CN108491770B - Data processing method based on fracture image - Google Patents
Data processing method based on fracture image Download PDFInfo
- Publication number
- CN108491770B CN108491770B CN201810191832.4A CN201810191832A CN108491770B CN 108491770 B CN108491770 B CN 108491770B CN 201810191832 A CN201810191832 A CN 201810191832A CN 108491770 B CN108491770 B CN 108491770B
- Authority
- CN
- China
- Prior art keywords
- image
- fracture
- data
- lines
- ray film
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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]
Abstract
The invention relates to a data processing method based on fracture images, which comprises the following steps: a) The fracture image is imported into a data processing center; b) Performing image recognition on the imported image; c) Measuring a preset parameter value of the identified image to obtain a group of data values; d) And c) processing the data value obtained in the step c) and outputting the processed data value. The method can help the bone doctor to read the image of the bone and judge the illness state, and greatly improves the working efficiency and quality of the doctor.
Description
Technical Field
The invention belongs to the technical field of medical treatment, and particularly relates to a data processing method based on fracture images.
Background
Along with the change of life style and the aggravation of aging, the incidence of fracture in China is increased year by year. In the diagnosis and treatment of the disease, the X-ray film has important significance and is almost a necessary examination in the diagnosis and treatment process of all patients. However, the method is limited by medical environment and medical level in China, and the method is very difficult to accurately read and fully utilize the fracture X-ray film in actual clinical work. Therefore, the misdiagnosis and missed diagnosis rates of fracture patients in China are high, so that great loss is brought to the health of the patients, and the risk of medical disputes is increased. In addition, the fracture treatment methods are various, and doctors are required to analyze according to the specific conditions of patients, so that the doctors need to grasp the solid professional skills, have rich diagnosis and treatment experience, and have serious consequences for both doctors and patients once the diagnosis and treatment methods are wrong. The above problems are all urgently needed to be solved by effective measures.
The fracture image can display the number, shape, position and relation of the fracture lines and surrounding structures, and the degree of fracture displacement or angulation can be further quantified through measuring various parameters of the X-ray film. However, it is very difficult to accurately read and fully utilize the fracture X-ray film in actual clinical work. The existing application method of fracture X-ray film is manual image reading, and the method has the following problems:
1. has strong speciality
For cases with obvious displacement and large wounds, most doctors can accurately distinguish whether fracture exists. However, due to the uniqueness of the skeletal anatomy, it is difficult for some doctors with insufficient expertise to give a correct diagnosis for certain irregularly shaped, irregularly arranged fracture sites, or fracture sites with insignificant displacement.
2. Misdiagnosis of missing diagnosis
The fracture patient has sudden illness, especially the patient with multiple injuries, the wound is heavy and the condition is complex, and the gold treatment time is short. The emergency treatment workload is large, the time for receiving the diagnosis of each patient is limited, and certain important image parameters cannot be measured in detail and accurately, so that diagnosis and treatment can be influenced, misdiagnosis is caused, and the optimal treatment opportunity of the patient is missed.
3. Complicated parting
The AO typing of fracture has important guiding significance for disease treatment, but the typing rule is complex, hard to remember and easy to forget, and even the bone doctor with abundant experience often causes typing errors due to forgetting, negligence and other reasons, so that the subsequent treatment is influenced.
Disclosure of Invention
In order to solve the technical problems, the invention provides a data processing method based on fracture images. The method can help the bone doctor to read the image of the bone and judge the illness state, and greatly improves the working efficiency and quality of the doctor.
The invention is realized by the following technical scheme: a data processing method based on fracture image comprises the following steps:
a) The fracture image is imported into a data processing center;
b) Performing image recognition on the imported image;
c) Measuring a preset parameter value of the identified image to obtain a group of data values;
d) And c) processing the data value obtained in the step c) and outputting the processed data value.
Further, the fracture image is an X-ray film.
Further, in the step b), the image recognition of the imported image further includes the steps of:
b1 Marking skeleton contour lines on the X-ray film;
b2 Marking a bone fracture line on the X-ray film;
b3 Marking identification lines and/or identification points on the X-ray film;
b4 Displaying part or all of each of the parameter values and the identification lines or points on the X-ray film.
Further, step b) further comprises: b5 The number of the broken lines and/or the positional relationship of the broken lines with the identification line or the identification point are identified.
Further, step c) further comprises measuring parameters required for corresponding typing according to different fracture typing requirements, and storing the parameters in a preset database.
Further, a fracture parting database is preset in the data processing center, in the step d), the processed data value and the parting database are subjected to data matching, and parting results are output according to the matching results.
Further, the typing database comprises an AO typing database.
Furthermore, a treatment scheme corresponding to each type of fracture under different bone parting is preset in the data processing center, and the AO parting result is output and the corresponding treatment scheme is output together.
Further, step b) performs image recognition on the imported image, including the following preprocessing steps:
b01 Firstly, filtering and denoising the image, and then performing linear gray level transformation in a segmented mode;
b02 After the steps, image segmentation and edge extraction are carried out, and morphological filtration is carried out after connected domain treatment is carried out;
b03 Transferring data from the image block to the contour shape;
b04 A path from the image block to the texture is formed through the CNN learning image block texture mode and the combined expression layer of the outline shape mode;
b05 Contour extraction along the path to obtain the contour shape of the bone structure.
Further, step b 03) further comprises:
and performing image scaling on the fracture image to obtain an interested region.
Further, step b) further comprises: b06 Multiple linear regression classifiers are used to obtain a combination of likelihood of skeletal anatomy in the image.
Further, a human-computer interaction mode is adopted, and skeleton contour lines are marked on the X-ray film in a manual auxiliary mode; and/or the number of the groups of groups,
manually marking a broken line on the X-ray film in an auxiliary manner by adopting a man-machine interaction mode; and/or the number of the groups of groups,
and manually marking the identification lines and/or the identification points on the X-ray film in an auxiliary manner by adopting a man-machine interaction mode.
Further, in step c), the method further comprises the step of storing the measured data values in a data processing center database and performing classification management.
Further, in step c), a time recurrent neural network is used to label each image, and the image under the label and the corresponding data value result are stored in a data processing center database.
Further, the fracture image is a wrist joint fracture image or a intertrochanteric fracture image.
Therefore, the invention relates to a method for rapidly and accurately identifying and measuring the fracture X-ray film of a patient by using a computer/artificial intelligent identification-measurement calculation-analysis system, acquiring relevant important parameters, comprehensively analyzing and deducing fracture typing and providing a treatment scheme based on typing. The invention can improve the film reading speed and accuracy of fracture X-ray images, solve the problem of high false diagnosis and missed diagnosis rate of manual film reading, and improve the medical efficiency and medical quality of emergency and orthopedics doctors in the fracture diagnosis and treatment process.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings in connection with embodiments. The principles and features of the present invention are described below with reference to the drawings, and it should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The examples are given solely for the purpose of illustration and are not intended to limit the scope of the invention.
Fracture types are various, and distal radius fracture is the most common fracture in clinical upper limb fracture, accounting for about 1/6 of the total body fracture, and AO typing of distal radius fracture has important guiding significance for fracture treatment. Therefore, in order to better illustrate the technical scheme disclosed by the invention, the invention is specifically described below by selecting distal radius fracture as a specific example.
Noun interpretation:
fracture: fracture refers to a complete or partial fracture of the continuity of a bone structure. Can be caused by violent or accumulated strain, often being a fracture at one part and a few being multiple fractures. After timely and proper treatment, most patients can recover the original functions, and few patients can leave sequelae with different degrees.
Distal radius fracture: a fracture within 3cm from the distal radius joint surface.
The connection between bones is called a joint, and the articular surface is the contact surface of each associated bone that participates in making up the joint.
Center Reference Point (CRP): on the front side image of the wrist joint, the middle point of the connecting line between the dorsal corners of the palmar dorsal aspect of the lunar bone is cut. The radial tilt and ulna variation can be measured more accurately, with the central reference point being located substantially on the coronal plane of the center of the lunar notch, which is not determined by palmar tilt or dorsiflexion.
The radioobliquity (ulnar deviation angle) is an anatomical parameter that is the angle formed between the line connecting the styloid process of the radius to the CRP and the perpendicular to the long axis of the radius. Normal wrist radial tilt is about 24 °. Typically, patients with distal radius fractures have a radial tilt <15 ° with relative surgical indications.
Radius height: as another parameter, it was also used to evaluate the radial contractility. A specific value can be obtained by measuring the distance between two straight lines perpendicular to the reference line, i.e. the long axis of the radius shaft, which are the perpendicular through the apex of the radius styloid and the perpendicular through the CRP, respectively. The normal value of radius height is 11.6mm.
Palm inclination angle: refers to the angle of the vertical line of the central axis of the radius stem and the line of the lateral border of the middle palm of the lateral image. The normal carpal joint metacarpal tilt angle is approximately 10 °. In the lateral image, the palmar inclination angle is used to measure the angulation of the articular surface. Fractures displaced to the palms often show an increase in palmar inclination, which are extremely unstable and require some degree of fixation.
Fracture line: the broken line is an unhealed line of the fracture part on the X-ray, is an important sign for judging whether the fracture is clinically, and indicates that the fracture is not healed if the broken line is not disappeared. Fracture lines are generally classified into complete fracture and incomplete fracture according to fracture lines.
Transverse fracture: the fracture line is almost perpendicular to the diaphyseal longitudinal axis.
Oblique fracture: the fracture line is not perpendicular to the diaphyseal longitudinal axis.
Spiral fracture: the fracture line is spiral.
Comminuted fracture: more than 2 fragments of the fracture, such as T-shaped or Y-shaped broken lines, are also called T-shaped or Y-shaped fracture.
Insertion fracture: after fracture, cortical bone is inserted into cancellous bone.
Artificial intelligence: artificial intelligence (Artificial Intelligence), english is abbreviated AI. It is a new technical science for researching, developing theory, method, technology and application system for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the nature of intelligence and to produce a new intelligent machine that can react in a similar manner to human intelligence, research in this field including robotics, language recognition, image recognition, natural language processing, and expert systems. Artificial intelligence can simulate the information process of consciousness and thinking of people. Artificial intelligence is not human intelligence, but can think like a human, and may also exceed human intelligence.
The convolutional neural network (Convolutional Neural Network, CNN) is a feed-forward neural network whose artificial neurons can respond to surrounding cells in a part of the coverage area with excellent performance for large image processing. It includes a convolution layer (convolutional layer) and a pooling layer (pooling layer).
RCNN (Region-based Convolutional Neural Network), a method for extracting local area information for target detection using convolutional neural networks. The gist of the process of RCNN can be expressed simply as:
1. region of interest ROI extraction of input image by using selective search method
2. Placing the extracted region into a pretrained CNN for feature extraction
3. The SVM classifier is subjected to fine-tuning, and the output labels are changed into N+1
4. Training the SVM, and obtaining the classification of the detection target and the regression of the bounding box by using the trained SVM for the feature vector coming out of the CNN.
Fast-RCNN and Fast-RCNN are further improved image recognition algorithms based on RCNN, so that the speed during testing and training is improved, and the training space is reduced.
Referring to fig. 1, a flowchart of an embodiment of a data processing method based on fracture image according to the present invention is shown.
First, image acquisition
The normal X-ray film and the lateral X-ray film of the wrist joint image are led into a data processing center, and other X-ray films can be led in if necessary.
The introduction mode may be obtained from a PACS system of the imaging department of the hospital by using a DICOM system and then directly introduced, or may be introduced after shooting by a mode of shooting pictures. The data processing center is used for processing data of the imported image, and can be a computer software system or a processing system of mobile equipment such as a mobile phone, a tablet computer and the like. The data processing center can be integrated with the display end after data processing, or the required result is returned to the transmitting end after the data processing center processes the image after the image is transmitted to the data processing center in a remote communication mode.
The X-ray film required is different for the bone of the non-passing type, some bones can need to be positioned at two sides, some bones can need only one position, some lights can not be positioned at all, and the images of the inclined positions or other positions can be needed.
Second, image recognition
Image recognition is carried out on the imported image, and pretreatment is needed to be carried out on the image, and the method comprises the following steps:
b01 Filtering the image, and then performing linear gray level conversion in a segmented mode;
b02 After the steps, image segmentation and edge extraction are carried out, and morphological filtration is carried out after connected domain treatment is carried out;
b03 Transferring data from the image block to the contour shape using a multi-modal depth boltzmann machine (Deep Boltzmann Machine);
b04 A path from the image block to the texture is formed through the CNN learning image block texture mode and the combined expression layer of the outline shape mode;
b05 Contour extraction along the path using Gibbs Sampling (Gibbs Sampling) method, resulting in a contour shape of the bone structure.
b06 Multiple linear regression classifiers are used to obtain a combination of likelihood of skeletal anatomy in the image.
After the image preprocessing, operations such as scribing, marking and the like are needed to be carried out on the image, and the method specifically comprises the following steps:
b1 Marking skeleton contour lines on the X-ray film;
b2 Marking a bone fracture line on the X-ray film;
b3 Marking identification lines and/or identification points on the X-ray film;
b4 Displaying part or all of each of the parameter values and the identification lines or points on the X-ray film;
b5 The number of fracture lines and the positional relationship of the fracture lines and the identification lines or points are identified.
The identification line and the identification point are different according to different bone types, and when the data processing of fracture images is carried out on the wrist joint, a Central Reference Point (CRP) needs to be identified, wherein the reference point is the identification point, and is positioned on the front side image of the wrist joint, and the midpoint of the connecting line between the back side angles of the lunar bone notch palms. The radial tilt and ulna variation can be measured more accurately, with the central reference point being located substantially on the coronal plane of the center of the lunar notch, which is not determined by palmar tilt or dorsiflexion.
In addition, the angle line of the radial dip angle (ulnar deviation angle) is the included angle formed between the line from the styloid process of the radius to the CRP and the perpendicular to the long axis of the radius, and can be marked as a marking line. Normal wrist radial tilt is about 24 °. Typically, patients with distal radius fractures have a radial tilt <15 ° with relative surgical indications.
Another parameter is the height of the radius, which is also used as another parameter for assessing the contractility of the radius. A specific value can be obtained by measuring the distance between two straight lines perpendicular to the reference line, i.e. the long axis of the radius shaft, which are the perpendicular through the apex of the radius styloid and the perpendicular through the CRP, respectively. The normal value of radius height is 11.6mm.
In the process of image identification, if the growth and development conditions of some individuals are more special, the individuals can not be automatically identified by adopting a conventional algorithm, or doctors have preference, or a man-machine interaction mode can be adopted, so that the doctors can manually mark skeleton contour lines on the X-ray film in an auxiliary manner, or mark fracture lines on the X-ray film in an auxiliary manner, or mark identification lines and/or identification points on the X-ray film in an auxiliary manner.
In the identification process, if the individual development condition is very normal, the image data is clear, the identification is easy, and the identification operation can be completely carried out by a computer.
In another specific embodiment, a man-machine interaction mode can be adopted, a doctor can assist in drawing a part of lines or points needing special identification, and the rest of lines or points are processed by a computer data processing center.
The different modes can be selected by a doctor to operate, so that more requirements can be met, and the application range of the method is improved.
By using the method for identifying the imported image, the accuracy is high, the self-adaption capability is strong, and the processing speed is high and rapid.
Third, image analysis, parameter measurement
After the image recognition work is completed, the radius structure can be analyzed and measured according to a series of constraint conditions, and the fracture displacement or angulation degree can be quantified. The image analysis includes removing background clutter, identifying key areas, ulna, radius, ulna-radius joint and surrounding carpal bones, identifying abnormal fracture lines and fracture blocks, and measuring related parameters (number, position, relation with joint surfaces, radius height, ulna deflection angle and palmar inclination angle) as typing input parameters. For specific meaning of each parameter, please refer to the above explanation of nouns.
Because the doctor only has difficulty in implementing according to a simple operation scheme when doing an operation for the patient, in order to facilitate the doctor to conveniently view the image at any time in the operation, the data processing center can add the identification line or the identification point on the image, and the doctor can selectively display the parameter values and the identification line or the identification point on the image partially or completely according to the needs. Therefore, the image with the mark can be directly printed, so that a doctor can check the image at any time during operation conveniently, and various defects of manual scribing are overcome.
Fourth, data analysis
According to the parameter values which are directly measured, the data analysis is carried out on part of the data to obtain new data so as to meet the requirements of doctors and facilitate the doctors to judge the illness state according to the analysis results.
5. Result output
In terms of output results, in order to maximally reduce the workload of doctors and improve the medical efficiency, various databases for bone analysis, such as an AO analysis database, are preset in a data processing center, the processed data values and the typing database are subjected to data matching and storage, and the typing results are output according to the matching results.
In order to facilitate a doctor to quickly and accurately obtain a treatment scheme directly, the treatment scheme corresponding to each type under various bone parting is preset in the data processing center, and the parting result is output and the corresponding treatment scheme is output together.
In addition, in order to improve the accuracy and efficiency of the processing system, after each image picture of a case is processed, a time recurrent neural network is used to label each image, and the image under the label and the corresponding data value result are stored in a data processing center database. Therefore, the data can be continuously accumulated, the artificial intelligence deep learning effect of the system is continuously enhanced, and the image processing speed is faster and more accurate.
According to the method provided by the invention, the basic image information of the wrist joint positive side X-ray film is firstly obtained through a CNN image recognition series technology (RCNN, fast-CNN and Fast-CNN), the specific positioning of the bone fracture line is obtained through further processing of the image, the key parameters are obtained through automatic measurement and calculation of a computer, the specific AO typing or other typing can be obtained through further deduction of the parameters, and finally the optimal treatment suggestion is proposed according to the typing.
The above embodiments are only described by taking the wrist bone as an example, and the method may also be used for processing the image data of the fracture image between the trochanters of femur or other bones, and the specific method is not described herein.
The data processing method based on fracture image disclosed by the invention is suitable for auxiliary diagnosis, parting and auxiliary treatment of fracture, can be used for rapidly and accurately identifying and measuring the fracture X-ray film of a patient, acquiring relevant important parameters, comprehensively analyzing and deducing fracture parting, can provide various parting schemes for the same fracture X-ray film according to clinical requirements, and can provide corresponding treatment schemes based on each parting, thereby being used for auxiliary operation scheme design. The invention can improve the film reading speed and accuracy of the fracture X-ray image, can rapidly and accurately obtain the key data of the fracture X-ray image, solves the problem of high misdiagnosis and missed diagnosis rate of the manual film reading, and improves the medical efficiency and medical quality of emergency and orthopedics doctors in the fracture diagnosis and treatment process.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (14)
1. The data processing method based on the fracture image is characterized by comprising the following steps of:
a) The fracture image is imported into a data processing center;
b) Performing image recognition on the imported image;
c) Measuring a preset parameter value of the identified image to obtain a group of data values; the parameter values comprise the number and the position of the broken lines, the relation between the broken lines and the joint surface, the height of the radius, the ulna deflection angle and the palm inclination angle;
d) Processing the data value obtained in the step c) and outputting the processed data value;
step b) of image recognition of the imported image, comprising the steps of:
b01 Filtering the image, and then performing linear gray level conversion in a segmented mode;
b02 After the steps, image segmentation and edge extraction are carried out, and morphological filtration is carried out after connected domain treatment is carried out;
b03 Transferring data from the image block to the contour shape;
b04 A path from the image block to the texture is formed through the CNN learning image block texture mode and the combined expression layer of the outline shape mode;
b05 Contour extraction along the path to obtain the contour shape of the bone structure.
2. The method of claim 1, wherein the fracture image is an X-ray film.
3. The method for processing bone fracture image-based data according to claim 2, wherein in the step b), the image recognition is performed on the imported image, further comprising the steps of:
b1 Marking skeleton contour lines on the X-ray film;
b2 Marking a bone fracture line on the X-ray film;
b3 Marking identification lines and/or identification points on the X-ray film;
b4 Displaying part or all of each of the parameter values and the identification lines or points on the X-ray film.
4. A method of processing bone fracture image based data according to claim 3, wherein step b) further comprises:
b5 The number of fracture lines and/or the positional relationship of the fracture lines to the identification lines and/or points are identified.
5. The method of claim 4, wherein step c) further comprises measuring parameters required for the corresponding typing according to different fracture typing requirements, and storing the parameters in a preset database.
6. The method according to claim 1, wherein a fracture typing database is preset in the data processing center, and in step d), the processed data value is subjected to data matching with the typing database, and the typing result is output according to the matching result.
7. The method of claim 6, wherein the typing database comprises an AO typing database.
8. The method for processing data based on fracture image according to claim 6, wherein the data processing center is further preset with a treatment scheme corresponding to each type of fracture under different bone parting, and outputs the AO parting result and the corresponding treatment scheme.
9. The method of claim 1, wherein step b 03) further comprises:
and performing image scaling on the fracture image to obtain an interested region.
10. The method of claim 9, wherein step b) further comprises:
b06 Multiple linear regression classifiers are used to obtain a combination of likelihood of skeletal anatomy in the image.
11. A method for processing data based on fracture image according to claim 3, wherein,
manually marking skeleton contour lines on the X-ray film in an auxiliary manner by adopting a man-machine interaction mode; and/or the number of the groups of groups,
manually marking a broken line on the X-ray film in an auxiliary manner by adopting a man-machine interaction mode; and/or the number of the groups of groups,
and manually marking the identification lines and/or the identification points on the X-ray film in an auxiliary manner by adopting a man-machine interaction mode.
12. The method for processing bone fracture image based data according to any one of claims 1 to 11, further comprising, in step c)
And storing the measured data values in a data processing center database and performing classified management.
13. The method for processing bone fracture image based data according to any one of claims 1 to 11, further comprising, in step c)
And labeling each image by using a time recurrent neural network, and storing the labeled images and the corresponding data value results in a data processing center database.
14. A method of processing data based on fracture imaging according to any one of claims 1 to 11, wherein the fracture image is a wrist fracture image or a intertrochanteric fracture image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810191832.4A CN108491770B (en) | 2018-03-08 | 2018-03-08 | Data processing method based on fracture image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810191832.4A CN108491770B (en) | 2018-03-08 | 2018-03-08 | Data processing method based on fracture image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108491770A CN108491770A (en) | 2018-09-04 |
| CN108491770B true CN108491770B (en) | 2023-05-30 |
Family
ID=63338047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810191832.4A Active CN108491770B (en) | 2018-03-08 | 2018-03-08 | Data processing method based on fracture image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108491770B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3614337A1 (en) * | 2018-08-19 | 2020-02-26 | Chang Gung Memorial Hospital, Linkou | Method and system of analyzing medical images |
| CN109124836B (en) * | 2018-09-18 | 2021-04-30 | 北京爱康宜诚医疗器材有限公司 | Method and device for determining acetabular bone defect treatment mode |
| CN109106481B (en) * | 2018-09-18 | 2021-04-30 | 北京爱康宜诚医疗器材有限公司 | Method and device for determining acetabular bone defect degree |
| KR102540998B1 (en) * | 2019-01-18 | 2023-06-05 | 가톨릭대학교 산학협력단 | Method And Apparatus For Generating Virtual Internal Fixation Device Based On Image Reduction |
| CN111354057B (en) * | 2020-03-10 | 2022-07-08 | 中南大学 | Bone fracture line map drawing method based on image deformation technology |
| CN111899880A (en) * | 2020-08-03 | 2020-11-06 | 暨南大学附属第一医院（广州华侨医院） | Lumbar vertebra trabecular load stress change and hidden fracture artificial risk assessment method |
| CN111933281B (en) * | 2020-09-30 | 2021-02-12 | 平安科技（深圳）有限公司 | Disease typing determination system, method, device and storage medium |
| CN112435269A (en) * | 2020-12-02 | 2021-03-02 | 山东中医药大学 | Distal radius fracture image processing method based on fast-RCNN |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002096280A2 (en) * | 2001-05-29 | 2002-12-05 | Innovationsagentur Gesellschaft M.B.H. | Method and device for obtaining information relating to a bone fracture |
| EP1293925A1 (en) * | 2001-09-18 | 2003-03-19 | Agfa-Gevaert | Radiographic scoring method |
| CN1682236A (en) * | 2002-08-20 | 2005-10-12 | 成像治疗仪股份有限公司 | Methods and devices for analysis of X-ray images |
| CN101452577A (en) * | 2008-11-26 | 2009-06-10 | 沈阳东软医疗系统有限公司 | Rib auto-demarcating method and device |
| CN106023094A (en) * | 2016-05-10 | 2016-10-12 | 中南大学 | Image-based bone tissue microstructure restoration system and restoration method thereof |
| CN107154038A (en) * | 2016-04-22 | 2017-09-12 | 孔德兴 | A kind of visual fracture of rib aided diagnosis method of rib |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8064660B2 (en) * | 2004-02-27 | 2011-11-22 | National University Of Singapore | Method and system for detection of bone fractures |
| US9480439B2 (en) * | 2012-11-01 | 2016-11-01 | Virginia Commonwealth University | Segmentation and fracture detection in CT images |
-
2018
- 2018-03-08 CN CN201810191832.4A patent/CN108491770B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002096280A2 (en) * | 2001-05-29 | 2002-12-05 | Innovationsagentur Gesellschaft M.B.H. | Method and device for obtaining information relating to a bone fracture |
| EP1293925A1 (en) * | 2001-09-18 | 2003-03-19 | Agfa-Gevaert | Radiographic scoring method |
| CN1682236A (en) * | 2002-08-20 | 2005-10-12 | 成像治疗仪股份有限公司 | Methods and devices for analysis of X-ray images |
| CN101452577A (en) * | 2008-11-26 | 2009-06-10 | 沈阳东软医疗系统有限公司 | Rib auto-demarcating method and device |
| CN107154038A (en) * | 2016-04-22 | 2017-09-12 | 孔德兴 | A kind of visual fracture of rib aided diagnosis method of rib |
| CN106023094A (en) * | 2016-05-10 | 2016-10-12 | 中南大学 | Image-based bone tissue microstructure restoration system and restoration method thereof |
Non-Patent Citations (2)
| Title |
|---|
| N. Umadevi等.Multiple classification system for fracture detection in human bone x-ray images.《2012 Third International Conference on Computing, Communication and Networking Technologies (ICCCNT"12)》.2012, * |
| 基于BP神经网络的CT图像骨皮质分割;卫娇;《医用生物力学》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108491770A (en) | 2018-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108491770B (en) | Data processing method based on fracture image | |
| EP3567525A1 (en) | Systems and methods for analysis of anatomical images each captured at a unique orientation | |
| CN109544518B (en) | Method and system applied to bone maturity assessment | |
| CN112734757B (en) | Spine X-ray image cobb angle measuring method | |
| CN108309334B (en) | Data processing method of spine X-ray image | |
| EP3654343A1 (en) | Application of deep learning for medical imaging evaluation | |
| Ogiela et al. | Image languages in intelligent radiological palm diagnostics | |
| Mansourvar et al. | Automated web based system for bone age assessment using histogram technique | |
| Mihail et al. | Automatic hand skeletal shape estimation from radiographs | |
| Thangam et al. | Skeletal Bone Age Assessment-Research Directions. | |
| Liu et al. | Artificial intelligence to diagnose tibial plateau fractures: an intelligent assistant for orthopedic physicians | |
| Karanam et al. | A statistical model approach based on the Gaussian Mixture Model for the diagnosis and classification of bone fractures | |
| Pham et al. | Chest x-rays abnormalities localization and classification using an ensemble framework of deep convolutional neural networks | |
| Sathish Kumar et al. | A comparative experimental analysis and deep evaluation practices on human bone fracture detection using x‐ray images | |
| Akhbardeh et al. | Classification and assessment of hand arthritis stage using support vector machine | |
| Duryea et al. | Automated algorithm for the identification of joint space and phalanx margin locations on digitized hand radiographs | |
| Sumi et al. | Classifying humerus fracture using x-ray images | |
| CN116564458A (en) | Data processing method, system, equipment and medium based on electronic medical record | |
| CN116664592A (en) | Image-based arteriovenous blood vessel separation method and device, electronic equipment and medium | |
| Duryea et al. | Neural network based automated algorithm to identify joint locations on hand/wrist radiographs for arthritis assessment | |
| Ogiela et al. | Graph image language techniques supporting radiological, hand image interpretations | |
| CN115206478A (en) | Medical report generation method and device, electronic equipment and readable storage medium | |
| Antani et al. | Vertebra shape classification using MLP for content-based image retrieval | |
| Bhisikar et al. | Automatic analysis of rheumatoid Arthritis based on statistical features | |
| Su et al. | Combining frontal and profile view facial images to predict difficult-to-intubate patients using AI |
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 |