping symptoms occur or not is judged through the distance and the angle between the key points, and the severity of lumbar slipping is given according to the preset index, so that the accuracy and the efficiency of lumbar instability and slipping diagnosis are improved.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a system configuration diagram of a first embodiment.
Fig. 2 is a DR image labeled with a key point in the first embodiment.
Fig. 3 is a gaussian heat map of locating keypoints in the first embodiment.
Fig. 4 is a DR image of a localization key point in the first embodiment.
Fig. 5 is a schematic diagram of the offset distance in the first embodiment.
Fig. 6 is an angle schematic view of the first embodiment.
Detailed Description
The invention will be further described with reference to the drawings and examples.
Example 1
The embodiment discloses a lumbar vertebra instability and slippage diagnosis system based on a Unet network, wherein key points in a lumbar vertebra DR image are identified through the Unet network, whether lumbar vertebra instability and slippage occur or not is judged through the distance and the angle between the key points, and the severity of lumbar vertebra slippage is given according to a preset index, so that the accuracy and the efficiency of lumbar vertebra instability and slippage diagnosis are improved.
As shown in fig. 1, a lumbar instability and slippage diagnosis system based on a Unet network includes:
model training module 101: and constructing a training data set and a key point positioning model based on the Unet network, and training the model.
(1) Training a data set, and constructing an image pair set consisting of a DR image and a thermodynamic diagram for locating key points, wherein the image pair set is specifically as follows:
firstly, please the medical imaging professional to mark the lumbar vertebra bone points in the DR image, 22 points are taken as the key points in the embodiment as shown in fig. 2, and the lumbar vertebra bone points are lumbar 1-sacral 1 vertebral corner points.
After labeling, the python script first pre-processes the labeled DR image to convert it into a format that can be used by the network, and in this embodiment, the thermodynamic diagram hematmap format is adopted: which corresponds to a 1×512×512 image. In the thermodynamic diagram, if the coordinate point is a key point, outputting 1, otherwise outputting 0; however, in the positioning task, it is difficult to accurately position the target point to a certain pixel position, that is, it is difficult to accurately position the target point, and the points around the pixel point are directly defined as negative samples, which may cause interference to the training of the network. To solve this problem, a gaussian heat map method is used, assuming that the coordinates of the labeled keypoints are p= (x) 0 ,y 0 ) Then the thermodynamic value at a point (x, y) on the gaussian is:
wherein sigma 2 Is the variance of the gaussian distribution; the network can be better converged by using the Gaussian heat map, and the Gaussian heat map marked with key points is shown in fig. 3.
And storing an image pair formed by the DR image and the Gaussian heat map marked with the key points into a training data set for training the key point positioning model.
(2) And the key point positioning model is used for processing the input DR image and outputting a Gaussian heat map for positioning the key points.
The key point positioning model is used in a Unet network which has better performance in the medical industry, and modifies an output layer of the Unet network. The input size of the network maintains the size of n×3×512×512 of the original network, and the output is changed to n×1×512×512, where N is the number of input images.
The dimension of the model output is 1, compared with a method that one key point occupies one dimension, the method that all key points occupy one dimension together is adopted in the embodiment, and through experiments, the model can be better converged, and the key points can be positioned more accurately.
And training the model by using the training data set, taking the DR image as input and taking the thermodynamic diagram of the positioning key point as output.
The keypoint location module 102: acquiring two medical image images of overstretching position and overstretching position of a patient to be identified, respectively inputting the two medical image images into a trained key point positioning model, positioning and outputting thermodynamic diagrams of two positioning key points.
The overstretched position and the overstretched position are lateral position x-ray films shot by a patient in a buckling position state and an overstretched position state, and the images can display the abnormal widening or narrowing of the intervertebral body by sliding the vertebral body forwards or backwards, and are mainly used for judging the stability of the spine.
Two lumbar vertebra DR images of the overstretching position and the overstretching position of the patient are respectively input into a trained key point positioning model to obtain thermodynamic diagrams of two positioning key points.
Offset calculation module 103: based on the thermodynamic diagrams of the positioning key points, the offset distance and the angle of the overstretched position and the overstretched position vertebrae are calculated respectively.
The offset calculation module comprises a key point searching unit, a key point sorting unit, an offset distance calculation unit and an angle calculation unit.
Key point searching unit
Searching 22 points with the largest thermodynamic value in a thermodynamic diagram output from the key point positioning model, and taking the thermodynamic value of each pixel point (x, y) in the thermodynamic diagram as a hemmap (x, y), wherein the thermodynamic value is specifically as follows:
(1) Finding the point P where the thermal value is maximum max ＝(x max ,y max )；
(2) Define output result P (x, y) =min (hetmap), where x e [ x ] max -σ,x max +σ],y∈[y max -σ,y max +σ]Min (hetmap) is the minimum of thermodynamic values in the whole hetmap thermodynamic diagram, σ is the gaussian distributionThe difference, which is an adjustable parameter, is set to 9 in this embodiment;
(3) Sequentially cycling the steps (1) and (2) for 22 times, and finding 22 key points.
The 22 points found are marked on the input DR image to obtain a DR image of the locating key points, as shown in FIG. 4.
Key point ordering unit
The found 22 lumbar vertebra key points need to be further sequenced, and are sequenced according to the coordinate positions of the key points from top to bottom and from left to right, and the marks from the left point of the uppermost lumbar vertebra to the right point of the lowermost lumbar vertebra are sequentially 1 to 22, specifically:
(1) Searching two points No. 1 and No. 2 of the uppermost lumbar vertebra to be used as reference points; and ordering the key point groups obtained by the key point searching unit from small to large according to the value of x, wherein the point with the smallest y value is positioned on the bone at the top and is called a candidate point. And selecting a second small point and a third small point, connecting the second small point and the third small point with the candidate points respectively, calculating the shortest distance between the other points and the two straight lines respectively, and selecting the straight line with larger distance between the two straight lines as the correct straight line. Ordering two points on a straight line according to the value of x, wherein the point P with smaller value of x is the point P with the number 1 01 (x 01 ,y 01 ) Larger is point number 2P 02 (x 02 ,y 02 ). Connecting two points in a straight line L 0 Will L 0 Is the reference length, L 0 The method comprises the following steps:
(2) Of the remaining points, the point P (x 1 ,y 1 ) And the second smallest two points P (x 2 ,y 2 ) Connecting two points in a straight line L 12 Calculate L 12 Length of (2)And calculate L 0 And L is equal to 12 Angle (v):
(3) Comparison L 0 And L 12 Length and angle of (1), if L 12 <0.7L 0 or theta is larger than 50 DEG, if false judgment is considered to occur, continuously selecting a point P (x 3 ,y 3 ) And according to the method of the second step, P (x 1 ,y 1 ) And P (x) 3 ,y 3 ) Recalculate L 13 And the included angle theta is brought into the discriminant until the condition that the requirements are not met appears, and the two correct points are found.
(4) Returning to the step (2) to continue searching for points until all points are found.
Offset distance calculation unit
First, after obtaining 22 points of the rank number, a perpendicular line is drawn from the points of i, i=4, 8,12,16 to the right vertebral point line of the next layer, and when i=22, a perpendicular line is drawn to the vertebral point of the previous layer, as shown in fig. 5.
Then, the distances from the points of i=4, 8,12,16 to the foot drop, respectively, are calculated and denoted as D i I=1, 2,3,4,5, as indicated by the dashed lines in the above figures.
Angle calculating unit
The included angles of the lower lumbar vertebra and the next upper lumbar vertebra are calculated respectively, as shown in fig. 6, and the specific formula is as follows:
the result judgment module 104: and outputting a diagnosis result according to the offset distance difference and the angle difference of the relative positions between the overstretching position and the overstretching position.
Obtaining the vertebral offset distance D of the same position of overstretching position and overstretching position 1 、D 2 And angle theta 1 、θ 2 Then, the offset distance and angle of the overstretching position and the overstretching position are differed.
If |D 1 -D 2 | > 10 or |θ 1 -θ 2 And if the I is more than 5, the destabilization condition is considered to occur.
If |D 1 -D 2 | > 20 or |θ 1 -θ 2 And if the absolute value is more than 10, the slipping condition is considered to occur.
According to the preset distance and angle indexes, the severity degree of lumbar spondylolisthesis can be divided into four levels, and the greater the numerical value is, the more serious the illness state is, specifically:
first-order:
25＞|D 1 -D 2 | > 20 or 15 > |θ 1 -θ 2 |＞10
And (2) second-stage:
30＞|D 1 -D 2 | > 25 or 20 > |θ 1 -θ 2 |＞15
Three stages:
35＞|D 1 -D 2 | > 30 or 25 > |θ 1 -θ 2 |＞20
Four stages:
|D 1 -D 2 i > 35 or I θ 1-θ 2 |＞25
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A lumbar instability and slippage diagnostic system based on a Unet network, comprising:
model training module: constructing a training data set and a key point positioning model based on a Unet network, and training the model;
and the key point positioning module is used for: acquiring two medical image images of overstretching position and overstretching position of a patient to be identified, respectively inputting the two medical image images into a trained key point positioning model, positioning and outputting thermodynamic diagrams of two positioning key points;
and an offset calculation module: calculating offset distances and angles of the overstretched position vertebrae and the overstretched position vertebrae respectively based on thermodynamic diagrams of the positioning key points;
and a result judging module: and outputting a diagnosis result according to the offset distance difference and the angle difference of the relative positions between the overstretching position and the overstretching position.
2. The system for diagnosing lumbar instability and slippage based on a network of claim 1 wherein said medical image is a lumbar DR image and said key points are lumbar bone sites.
3. The lumbar instability and slippage diagnosis system based on a Unet network according to claim 1, wherein the key point positioning model modifies an output layer of the Unet network based on the Unet network;
the key point positioning model is input into a lumbar vertebra DR image and output into a thermodynamic diagram for positioning key points of lumbar vertebra bones.
4. The system for diagnosing lumbar instability and slippage based on a Unet network according to claim 3, wherein the input size of the network is kept to be the size of Nx3×512×512 of the original network, and the output is changed to Nx1×512×512, wherein N is the number of input images;
the dimension of the network output is 1, and all key points share one dimension.
5. The lumbar instability and slippage diagnosis system based on the uiet network according to claim 2, wherein the training data set is specifically:
marking lumbar vertebra bone points in the DR image by a medical imaging professional;
preprocessing the marked DR image and converting the DR image into a thermodynamic diagram format;
and training the model by taking the DR image as an input and taking the thermodynamic diagram of the positioning key point as an output.
6. The lumbar instability and slippage diagnosis system of claim 1, wherein the offset calculation module comprises a key point searching unit, a key point sorting unit, an offset distance calculation unit and an angle calculation unit.
7. The lumbar vertebra instability and slippage diagnosis system based on a Unet network according to claim 6, wherein the key point searching unit searches 22 points with maximum thermodynamic values as key points from a thermodynamic diagram output from a key point positioning model.
8. The lumbar spine instability and slippage diagnosis system of claim 6 wherein the key points ordering unit orders according to the coordinate positions of the key points in a top-to-bottom and left-to-right order.
9. The system for diagnosing lumbar instability and slippage based on a network of claim 6 wherein said offset distance calculation unit, after obtaining 22 points after being sorted, respectively making a vertical line from the point of i, i=4, 8,12,16 to the right vertebral point connecting line of the next level, and when i=22, making a vertical line to the vertebral point of the previous level; the distances from the points of i=4, 8,12,16 to the drop foot are then calculated.
10. The system for diagnosing lumbar vertebral instability and slippage based on a network of claim 6 wherein said angle calculating unit calculates the angles of the lower lumbar vertebra and the next upper lumbar vertebra, respectively.
CN202310225252.3A 2023-03-03 2023-03-03 Lumbar vertebra instability and slipping diagnosis system based on Unet network Pending CN116452499A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310225252.3A CN116452499A (en) 2023-03-03 2023-03-03 Lumbar vertebra instability and slipping diagnosis system based on Unet network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310225252.3A CN116452499A (en) 2023-03-03 2023-03-03 Lumbar vertebra instability and slipping diagnosis system based on Unet network

Publications (1)

Publication Number Publication Date
CN116452499A true CN116452499A (en) 2023-07-18

Family

ID=87132784

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310225252.3A Pending CN116452499A (en) 2023-03-03 2023-03-03 Lumbar vertebra instability and slipping diagnosis system based on Unet network

Country Status (1)

Country Link
CN (1) CN116452499A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117670845A (en) * 2023-12-08 2024-03-08 北京长木谷医疗科技股份有限公司 Spinal column slippage identification and assessment method and device based on X-ray medical image
CN117830570A (en) * 2023-12-29 2024-04-05 武汉爱尔眼科洪山医院有限公司 ICL implantation method, system, equipment and readable storage medium based on machine learning
CN117893694A (en) * 2024-03-15 2024-04-16 北京大学第三医院（北京大学第三临床医学院） Atlantoaxial dislocation treatment scheme recommendation method and system

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117670845A (en) * 2023-12-08 2024-03-08 北京长木谷医疗科技股份有限公司 Spinal column slippage identification and assessment method and device based on X-ray medical image
CN117830570A (en) * 2023-12-29 2024-04-05 武汉爱尔眼科洪山医院有限公司 ICL implantation method, system, equipment and readable storage medium based on machine learning
CN117830570B (en) * 2023-12-29 2024-10-29 武汉爱尔眼科洪山医院有限公司 ICL implantation method, system, equipment and readable storage medium based on machine learning
CN117893694A (en) * 2024-03-15 2024-04-16 北京大学第三医院（北京大学第三临床医学院） Atlantoaxial dislocation treatment scheme recommendation method and system

Similar Documents

Publication Publication Date Title
CN116452499A (en) Lumbar vertebra instability and slipping diagnosis system based on Unet network
US8150132B2 (en) Image analysis apparatus, image analysis method, and computer-readable recording medium storing image analysis program
US8194959B2 (en) Medical image part recognition apparatus and medical image part recognition program
JP5186269B2 (en) Image recognition result determination apparatus, method, and program
US8295568B2 (en) Medical image display processing apparatus and medical image display processing program
US20080253631A1 (en) Apparatus and program for assisting report generation
CN108836479B (en) Medical image registration method and surgical navigation system
CN107481276A (en) The automatic identifying method of mark point sequence in a kind of 3 d medical images
CN111179252B (en) Cloud platform-based digestive tract disease focus auxiliary identification and positive feedback system
CN108309334B (en) Data processing method of spine X-ray image
CN101040779A (en) Method and system for virtual slice positioning in a 3d volume data set
CN111311655A (en) Multi-modal image registration method and device, electronic equipment and storage medium
CN112258516A (en) Method for generating scoliosis image detection model
JP7083191B2 (en) Automatic recognition method of measurement points in Cephalo images
CN112802019B (en) Leke typing method based on spine AIS image
CN111861989A (en) Method, system, terminal and storage medium for detecting midline of brain
CN115690178A (en) Cross-module non-rigid registration method, system and medium based on deep learning
CN115937319A (en) Key point marking method based on X-ray image, electronic equipment and storage medium
CN115578320A (en) Full-automatic space registration method and system for orthopedic surgery robot
CN115187606B (en) Juvenile idiopathic scoliosis PUMC typing method
CN111524188A (en) Lumbar positioning point acquisition method, equipment and medium
CN115240029A (en) Training method of image regression model, image regression analysis method, medium, and terminal
JP2008224641A (en) System for estimation of camera attitude
CN113989269B (en) Traditional Chinese medicine tongue image tooth trace automatic detection method based on convolutional neural network multi-scale feature fusion
CN118037656A (en) Automatic diagnosis method for congenital tracheal stenosis of children based on artificial intelligence

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination