CN111724357A - Arm bone density measuring method based on digital radiation image and support vector regression - Google Patents

Arm bone density measuring method based on digital radiation image and support vector regression Download PDF

Info

Publication number
CN111724357A
CN111724357A CN202010516559.5A CN202010516559A CN111724357A CN 111724357 A CN111724357 A CN 111724357A CN 202010516559 A CN202010516559 A CN 202010516559A CN 111724357 A CN111724357 A CN 111724357A
Authority
CN
China
Prior art keywords
image
bone density
gray
features
support vector
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.)
Granted
Application number
CN202010516559.5A
Other languages
Chinese (zh)
Other versions
CN111724357B (en
Inventor
高绍兵
周逸菲
谭敏洁
邱健珲
杨睿
彭舰
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.)
Sichuan University
Original Assignee
Sichuan 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 Sichuan University filed Critical Sichuan University
Priority to CN202010516559.5A priority Critical patent/CN111724357B/en
Publication of CN111724357A publication Critical patent/CN111724357A/en
Application granted granted Critical
Publication of CN111724357B publication Critical patent/CN111724357B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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)
  • Radiology & Medical Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Molecular Biology (AREA)
  • Public Health (AREA)
  • Optics & Photonics (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Orthopedic Medicine & Surgery (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses an arm bone mineral density measuring method based on digital radial images and support vector regression, which comprises the following steps: s1, inputting the DR image and segmenting an interested area; s2, respectively extracting the gray features and the texture features of the DR image from the region of interest; s3, establishing a regression model by using the support vector: establishing a regression model by using an SVR algorithm, and performing regression by using the image characteristic values extracted in S2 and the corresponding bone density label data; s4, calculating a bone density predicted value and outputting a predicted result: bone density of DR images of new subjects was predicted using the regression model generated from training in S3. According to the method, the region of interest is segmented and the image characteristics are extracted on the conventional DR image, and the bone density of the DR image is measured by establishing the regression model through the SVR algorithm.

Description

Arm bone density measuring method based on digital radiation image and support vector regression
Technical Field
The invention belongs to the technical field of computer vision and medical image processing, and particularly relates to an arm bone mineral density measuring method based on digital radial images and support vector regression.
Background
Osteoporosis is a common, frequently encountered disease, which seriously threatens the health of the middle-aged and elderly people. There are currently over 2 billion patients worldwide 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 bones. Bone density is a quantitative diagnostic index for bones and is commonly used for diagnosing osteoporosis, predicting fracture risk and evaluating treatment effect.
At present, the double energy X-ray absorption method (DXA) for detecting the bone density is a recognized standard for clinical diagnosis of osteoporosis, and is also the only unified index recommended by the world health organization to be used as the global diagnosis of osteoporosis. DXA is not widely used because of its many disadvantages, including relatively expensive test equipment, high maintenance costs, and the need for specially trained professionals to operate it.
In this context, applying artificial intelligence technology to the medical field makes it possible to develop new bone density measurement techniques.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides an arm bone density measuring method based on digital radiation image and support vector regression, which is used for segmenting a region of interest and extracting image characteristics on the conventional DR image, and measuring the arm bone density by establishing a regression model through an SVR algorithm, is favorable for eliminating errors caused by different bone density detectors, and improves the accuracy of bone density evaluation.
The purpose of the invention is realized by the following technical scheme: the arm bone density measuring method based on digital radiation image and support vector regression includes the following steps:
s1, inputting the DR image and segmenting an interested area;
s2, extracting image features of the divided regions, and respectively extracting gray features and texture features of the DR image from the divided regions of interest;
s3, establishing a regression model by using the support vector: establishing a regression model by using an SVR algorithm, and performing regression by using the image characteristic values extracted in S2 and the corresponding bone density label data;
s4, calculating a bone density predicted value and outputting a predicted result: bone density of DR images of new subjects was predicted using the regression model generated from training in S3.
Further, the step S1 includes the following sub-steps:
s11, segmenting the region of interest from the original DR image;
s12, normalizing the image obtained in the step S11 to normalize the pixel value of the image between 0 and 255.
Further, the specific implementation method of step S2 is as follows:
s21, extracting gray features: respectively extracting 5 gray features of mean value, variance, standard deviation, energy and entropy by calculating a gray histogram of the DR image;
mean value: average value of gray level reflecting a DR image:
Figure BDA0002530333810000021
h (i) represents the gray value of the ith point, and L represents the gray level number of the image;
variance: the method reflects the discrete distribution of the gray scale of a DR image on the value:
Figure BDA0002530333810000022
standard deviation: is the square root of the variance;
energy: reflecting the uniformity degree of the gray distribution, the calculation formula is as follows:
Figure BDA0002530333810000023
entropy: reflecting the uniformity of the distribution of the gray level histogram, and the calculation formula is as follows:
Figure BDA0002530333810000024
s22, extracting texture features: extracting texture features of the image by adopting a gray level co-occurrence matrix method, and respectively extracting 4 texture features of secondary moment, contrast, correlation and homogenization;
second moment: reflecting the smoothness of a DR image, the calculation formula is as follows:
W1＝∑i∑j[m(i，j)]2
m (i, j) represents an element in a gray level co-occurrence matrix defined as a probability from a point of the original image having a gray level i to a point of the original image having a gray level j; i, j ═ 0, 1, 2,. said, L-1;
contrast ratio: reflecting the definition of a DR image, the calculation formula is as follows:
W2＝∑i∑j(i-j)2m(i，j)
correlation coefficient: reflecting the linear correlation degree of the rows and the columns in the gray level co-occurrence matrix, wherein the calculation formula is as follows:
Figure BDA0002530333810000025
wherein the content of the first and second substances,
μx＝∑ii∑jm(i，j)
μy＝∑jj∑im(i，j)
Figure BDA0002530333810000033
Figure BDA0002530333810000034
homogenization: the degree of closeness of the distribution of the elements in the gray level co-occurrence matrix to the diagonal is reflected, and the calculation formula is as follows:
Figure BDA0002530333810000031
s23, data summarization is carried out on the extracted gray-scale features and texture features, data normalization processing is carried out on the feature values, and different features are scaled according to the proportion and are mapped into a specific interval of [ -1, 1 ];
the normalized formula is:
Figure BDA0002530333810000032
where x is the original characteristic value, x*The characteristic value is normalized; mean is the mean of the feature data, max is the maximum of the feature data, and min is the minimum of the feature data.
Further, in step S3, the bone density label data is the real bone density corresponding to the image.
The invention has the beneficial effects that:
1. the method provided by the invention has the advantages that the segmentation of the region of interest and the extraction of the image characteristics are carried out on the conventional DR image, and the bone density of the DR image is measured by establishing the regression model through the SVR algorithm.
2. The bone density measurement result of the method disclosed by the invention is similar to the acquisition result of the existing bone density detector, the measurement error is small, the measurement precision is high, the accuracy of bone density evaluation is favorably improved, and the method can be used for clinical detection of the bone density of the arm of the human body.
3. The method disclosed by the invention has stable bone density measurement results, and compared with the traditional DXA method, the method 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 with the most development prospects for diagnosing osteoporosis.
Drawings
FIG. 1 is a flow chart of the method for measuring bone density of an arm based on digital radial image and support vector regression according to the present invention;
FIG. 2 is a DR image collected in the present embodiment;
fig. 3 is a region-of-interest image.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
As shown in fig. 1, the method for measuring bone density of an arm based on digital radial image and support vector regression of the present invention includes the following steps:
s1, inputting the DR image and segmenting an interested area; the method specifically comprises the following substeps:
s11, segmenting the region of interest from the original DR image;
s12, normalizing the image obtained in the step S11 to normalize the pixel value of the image between 0 and 255.
DR image data were collected on the forearms of 173 male and female subjects using a conventional bone density monitor, 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 to effectively segment the bone region of interest (ulna region, as shown in fig. 3).
S2, extracting image features of the divided regions, and respectively extracting gray features and texture features of the DR image from the divided regions of interest; the specific implementation method comprises the following steps:
s21, extracting gray features: respectively extracting 5 gray features of mean value, variance, standard deviation, energy and entropy by calculating a gray histogram of the DR image;
mean value: average value of gray level reflecting a DR image:
Figure BDA0002530333810000041
h (i) represents the gray value of the ith point, and L represents the gray level number of the image;
variance: the method reflects the discrete distribution of the gray scale of a DR image on the value:
Figure BDA0002530333810000042
standard deviation: is the square root of the variance;
energy: reflecting the uniformity degree of the gray distribution, the calculation formula is as follows:
Figure BDA0002530333810000043
entropy: reflecting the uniformity of the distribution of the gray level histogram, and the calculation formula is as follows:
Figure BDA0002530333810000044
and 5 gray features of mean value, variance, standard deviation, energy and entropy are extracted through corresponding gray histograms of the images, and are 708619223, 5.03144983470948e +23, 709327134311.770, 286421983777.000 and 62393739.6779687 respectively.
S22, extracting texture features: extracting texture features of the image by adopting a gray level co-occurrence matrix method, and respectively extracting 4 texture features of secondary moment, contrast, correlation and homogenization;
second moment: reflecting the smoothness of a DR image, the calculation formula is as follows:
W1＝∑i∑j[m(i，j)]2
m (i, j) represents an element in a gray level co-occurrence matrix defined as a probability from a point of the original image having a gray level i to a point of the original image having a gray level j; i, j ═ 0, 1, 2,. said, L-1;
contrast ratio: reflecting the definition of a DR image, the calculation formula is as follows:
W2＝∑i∑j(i-j)2m(i，j)
correlation coefficient: reflecting the linear correlation degree of the rows and the columns in the gray level co-occurrence matrix, wherein the calculation formula is as follows:
Figure BDA0002530333810000051
wherein the content of the first and second substances,
μx＝∑ii∑jm(i，j)
μy＝∑jj∑im(i，j)
Figure BDA0002530333810000054
Figure BDA0002530333810000055
homogenization: the degree of closeness of the distribution of the elements in the gray level co-occurrence matrix to the diagonal is reflected, and the calculation formula is as follows:
Figure BDA0002530333810000052
the results of the 4 characteristics of second moment, contrast, correlation and homogenization extracted in this example are 0.350538853001145, 0.0203936063936064, 0.998352776124655 and 0.989803196803197, respectively.
S23, data summarization is carried out on the extracted gray-scale features and texture features, data normalization processing is carried out on the feature values, and different features are scaled according to the proportion and are mapped into a specific interval of [ -1, 1 ];
the normalized formula is:
Figure BDA0002530333810000053
where x is the original characteristic value, x*The characteristic value is normalized; mean is the mean of the characteristic dataMax is the maximum value of the characteristic data, and min is the minimum value of the characteristic data. The results of the normalization processing in this example are-0.0676965, -0.151447, -0.0676965, 0.248400, -0.965191, -0.196041, -0.115126, 0.191109, 0.115126.
S3, establishing a regression model by using the support vector: and establishing a regression model by using an SVR algorithm, and performing regression by using the image characteristic values (-0.0676965, -0.151447, -0.0676965, 0.248400, -0.965191, -0.196041, -0.115126, 0.191109 and 0.115126) extracted in S2 and the bone density label (the true bone density is 0.788) of the image to establish the regression model. The idea of the SVR algorithm is as follows:
given a training sample, D { (x)1，y1)，(x2，y2)，......，(xm，ym)}，yi∈ R, training a regression model so that f (x) is as close as possible to y, and w and b are the model parameters to be determined the model parameters of the SVR are adjusted by a grid search method to determine an optimal model for measuring bone density.
S4, calculating a bone density predicted value and outputting a predicted result: the regression model generated by training in S3 was used to predict bone density of DR images of new subjects, which was predicted to be 0.777952.
It will be appreciated by those of ordinary skill in the art that the embodiments described herein are intended to assist the reader in understanding the principles of the invention and are to be construed as being without limitation to such specifically recited embodiments and examples. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.

Claims (4)

1. The method for measuring the bone density of the arm based on the digital radiological image and the support vector regression is characterized by comprising the following steps of:
s1, inputting the DR image and segmenting an interested area;
s2, extracting image features of the divided regions, and respectively extracting gray features and texture features of the DR image from the divided regions of interest;
s3, establishing a regression model by using the support vector: establishing a regression model by using an SVR algorithm, and performing regression by using the image characteristic values extracted in S2 and the corresponding bone density label data;
s4, calculating a bone density predicted value and outputting a predicted result: bone density of DR images of new subjects was predicted using the regression model generated from training in S3.
2. The method for measuring bone density of an arm based on digital radial image and support vector regression as claimed in claim 1, wherein said step S1 includes the following sub-steps:
s11, segmenting the region of interest from the original DR image;
s12, normalizing the image obtained in the step S11 to normalize the pixel value of the image between 0 and 255.
3. The method for measuring arm bone density based on digital radial image and support vector regression as claimed in claim 1, wherein said step S2 is implemented by:
s21, extracting gray features: respectively extracting 5 gray features of mean value, variance, standard deviation, energy and entropy by calculating a gray histogram of the DR image;
mean value: average value of gray level reflecting a DR image:
Figure FDA0002530333800000011
h (i) represents the gray value of the ith point, and L represents the gray level number of the image;
variance: the method reflects the discrete distribution of the gray scale of a DR image on the value:
Figure FDA0002530333800000012
standard deviation: is the square root of the variance;
energy: reflecting the uniformity degree of the gray distribution, the calculation formula is as follows:
Figure FDA0002530333800000013
entropy: reflecting the uniformity of the distribution of the gray level histogram, and the calculation formula is as follows:
Figure FDA0002530333800000014
s22, extracting texture features: extracting texture features of the image by adopting a gray level co-occurrence matrix method, and respectively extracting 4 texture features of secondary moment, contrast, correlation and homogenization;
second moment: reflecting the smoothness of a DR image, the calculation formula is as follows:
W1＝∑i∑j[m(i，j)]2
m (i, j) represents an element in the gray level co-occurrence matrix, i, j is 0, 1, 2, …, L-1;
contrast ratio: reflecting the definition of a DR image, the calculation formula is as follows:
W2＝∑i∑j(i-j)2m(i，j)
correlation coefficient: reflecting the linear correlation degree of the rows and the columns in the gray level co-occurrence matrix, wherein the calculation formula is as follows:
Figure FDA0002530333800000021
wherein the content of the first and second substances,
μx＝∑ii∑jm(i，j)
μy＝∑jj∑im(i，j)
Figure FDA0002530333800000022
Figure FDA0002530333800000023
homogenization: the degree of closeness of the distribution of the elements in the gray level co-occurrence matrix to the diagonal is reflected, and the calculation formula is as follows:
Figure FDA0002530333800000024
s23, data summarization is carried out on the extracted gray-scale features and texture features, data normalization processing is carried out on the feature values, and different features are scaled according to the proportion and are mapped into a specific interval of [ -1, 1 ];
the normalized formula is:
Figure FDA0002530333800000025
where x is the original characteristic value, x*The characteristic value is normalized; mean is the mean of the feature data, max is the maximum of the feature data, and min is the minimum of the feature data.
4. The method of claim 1, wherein the bone density label data in step S3 is the corresponding actual bone density of the image.
CN202010516559.5A 2020-06-09 2020-06-09 Arm bone density measurement method based on digital radiological image and support vector regression Active CN111724357B (en)

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 true CN111724357A (en) 2020-09-29
CN111724357B 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)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116458909A (en) * 2023-04-10 2023-07-21 清华大学 Method and device for measuring three-dimensional bone density distribution by using cone beam DR equipment
CN116486021A (en) * 2023-06-25 2023-07-25 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
CN117876372A (en) * 2024-03-12 2024-04-12 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
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 (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020025063A1 (en) * 1998-08-28 2002-02-28 Chunsheng Jiang Method and system for the computerized analysis of bone mass and structure
US20050010106A1 (en) * 2003-03-25 2005-01-13 Imaging Therapeutics, Inc. Methods for the compensation of imaging technique in the processing of radiographic images
CN1735373A (en) * 2003-01-07 2006-02-15 成像治疗仪股份有限公司 Methods of predicting musculoskeletal disease
US20130342577A1 (en) * 2012-06-20 2013-12-26 Carestream Health, Inc. Image synthesis for diagnostic review
US20160262686A1 (en) * 2013-11-25 2016-09-15 Media Co., Ltd. Osteoporosis diagnostic support apparatus
US20180020999A1 (en) * 2015-02-13 2018-01-25 Shimadzu Corporation Bone analyzing device
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

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020025063A1 (en) * 1998-08-28 2002-02-28 Chunsheng Jiang Method and system for the computerized analysis of bone mass and structure
CN1735373A (en) * 2003-01-07 2006-02-15 成像治疗仪股份有限公司 Methods of predicting musculoskeletal disease
US20050010106A1 (en) * 2003-03-25 2005-01-13 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
US20160262686A1 (en) * 2013-11-25 2016-09-15 Media Co., Ltd. Osteoporosis diagnostic support apparatus
US20180020999A1 (en) * 2015-02-13 2018-01-25 Shimadzu Corporation Bone analyzing device
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)

* Cited by examiner, † Cited by third party
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" *
孙涛: "基于DR骨密度分析系统的研究" *
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" *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116458909A (en) * 2023-04-10 2023-07-21 清华大学 Method and device for measuring three-dimensional bone density distribution by using cone beam DR equipment
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
CN116486021A (en) * 2023-06-25 2023-07-25 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
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
CN117876372A (en) * 2024-03-12 2024-04-12 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
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

Also Published As

Publication number Publication date
CN111724357B (en) 2023-05-16

Similar Documents

Publication Publication Date Title
CN107103187B (en) Lung nodule detection grading and management method and system based on deep learning
Saikumar et al. A novel implementation heart diagnosis system based on random forest machine learning technique.
Lu et al. Automated fetal head detection and measurement in ultrasound images by iterative randomized Hough transform
US9262822B2 (en) Malignant mass detection and classification in radiographic images
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
CN108805858A (en) Hepatopathy CT image computers assistant diagnosis system based on data mining and method
US20230154006A1 (en) Rapid, accurate and machine-agnostic segmentation and quantification method and device for coronavirus ct-based diagnosis
CN101103924A (en) Galactophore cancer computer auxiliary diagnosis method based on galactophore X-ray radiography and system thereof
CN111260671A (en) Lung leaf segmentation method and system for CT image
CN111724357B (en) Arm bone density measurement method based on digital radiological image and support vector regression
Kong et al. Automated maxillofacial segmentation in panoramic dental x-ray images using an efficient encoder-decoder network
CN113222951B (en) Osteoporosis artificial intelligent diagnosis device for recognizing hip joint X-ray
CN111738997A (en) Method for calculating new coronary pneumonia lesion area ratio based on deep learning
EP3971830B1 (en) Pneumonia sign segmentation method and apparatus, medium and electronic device
CN112071418B (en) Gastric cancer peritoneal metastasis prediction system and method based on enhanced CT image histology
Liu et al. A clinical decision support system for predicting cirrhosis stages via high frequency ultrasound images
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+
Chowdhary et al. An improved tumour identification with gabor wavelet segmentation
WO2022033598A1 (en) Breast x-ray radiography acquisition method and apparatus, and computer device and storage medium
CN115101150A (en) Specimen collection method for clinical tumor operation in general surgery department

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