CN111724357B - Arm bone density measurement method based on digital radiological image and support vector regression - Google Patents
Arm bone density measurement method based on digital radiological image and support vector regression Download PDFInfo
- Publication number
- CN111724357B CN111724357B CN202010516559.5A CN202010516559A CN111724357B CN 111724357 B CN111724357 B CN 111724357B CN 202010516559 A CN202010516559 A CN 202010516559A CN 111724357 B CN111724357 B CN 111724357B
- Authority
- CN
- China
- Prior art keywords
- image
- gray
- features
- bone density
- value
- 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
- 230000037182 bone density Effects 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 26
- 210000000784 arm bone Anatomy 0.000 title claims abstract description 11
- 238000001739 density measurement Methods 0.000 title description 5
- 210000000988 bone and bone Anatomy 0.000 claims abstract description 17
- 229910052500 inorganic mineral Inorganic materials 0.000 claims abstract description 14
- 239000011707 mineral Substances 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000010606 normalization Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000000265 homogenisation Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract description 2
- 230000011218 segmentation Effects 0.000 abstract description 2
- 208000001132 Osteoporosis Diseases 0.000 description 8
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000010392 Bone Fractures Diseases 0.000 description 1
- 206010017076 Fracture Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000012631 diagnostic technique Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000000245 forearm Anatomy 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000000623 ulna Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- 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
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
-
- 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
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- High Energy & Nuclear Physics (AREA)
- Optics & Photonics (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Quality & Reliability (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an arm bone density measuring method based on digital radiological images and support vector regression, which comprises the following steps: s1, inputting a DR image and segmenting out a region of interest; s2, respectively extracting gray features and texture features of the DR image from the region of interest; s3, building a regression model by using the support vector: establishing a regression model by using an SVR algorithm, and carrying out regression by using the image characteristic values extracted in the S2 and the corresponding bone density label data; s4, calculating a bone mineral density predicted value and outputting a predicted result: and (3) predicting the bone density of the DR image of the new subject by using the regression model generated by training in the step S3. According to the invention, the segmentation of the region of interest and the extraction of the image features are carried out on the existing DR image, and the regression model is established by the SVR algorithm to measure the bone density of the DR image.
Description
Technical Field
The invention belongs to the technical field of computer vision and medical image processing, and particularly relates to an arm bone density measurement method based on digital radiological images and support vector regression.
Background
Osteoporosis is a common and frequently occurring disease that severely threatens the health of the middle-aged and elderly people. Over 2 million patients worldwide are currently in existence, and osteoporosis is an increasingly serious public health problem. Although diagnostic techniques are now advancing, diagnostic methods for osteoporosis remain unpopular. The main basis for diagnosing osteoporosis is to measure the decrease in bone density of the bones. Bone density is a quantitative diagnostic index for bone and is commonly used for diagnosing osteoporosis, predicting fracture risk and assessing treatment effect.
Currently, the Dual-energy X-ray absorption method (Dual X-ray Absorptiometry, DXA) for detecting bone density is a standard accepted by clinical diagnosis of osteoporosis, and is also the only unified index recommended by the world health organization to be used as a global diagnosis of osteoporosis. However, DXA is not very widely used because of the disadvantages of relatively expensive detection equipment, high maintenance costs, and the need for specialized training for professional operations.
In this context, the application of artificial intelligence technology to the medical field has made possible the development of new bone density measurement techniques.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides the arm bone density measuring method based on digital radiological image and support vector regression, which is used for segmenting the region of interest and extracting the image characteristics on the existing DR image, and the regression model is established through the SVR algorithm to measure the arm bone density, so that the errors caused by different bone density detectors are eliminated, and the accuracy of bone density assessment is improved.
The aim of the invention is realized by the following technical scheme: the arm bone density measuring method based on digital radiological image and support vector regression comprises the following steps:
s1, inputting a DR image and segmenting out a region of interest;
s2, extracting image features of the segmented regions, and respectively extracting gray features and texture features of the DR images of the segmented regions of interest;
s3, building a regression model by using the support vector: establishing a regression model by using an SVR algorithm, and carrying out regression by using the image characteristic values extracted in the S2 and the corresponding bone density label data;
s4, calculating a bone mineral density predicted value and outputting a predicted result: and (3) predicting the bone density of the DR image of the new subject by using the regression model generated by training in the step S3.
Further, the step S1 includes the following substeps:
s11, segmenting an interested region from an original DR image;
s12, carrying out normalization processing on the image obtained in the step S11, and normalizing the pixel value of the image to be between 0 and 255.
Further, the specific implementation method of the step S2 is as follows:
s21, extracting gray features: respectively extracting 5 gray features of mean, variance, standard deviation, energy and entropy by calculating a gray histogram of the DR image;
average value: reflecting the gray average value of a DR image:
h (i) represents the gray value of the i-th point, and L represents the gray level number of the image;
variance: reflecting the discrete distribution of gray scale of a DR image in terms of value:
standard deviation: is the square root of the variance;
energy: the uniformity of gray level distribution is reflected, and the calculation formula is as follows:
entropy: the uniformity of gray level histogram distribution is reflected, and the calculation formula is as follows:
s22, extracting texture features: extracting the texture features of the image by adopting a gray level co-occurrence matrix method, and respectively extracting 4 texture features of second moment, contrast, correlation and homogeneity;
second moment: reflects the smoothness of a DR image, and the calculation formula is as follows:
W 1 =∑ i ∑ j [m(i,j)] 2
m (i, j) represents an element in a gray level co-occurrence matrix, the gray level matrix being defined as a probability from a point of an original image having a gray level i to a point of the original image having a gray level j; i, j=0, 1,2,., L-1;
contrast ratio: the definition of a DR image is reflected, and the calculation formula is as follows:
W 2 =∑ i ∑ j (i-j) 2 m(i,j)
correlation coefficient: the linear correlation degree of rows and columns in the gray level co-occurrence matrix is reflected, and the calculation formula is as follows:
wherein,,
μ x =∑ i i∑ j m(i,j)
μ y =∑ j j∑ i m(i,j)
homogenization: the distribution of elements in the gray level co-occurrence matrix to the diagonal tightness degree is reflected, and the calculation formula is as follows:
s23, data summarizing is carried out on the extracted gray features and texture features, data normalization processing is carried out on feature values, and different features are scaled to map to a specific interval of [ -1,1 ];
the normalized formula is:
where x is the original eigenvalue, x * The normalized characteristic value; mean is the mean value of the feature data, max is the maximum value of the feature data, and min is the minimum value of the feature data.
Further, in the step S3, the bone mineral density label data is the real bone mineral density corresponding to the image.
The beneficial effects of the invention are as follows:
1. the method of the invention performs segmentation of the region of interest and extraction of image features on the existing DR image, and establishes a regression model through SVR algorithm to measure the bone density of the DR image.
2. The bone mineral density measuring result of the method disclosed by the invention is similar to the acquisition result of the existing bone mineral density detector, has small measuring error and high measuring precision, is favorable for improving the accuracy of bone mineral density evaluation, and can be used for clinical detection of the bone mineral density of human arms.
3. Compared with the traditional DXA method, the method disclosed by the invention is favorable for eliminating errors caused by different bone density detectors and improving the repeatability research of experiments, so that the method is expected to become one of the technologies for diagnosing osteoporosis with the most development prospect.
Drawings
FIG. 1 is a flow chart of an arm bone density measurement method based on digital radiological images and support vector regression according to the present invention;
FIG. 2 is a DR image acquired in the present embodiment;
fig. 3 is a region of interest image.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, the method for measuring the arm bone density based on digital radiological image and support vector regression of the invention comprises the following steps:
s1, inputting a DR image and segmenting out a region of interest; the method specifically comprises the following substeps:
s11, segmenting an interested region from an original DR image;
s12, carrying out normalization processing on the image obtained in the step S11, and normalizing the pixel value of the image to be between 0 and 255.
DR image data was acquired on forearms of 173 male and female subjects using an existing bone density detector, as shown in fig. 2; a diagnostic report containing clinical information such as bone density is collected, and the region of interest of the collected DR image data is manually segmented, effectively segmenting the region of interest of bone (ulna region, as shown in fig. 3).
S2, extracting image features of the segmented regions, and respectively extracting gray features and texture features of the DR images of the segmented regions of interest; the specific implementation method comprises the following steps:
s21, extracting gray features: respectively extracting 5 gray features of mean, variance, standard deviation, energy and entropy by calculating a gray histogram of the DR image;
average value: reflecting the gray average value of a DR image:
h (i) represents the gray value of the i-th point, and L represents the gray level number of the image;
variance: reflecting the discrete distribution of gray scale of a DR image in terms of value:
standard deviation: is the square root of the variance;
energy: the uniformity of gray level distribution is reflected, and the calculation formula is as follows:
entropy: the uniformity of gray level histogram distribution is reflected, and the calculation formula is as follows:
and 5 gray level features of the mean, the variance, the standard deviation, the energy and the entropy are extracted through the gray level histogram corresponding to the image, wherein the gray level features are 708619223, 5.03144983470948e+23, 709327134311.770, 286421983777.000 and 62393739.6779687 respectively.
S22, extracting texture features: extracting the texture features of the image by adopting a gray level co-occurrence matrix method, and respectively extracting 4 texture features of second moment, contrast, correlation and homogeneity;
second moment: reflects the smoothness of a DR image, and the calculation formula is as follows:
W 1 =∑ i ∑ j [m(i,j)] 2
m (i, j) represents an element in a gray level co-occurrence matrix, the gray level matrix being defined as a probability from a point of an original image having a gray level i to a point of the original image having a gray level j; i, j=0, 1,2,., L-1;
contrast ratio: the definition of a DR image is reflected, and the calculation formula is as follows:
W 2 =∑ i ∑ j (i-j) 2 m(i,j)
correlation coefficient: the linear correlation degree of rows and columns in the gray level co-occurrence matrix is reflected, and the calculation formula is as follows:
wherein,,
μ x =∑ i i∑ j m(i,j)
μ y =∑ j j∑ i m(i,j)
homogenization: the distribution of elements in the gray level co-occurrence matrix to the diagonal tightness degree is reflected, and the calculation formula is as follows:
the results of the extracted 4 features of the present embodiment are 0.350538853001145, 0.0203936063936064, 0.998352776124655, 0.989803196803197, respectively.
S23, data summarizing is carried out on the extracted gray features and texture features, data normalization processing is carried out on feature values, and different features are scaled to map to a specific interval of [ -1,1 ];
the normalized formula is:
wherein x is the originalEigenvalues, x * The normalized characteristic value; mean is the mean value of the feature data, max is the maximum value of the feature data, and min is the minimum value of the feature data. The normalization of this example resulted in-0.0676965, -0.151447, -0.0676965,0.248400, -0.965191, -0.196041, -0.115126,0.191109, 0.115126.
S3, building a regression model by using the support vector: a regression model is established by using SVR algorithm, and regression is performed by using the image characteristic values (-0.0676965, -0.151447, -0.0676965,0.248400, -0.965191, -0.196041, -0.115126,0.191109,0.115126) extracted in S2 and the bone density label (real bone density 0.788) of the image. The idea of the SVR algorithm is:
given a training sample, d= { (x) 1 ,y 1 ),(x 2 ,y 2 ),......,(x m ,y m )},y i E R, a regression model is trained such that f (x) is as close as possible to y, w and b being the model parameters to be determined. Model parameters of the SVR are adjusted through a grid search method, so that an optimal model suitable for measuring bone mineral density is determined.
S4, calculating a bone mineral density predicted value and outputting a predicted result: the bone density of DR image of the new subject was predicted using the regression model generated by training in S3, and the predicted result in this example was 0.777952.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (3)
1. The arm bone density measuring method based on digital radiological image and support vector regression is characterized by comprising the following steps:
s1, inputting a DR image and segmenting out a region of interest;
s2, extracting image features of the segmented regions, and respectively extracting gray features and texture features of the DR images of the segmented regions of interest; the specific implementation method comprises the following steps:
s21, extracting gray features: respectively extracting 5 gray features of mean, variance, standard deviation, energy and entropy by calculating a gray histogram of the DR image;
average value: reflecting the gray average value of a DR image:
h (i) represents the gray value of the i-th point, and L represents the gray level number of the image;
variance: reflecting the discrete distribution of gray scale of a DR image in terms of value:
standard deviation: is the square root of the variance;
energy: the uniformity of gray level distribution is reflected, and the calculation formula is as follows:
entropy: the uniformity of gray level histogram distribution is reflected, and the calculation formula is as follows:
s22, extracting texture features: extracting the texture features of the image by adopting a gray level co-occurrence matrix method, and respectively extracting 4 texture features of second moment, contrast, correlation and homogeneity;
second moment: reflects the smoothness of a DR image, and the calculation formula is as follows:
W 1 =∑ i ∑ j [m(i-j)] 2
m (i, j) represents an element in the gray level co-occurrence matrix, i, j=0, 1,2, …, L-1;
contrast ratio: the definition of a DR image is reflected, and the calculation formula is as follows:
W 2 =∑ i ∑ j (i-j) 2 m(i,j)
correlation coefficient: the linear correlation degree of rows and columns in the gray level co-occurrence matrix is reflected, and the calculation formula is as follows:
wherein,,
μ x =∑ i i∑ j m(i,j)
μ y =∑ j j∑ i m(i,j)
homogenization: the distribution of elements in the gray level co-occurrence matrix to the diagonal tightness degree is reflected, and the calculation formula is as follows:
s23, data summarizing is carried out on the extracted gray features and texture features, data normalization processing is carried out on feature values, and different features are scaled to map to a specific interval of [ -1,1 ];
the normalized formula is:
where x is the original eigenvalue, x * The normalized characteristic value; mean is the mean value of the feature data, max is the maximum value of the feature data, and min is the minimum value of the feature data;
s3, building a regression model by using the support vector: establishing a regression model by using an SVR algorithm, and carrying out regression by using the image characteristic values extracted in the S2 and the corresponding bone density label data;
s4, calculating a bone mineral density predicted value and outputting a predicted result: and (3) predicting the bone density of the DR image of the new subject by using the regression model generated by training in the step S3.
2. The method for measuring arm bone density based on digital radiological image and support vector regression according to claim 1, wherein the step S1 comprises the sub-steps of:
s11, segmenting an interested region from an original DR image;
s12, carrying out normalization processing on the image obtained in the step S11, and normalizing the pixel value of the image to be between 0 and 255.
3. The method for measuring the bone mineral density of the arm based on the digital radiological image and the support vector regression according to claim 1, wherein the bone mineral density label data in the step S3 is the real bone mineral density corresponding to the image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010516559.5A CN111724357B (en) | 2020-06-09 | 2020-06-09 | Arm bone density measurement method based on digital radiological image and support vector regression |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010516559.5A CN111724357B (en) | 2020-06-09 | 2020-06-09 | Arm bone density measurement method based on digital radiological image and support vector regression |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111724357A CN111724357A (en) | 2020-09-29 |
CN111724357B true CN111724357B (en) | 2023-05-16 |
Family
ID=72566244
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010516559.5A Active CN111724357B (en) | 2020-06-09 | 2020-06-09 | Arm bone density measurement method based on digital radiological image and support vector regression |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111724357B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116458909B (en) * | 2023-04-10 | 2024-05-07 | 清华大学 | Method and device for measuring three-dimensional bone density distribution by using cone beam DR equipment |
CN116486021B (en) * | 2023-06-25 | 2023-08-18 | 天津医科大学总医院 | Three-dimensional model construction method and system based on CT density value and ultrasonic gray value |
CN117876372B (en) * | 2024-03-12 | 2024-05-28 | 中国医学科学院生物医学工程研究所 | Bone quality identification model training method based on label-free nonlinear multi-modal imaging |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1735373A (en) * | 2003-01-07 | 2006-02-15 | 成像治疗仪股份有限公司 | Methods of predicting musculoskeletal disease |
CN108447044A (en) * | 2017-11-21 | 2018-08-24 | 四川大学 | A kind of osteomyelitis lesions analysis method based on medical figure registration |
CN108764355A (en) * | 2018-05-31 | 2018-11-06 | 清华大学 | Image processing apparatus and method based on textural characteristics classification |
CN110200650A (en) * | 2019-05-31 | 2019-09-06 | 昆明理工大学 | A method of detection bone density |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6442287B1 (en) * | 1998-08-28 | 2002-08-27 | Arch Development Corporation | Method and system for the computerized analysis of bone mass and structure |
WO2004086972A2 (en) * | 2003-03-25 | 2004-10-14 | Imaging Therapeutics, Inc. | Methods for the compensation of imaging technique in the processing of radiographic images |
US20130342577A1 (en) * | 2012-06-20 | 2013-12-26 | Carestream Health, Inc. | Image synthesis for diagnostic review |
JP5722414B1 (en) * | 2013-11-25 | 2015-05-20 | メディア株式会社 | Osteoporosis diagnosis support device |
JP6515936B2 (en) * | 2015-02-13 | 2019-05-22 | 株式会社島津製作所 | Bone analyzer |
-
2020
- 2020-06-09 CN CN202010516559.5A patent/CN111724357B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1735373A (en) * | 2003-01-07 | 2006-02-15 | 成像治疗仪股份有限公司 | Methods of predicting musculoskeletal disease |
CN108447044A (en) * | 2017-11-21 | 2018-08-24 | 四川大学 | A kind of osteomyelitis lesions analysis method based on medical figure registration |
CN108764355A (en) * | 2018-05-31 | 2018-11-06 | 清华大学 | Image processing apparatus and method based on textural characteristics classification |
CN110200650A (en) * | 2019-05-31 | 2019-09-06 | 昆明理工大学 | A method of detection bone density |
Non-Patent Citations (3)
Title |
---|
Ehab I. Mohamed等.A novel morphological analysis of DXA-DICOM images by artificial neural networks for estimating bone mineral density in health and disease.《Journal of Clinical Densitometry》.2019,第22卷382-390. * |
孙涛.基于DR骨密度分析系统的研究.《中国优秀硕士学位论文全文数据库 医药卫生科技辑》.2012,(第2期),E065-110. * |
罗涛 ; 李剑峰 ; 韩家辉 ; 王艺宁 ; 雷璐 ; .一种基于多模态特征融合的骨质疏松评估方法.北京邮电大学学报.(06),84-90. * |
Also Published As
Publication number | Publication date |
---|---|
CN111724357A (en) | 2020-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111724357B (en) | Arm bone density measurement method based on digital radiological image and support vector regression | |
Saikumar et al. | A novel implementation heart diagnosis system based on random forest machine learning technique. | |
CN107103187B (en) | Lung nodule detection grading and management method and system based on deep learning | |
US8126242B2 (en) | Computer program products and methods for detection and tracking of rheumatoid arthritis | |
CN110772286B (en) | System for discernment liver focal lesion based on ultrasonic contrast | |
CN109036547A (en) | A kind of lung CT image computer aided system and method based on clustering | |
Udeshani et al. | Statistical feature-based neural network approach for the detection of lung cancer in chest x-ray images | |
WO2015106374A1 (en) | Multidimensional texture extraction method based on brain nuclear magnetic resonance images | |
US20230154006A1 (en) | Rapid, accurate and machine-agnostic segmentation and quantification method and device for coronavirus ct-based diagnosis | |
Maaliw et al. | A deep learning approach for automatic scoliosis cobb angle identification | |
Liu et al. | A fully automatic segmentation algorithm for CT lung images based on random forest | |
CN111462049A (en) | Automatic lesion area form labeling method in mammary gland ultrasonic radiography video | |
CN111738997A (en) | Method for calculating new coronary pneumonia lesion area ratio based on deep learning | |
CN112071418B (en) | Gastric cancer peritoneal metastasis prediction system and method based on enhanced CT image histology | |
Zhou et al. | Detection and semiquantitative analysis of cardiomegaly, pneumothorax, and pleural effusion on chest radiographs | |
CN110570425A (en) | Lung nodule analysis method and device based on deep reinforcement learning algorithm | |
CN111513743B (en) | Fracture detection method and device | |
CN111402244B (en) | Automatic classification method for standard fetal heart tangent planes | |
WO2023198166A1 (en) | Image detection method, system and device, and storage medium | |
Sun et al. | Liver tumor segmentation and subsequent risk prediction based on Deeplabv3+ | |
Zhou et al. | BSMNet: Boundary-salience multi-branch network for intima-media identification in carotid ultrasound images | |
CN115564756A (en) | Medical image focus positioning display method and system | |
CN115101150A (en) | Specimen collection method for clinical tumor operation in general surgery department | |
Shen et al. | Research on bone age automatic judgment algorithm based on deep learning and hand x-ray image | |
Xie et al. | [Retracted] Analysis of the Diagnosis Model of Peripheral Non‐Small‐Cell Lung Cancer under Computed Tomography Images |
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 |