CN115131300B - Intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning - Google Patents
Intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning Download PDFInfo
- Publication number
- CN115131300B CN115131300B CN202210680643.XA CN202210680643A CN115131300B CN 115131300 B CN115131300 B CN 115131300B CN 202210680643 A CN202210680643 A CN 202210680643A CN 115131300 B CN115131300 B CN 115131300B
- Authority
- CN
- China
- Prior art keywords
- cartilage
- target
- image data
- dimensional
- osteoarthritis
- 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
- 201000008482 osteoarthritis Diseases 0.000 title claims abstract description 80
- 238000003745 diagnosis Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000013135 deep learning Methods 0.000 title claims abstract description 35
- 210000000845 cartilage Anatomy 0.000 claims abstract description 253
- 238000003709 image segmentation Methods 0.000 claims abstract description 73
- 230000006378 damage Effects 0.000 claims abstract description 47
- 238000005481 NMR spectroscopy Methods 0.000 claims abstract description 46
- 208000003947 Knee Osteoarthritis Diseases 0.000 claims abstract description 43
- 230000011218 segmentation Effects 0.000 claims abstract description 38
- 210000000629 knee joint Anatomy 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 230000007547 defect Effects 0.000 claims description 64
- 206010007710 Cartilage injury Diseases 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 13
- 210000000988 bone and bone Anatomy 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004451 qualitative analysis Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 8
- 238000002595 magnetic resonance imaging Methods 0.000 description 12
- 238000004445 quantitative analysis Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000002950 deficient Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000002591 computed tomography Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 210000001188 articular cartilage Anatomy 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007850 degeneration Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 210000005065 subchondral bone plate Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 238000012800 visualization Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning. The method comprises the following steps: acquiring magnetic resonance image data of the knee joint; inputting the nuclear magnetic resonance image data into an image segmentation network model for cartilage region segmentation to obtain an output two-dimensional medical image of a cartilage body position region; the image segmentation network model is obtained by training a sample by taking the sample skeleton image data and a cartilage region segmentation result corresponding to the sample skeleton image data as the sample; obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image and the nuclear magnetic resonance image data of the cartilage body position area; and determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine the damage degree of the target cartilage. The method provided by the invention can be used for conveniently and rapidly detecting the knee osteoarthritis, reduces the missed diagnosis rate and the misdiagnosis rate, objectively diagnoses and evaluates the knee osteoarthritis, and improves the diagnosis effect and the detection precision of the knee osteoarthritis.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning. In addition, an electronic device and a processor-readable storage medium are also related.
Background
Knee osteoarthritis is the degeneration of articular cartilage on the joint surface caused by local damage and inflammation and chronic strain of the knee joint, and the reactive bone damage of subchondral bone plates, which causes a series of symptoms and physical signs on the knee joint. Because early pathological changes of knee osteoarthritis are not obvious, the traditional CT (Computed Tomography), namely electronic Computed Tomography, has poor diagnosis effect and high missed diagnosis and misdiagnosis rate. With the rapid development of intelligent equipment, MRI (Magnetic Resonance Imaging) dynamic scanning can acquire images through three-dimensional data acquisition, multi-sequence and multi-plane scanning, the image resolution is high, and the images can be compared with good tissues better. However, when the osteoarthritis is subjectively diagnosed by directly reading an MRI image (magnetic resonance image), there are differences between different doctors, which easily cause misdiagnosis and missed diagnosis, and thus the diagnosis effect and detection accuracy are not stable. Therefore, how to design an evaluation scheme with better stability and accuracy for the damage degree of the knee joint cartilage is a technical problem to be solved urgently.
Disclosure of Invention
Therefore, the invention provides an intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning, and aims to overcome the defects that in the prior art, the ecological service value accounting scheme of an ecological system is high in limitation, and the diagnosis effect and detection accuracy of knee osteoarthritis are poor.
The invention provides an intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning, which comprises the following steps:
acquiring magnetic resonance image data of the knee joint;
inputting the nuclear magnetic resonance image data into a preset image segmentation network model for cartilage region segmentation, and obtaining a two-dimensional medical image of a cartilage body position region output by the image segmentation network model; the image segmentation network model is obtained by training samples, namely sample skeleton image data and cartilage region segmentation results corresponding to the sample skeleton image data;
constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data;
and determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine the damage degree of the target cartilage.
Further, analyzing the target cartilage to determine the damage degree of the target cartilage comprises: and qualitatively analyzing the target cartilage, judging whether the target cartilage is knee osteoarthritis or not, and if so, quantitatively analyzing the target cartilage to determine the damage degree of the target cartilage.
Further, performing qualitative analysis on the target cartilage to determine whether the target cartilage is knee osteoarthritis, including:
performing defect detection on the target cartilage by using the image segmentation network model, judging whether the target cartilage has a defect area, and if so, judging that the target cartilage has knee osteoarthritis; if not, judging that the target cartilage does not have knee osteoarthritis.
Further, performing quantitative analysis on the target cartilage to determine the damage degree of the target cartilage, including:
identifying the outline of the defect area of the target cartilage;
determining the number of pixels of the defect area in the contour;
and grading the cartilage damage degree according to the ratio of the number of the pixels of the defect region to the number of the pixels of the total region of the target cartilage, and determining the first damage degree of the target cartilage.
Further, performing quantitative analysis on the target cartilage to determine the damage degree of the target cartilage, including:
identifying a contour of a defect area in which the target cartilage is present;
determining the cartilage thickness of the defect region, and identifying the maximum thickness of the target cartilage;
and classifying the cartilage defect degree according to the thickness ratio between the cartilage thickness of the defect area and the maximum thickness of the target cartilage, and determining a second damage degree of the target cartilage.
Further, the image segmentation network model includes: the system comprises a medical image segmentation module based on an attention mechanism and a Point Rend network module;
the attention mechanism-based medical image segmentation module is used for positioning a target position area in a nuclear magnetic resonance image and segmenting the nuclear magnetic resonance image based on the boundary of the target position area;
the Point Rend network module is used for reclassifying the boundary after the segmentation processing to obtain a boundary segmentation result meeting a preset condition; and outputting a two-dimensional medical image of the cartilage body position area based on the boundary segmentation result.
The invention also provides an intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning, which comprises:
the image data acquisition unit is used for acquiring the nuclear magnetic resonance image data of the knee joint;
the image segmentation processing unit is used for inputting the nuclear magnetic resonance image data into a preset image segmentation network model for cartilage region segmentation to obtain a two-dimensional medical image of a cartilage body position region output by the image segmentation network model; the image segmentation network model is obtained by training samples, namely sample skeleton image data and cartilage region segmentation results corresponding to the sample skeleton image data;
the three-dimensional reconstruction unit is used for constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data;
and the cartilage damage degree determining unit is used for determining the target cartilage in the three-dimensional medical image and analyzing the target cartilage to determine the damage degree of the target cartilage.
Further, the cartilage damage degree determination unit is specifically configured to: and qualitatively analyzing the target cartilage, judging whether the target cartilage is knee osteoarthritis or not, and if so, quantitatively analyzing the target cartilage and determining the damage degree of the target cartilage.
Further, performing qualitative analysis on the target cartilage to determine whether the target cartilage is knee osteoarthritis, specifically including:
performing defect detection on the target cartilage by using the image segmentation network model, judging whether the target cartilage has a defect area, and if so, judging that the target cartilage has knee osteoarthritis; if not, judging that the target cartilage does not have knee osteoarthritis.
Further, performing quantitative analysis on the target cartilage to determine the damage degree of the target cartilage, specifically comprising:
identifying the outline of the defect area of the target cartilage;
determining the number of pixels of the defect area in the contour;
and grading the cartilage damage degree according to the ratio of the number of the pixels of the defect region to the number of the pixels of the total region of the target cartilage, and determining the first damage degree of the target cartilage.
Further, the intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning further comprises: a thickness determination unit; the quantitative analysis is carried out on the target cartilage, and the damage degree of the target cartilage is determined, and the method specifically comprises the following steps:
identifying a contour of a defect area in which the target cartilage is present;
determining the cartilage thickness of the defect region, and identifying the maximum thickness of the target cartilage;
and classifying the cartilage defect degree according to the thickness ratio between the cartilage thickness of the defect area and the maximum thickness of the target cartilage, and determining a second damage degree of the target cartilage.
Further, the image segmentation network model includes: the system comprises a medical image segmentation module based on an attention mechanism and a Point Rend network module;
the attention mechanism-based medical image segmentation module is used for positioning a target position area in a nuclear magnetic resonance image and segmenting the nuclear magnetic resonance image based on the boundary of the target position area;
the Point Rend network module is used for reclassifying the boundary after the segmentation processing to obtain a boundary segmentation result meeting a preset condition; and outputting a two-dimensional medical image of the cartilage body position area based on the boundary segmentation result.
The present invention also provides an electronic device, comprising: the device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning.
The invention also provides a processor-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning according to any one of the above items.
The invention provides an intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning, which comprises the steps of inputting acquired nuclear magnetic resonance image data of a knee joint into a preset image segmentation network model to segment a cartilage region, and acquiring a two-dimensional medical image of a cartilage body position region; then, constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data; and determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine the damage degree of the target cartilage. The knee osteoarthritis diagnosis and evaluation device can conveniently and rapidly detect knee osteoarthritis, reduces the missed diagnosis rate and the misdiagnosis rate, objectively diagnoses and evaluates the knee osteoarthritis, and improves the diagnosis effect and the detection precision of the knee osteoarthritis.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a schematic flow chart of an intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning, provided by an embodiment of the invention;
fig. 2 is a schematic structural diagram of a medical image segmentation module of an image segmentation network model in an intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a Point Red network module of an image segmentation network model in the deep learning-based intelligent three-dimensional osteoarthritis diagnosis method according to the embodiment of the present invention
FIG. 4 is a flow chart of a method for constructing a three-dimensional image according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning according to an embodiment of the present invention;
fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The following describes an embodiment of the intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning according to the present invention in detail. As shown in fig. 1, which is a schematic flow chart of an intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning according to an embodiment of the present invention, the specific implementation process includes the following steps:
step 101: magnetic resonance image data of the knee joint is acquired.
Magnetic resonance imaging is a tomographic imaging technique that uses the phenomenon of magnetic resonance to reconstruct body information from corresponding electromagnetic signals obtained from the body. In the embodiment of the invention, firstly, the imaging data of different fault of the knee joint is established by a magnetic resonance imaging instrument to obtain the corresponding nuclear magnetic resonance image data of the knee joint, so that the knee joint contour can be conveniently obtained by an artificial intelligence algorithm in the following process, the three-dimensional reconstruction of the knee joint is completed, the cartilage is automatically identified, and the diagnosis of knee osteoarthritis and the judgment of the cartilage injury degree are realized by performing qualitative and quantitative analysis on the cartilage.
Step 102: inputting the nuclear magnetic resonance image data into a preset image segmentation network model for cartilage region segmentation, and obtaining a two-dimensional medical image of a cartilage body position region output by the image segmentation network model; the image segmentation network model is a neural network model obtained by training samples of sample bone image data and cartilage region segmentation results corresponding to the sample bone image data.
In this step, as shown in fig. 2 and 3, the image segmentation network model includes: an Attention-based medical image segmentation module (Attention-UNet) and a Point Rend network module (Point Rend network structure). The medical image segmentation network module based on the Attention mechanism comprises a Channel Attention module (Channel Attention module) and a Spatial Attention module (Spatial Attention module), namely an Attention mechanism comprises a Channel Attention and a Spatial Attention, and the Attention mechanism is realized by using a Unet with a soft Attention and supervising a feature of a previous stage through a feature of a next stage. The attention mechanism-based medical image segmentation module is used for positioning a target position area in a nuclear magnetic resonance image and segmenting the nuclear magnetic resonance image based on the boundary of the target position area; the Point Rend network module is used for reclassifying the boundary after the segmentation processing to obtain a boundary segmentation result meeting preset conditions, so that a better boundary segmentation effect is obtained; and outputting a two-dimensional medical image of the cartilage body position area based on the boundary segmentation result. The Attention UNet consists of two parts, namely feature extraction and feature restoration, wherein the feature extraction part consists of a basic convolution module and pooling operation, and the convolution module comprises convolution, batch normalization, activation and other operations; the characteristic recovery part is mainly completed by a convolution module and an up-sampling operation, and the up-sampling method is bilinear interpolationWhat is meant is the reduction of the size of the signature. The Point Red network module mainly comprises a volume layer and a full-connection layer, is a Point-based rendering neural network module and can perform Point-based segmentation prediction at a self-adaptively selected position based on an iterative subdivision algorithm. It should be noted that, as shown in fig. 2 and 3, in the embodiment of the present invention, the medical image segmentation module and the Point Rend network module included in the image segmentation network model may be composed of a plurality of initial network layers. An MRI image dataset is formed by obtaining sample bone image data, and the sample bone image data and a cartilage region segmentation result corresponding to the sample bone image data are used as training samples to train an initial image segmentation network model, so that the trained image segmentation network model capable of rapidly and accurately identifying and segmenting the cartilage region in the nuclear magnetic resonance image is obtained. In the model training process, an MRI sequence image (namely sample bone image data) is input, an MRI image data set needs to be obtained firstly, the MRI sequence image is converted into a jpg format, and areas of different types of bones and cartilage damage areas are marked by manually marking cartilage actual areas and cartilage theoretical areas in the MRI sequence image as standards. The method comprises the steps of dividing the MRI image data set into a training set and a testing set, storing corresponding images before and after annotation, establishing an image segmentation network model, training the image segmentation network model by using the training set, testing by using the testing set, and segmenting the nuclear magnetic resonance image of the knee joint by using the trained image segmentation network model. The initial learning rate of the model may be 1e -5 The batch size may be 8 and the optimizer Adam; the number of model iterations may be 8000, and the Loss function may be implemented by Dice Loss + Focal Loss, which is not described in detail herein.
Step 103: and constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data.
In a specific implementation process, the two-dimensional medical image based on the cartilage body position region and the nuclear magnetic resonance image data can be input into a preset Visualization tool function library (VTK), and a VTK reconstruction technology is used to construct a three-dimensional image, so as to obtain a corresponding three-dimensional medical image.
Step 104: and determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine the damage degree of the target cartilage.
In the embodiment of the invention, firstly, qualitative analysis is carried out on the target cartilage, whether the target cartilage is knee osteoarthritis or not is judged, if yes, quantitative analysis is further carried out on the target cartilage, and the damage degree of the target cartilage is determined. Performing qualitative analysis on the target cartilage, and judging whether the target cartilage is knee osteoarthritis or not, wherein the corresponding implementation process comprises the following steps: performing defect detection on the identified target cartilage by using the image segmentation network model, judging whether the target cartilage has a defect area, and if so, judging that the target cartilage has knee osteoarthritis; if not, judging that the target cartilage does not have knee osteoarthritis.
Before training the image segmentation network model by using the sample bone data and the cartilage region segmentation result corresponding to the sample bone data as samples, the sample image may be labeled to determine whether knee osteoarthritis exists in the target cartilage according to the result output by the image segmentation model. For example, the sample image of normal target cartilage is labeled as 1, and the sample image of defective target cartilage is labeled as 0. After the constructed three-dimensional medical image is input to the image segmentation network model, the image segmentation network model can output a result. If the output result of the image segmentation network model is 0, judging that knee osteoarthritis exists in the target cartilage; and if the output result of the image segmentation network model is 1, judging that the target cartilage does not have knee osteoarthritis. Of course, the sample image of the normal target cartilage may be labeled as 0, and the sample image of the defective target cartilage may be labeled as 1, which is not limited herein.
In addition, the target cartilage is subjected to quantitative analysis, the damage degree of the target cartilage is determined, and the corresponding specific implementation process comprises the following steps: identifying a contour of a defect area in which the target cartilage is present; determining the number of pixels of the defective area according to the outline of the defective area and a preset pixel statistical method; and grading the cartilage damage degree according to the ratio of the number of the pixels of the defect region to the number of the pixels of the total region of the target cartilage, and determining the first damage degree of the target cartilage. Wherein the target total cartilage area may include: a femoral distal medial condyle area, a femoral lateral condyle area, a patellar cartilage area, a tibial medial plateau area, a tibial lateral plateau area, and the like. In one possible implementation manner, if the ratio of the number of pixels in the defect region to the number of pixels in the target total cartilage region is less than or equal to 0.5, determining that the first damage degree is a severe defect; and if the ratio of the number of pixels of the defect region to the number of pixels of the target total cartilage region is greater than 0.5 and less than 0.9, determining the first damage degree as a general defect.
In addition, in order to obtain a more accurate detection result, the defect contour of the cartilage in each region can be identified, the cartilage thickness of the defect region is calculated, and the maximum thickness of the target cartilage is identified; classifying cartilage defect degrees according to the thickness ratio between the cartilage thickness of the defect area and the maximum thickness of the target cartilage, and determining a second damage degree of the target cartilage; in one possible implementation, if the thickness ratio between the cartilage thickness of the defect region and the maximum thickness of the target cartilage is less than or equal to 0.5, determining the second degree of damage as a severe defect; determining the second degree of damage as a general defect if the ratio of the thickness of the cartilage in the defect region to the maximum thickness of the target cartilage is greater than 0.5 and less than 0.9.
The thickness ratio of the cartilage thickness of the defect area to the maximum cartilage thickness is calculated, and the comprehensive classification of cartilage defects can be realized by using the obtained thickness ratio and defect area ratio. The MRI image is divided and three-dimensionally reconstructed to identify cartilage, osteoarthritis is diagnosed according to whether cartilage damage exists, damage area and thickness of the identified cartilage are calculated, cartilage damage degree is quantified according to the damage area and thickness of the cartilage, and cartilage defect degree can be objectively evaluated.
As shown in fig. 4, a flowchart of a method for constructing a three-dimensional image according to an embodiment of the present invention includes the following steps:
400: and starting.
401: inputting a nuclear magnetic resonance image (namely a standard Dicom file) of the knee joint;
402: segmenting cartilage regions of the nuclear magnetic resonance image by using an image segmentation network model;
403: and combining the divided Mask file with the meta information of the original Dicom file, and performing three-dimensional reconstruction by using a VTK reconstruction technology to obtain a corresponding three-dimensional medical image.
404: and (6) ending.
According to the intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning, provided by the embodiment of the invention, the acquired nuclear magnetic resonance image data of the knee joint is input into a preset image segmentation network model to segment the cartilage region, so that a two-dimensional medical image of the cartilage body position region is obtained; then, constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data; and determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine the damage degree of the target cartilage. The knee osteoarthritis diagnosis and evaluation device can conveniently and rapidly detect knee osteoarthritis, reduces the missed diagnosis rate and the misdiagnosis rate, objectively diagnoses and evaluates the knee osteoarthritis, and improves the diagnosis effect and the detection precision of the knee osteoarthritis.
Corresponding to the provided intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning, the invention also provides an intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning. Since the embodiment of the device is similar to the method embodiment, the description is simple, and please refer to the description in the method embodiment section, and the embodiment of the intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning described below is only schematic. Fig. 5 is a schematic structural diagram of an intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning according to an embodiment of the present invention.
The invention relates to an intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning, which specifically comprises:
an image data acquisition unit 501 for acquiring nuclear magnetic resonance image data of a knee joint;
an image segmentation processing unit 502, configured to input the nuclear magnetic resonance image data into a preset image segmentation network model for cartilage region segmentation, so as to obtain a two-dimensional medical image of a cartilage body position region output by the image segmentation network model; the image segmentation network model is obtained by training samples, namely sample skeleton image data and cartilage region segmentation results corresponding to the sample skeleton image data;
a three-dimensional reconstruction unit 503, configured to construct and obtain a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position region and the nuclear magnetic resonance image data;
a cartilage damage degree determination unit 504, configured to determine a target cartilage in the three-dimensional medical image, and analyze the target cartilage to determine a damage degree of the target cartilage.
Further, the cartilage damage degree determination unit is specifically configured to: and qualitatively analyzing the target cartilage, judging whether the target cartilage is knee osteoarthritis or not, and if so, quantitatively analyzing the target cartilage to determine the damage degree of the target cartilage.
Further, performing qualitative analysis on the target cartilage to determine whether the target cartilage is knee osteoarthritis, specifically including:
performing defect detection on the target cartilage by using the image segmentation network model, judging whether the target cartilage has a defect area, and if so, judging that the target cartilage has knee osteoarthritis; if not, judging that the target cartilage does not have knee osteoarthritis.
Further, performing quantitative analysis on the target cartilage to determine the damage degree of the target cartilage specifically includes:
identifying the outline of the defect area of the target cartilage;
determining the number of pixels of the defect area in the contour;
and grading the cartilage damage degree according to the ratio of the number of the pixels of the defect region to the number of the pixels of the total region of the target cartilage, and determining the first damage degree of the target cartilage.
Further, the intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning further comprises: a thickness determination unit; carrying out quantitative analysis on the target cartilage to determine the damage degree of the target cartilage, and specifically comprising the following steps:
identifying the outline of the defect area of the target cartilage;
determining the cartilage thickness of the defect region, and identifying the maximum thickness of the target cartilage;
and classifying the cartilage defect degree according to the thickness ratio between the cartilage thickness of the defect area and the maximum thickness of the target cartilage, and determining a second damage degree of the target cartilage.
Further, the image segmentation network model includes: the system comprises a medical image segmentation module based on an attention mechanism and a Point Rend network module;
the attention mechanism-based medical image segmentation module is used for positioning a target position area in a nuclear magnetic resonance image and segmenting the nuclear magnetic resonance image based on the boundary of the target position area;
the Point Rend network module is used for reclassifying the boundary after the segmentation processing to obtain a boundary segmentation result meeting a preset condition; and outputting a two-dimensional medical image of the cartilage body position area based on the boundary segmentation result.
According to the intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning, the two-dimensional medical image of the cartilage body position region is obtained by inputting the acquired nuclear magnetic resonance image data of the knee joint into the preset image segmentation network model to segment the cartilage region; then, constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data; and determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine the damage degree of the target cartilage. The knee osteoarthritis diagnosis and evaluation device can conveniently and rapidly detect knee osteoarthritis, reduces the missed diagnosis rate and the misdiagnosis rate, objectively diagnoses and evaluates the knee osteoarthritis, and improves the diagnosis effect and the detection precision of the knee osteoarthritis.
Corresponding to the provided intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning, the invention also provides electronic equipment. Since the embodiment of the electronic device is similar to the above method embodiment, the description is simple, and please refer to the description of the above method embodiment, and the electronic device described below is only schematic. Fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention. The electronic device may include: a processor (processor) 601, a memory (memory) 602 and a communication bus 603, wherein the processor 601 and the memory 602 communicate with each other through the communication bus 603 and communicate with the outside through the communication interface 604. Processor 601 may invoke logic instructions in memory 602 to perform a deep learning based intelligent three-dimensional diagnostic method for osteoarthritis, the method comprising: acquiring nuclear magnetic resonance image data of the knee joint; inputting the nuclear magnetic resonance image data into a preset image segmentation network model for cartilage region segmentation, and obtaining a two-dimensional medical image of a cartilage body position region output by the image segmentation network model; the image segmentation network model is obtained by training samples, namely sample skeleton image data and cartilage region segmentation results corresponding to the sample skeleton image data; constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data; and determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine the damage degree of the target cartilage.
Furthermore, the logic instructions in the memory 602 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a Memory chip, a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In another aspect, the present invention also provides a computer program product, which includes a computer program stored on a processor-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer can execute the deep learning-based intelligent three-dimensional osteoarthritis diagnosis method provided by the above-mentioned method embodiments. The method comprises the following steps: acquiring magnetic resonance image data of the knee joint; inputting the nuclear magnetic resonance image data into a preset image segmentation network model for cartilage region segmentation, and obtaining a two-dimensional medical image of a cartilage body position region output by the image segmentation network model; the image segmentation network model is obtained by training samples, namely sample skeleton image data and cartilage region segmentation results corresponding to the sample skeleton image data; constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data; determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine a damage degree of the target cartilage.
In still another aspect, the present invention further provides a processor-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the intelligent deep learning-based osteoarthritis three-dimensional diagnosis method provided in the foregoing embodiments when executed by a processor. The method comprises the following steps: acquiring magnetic resonance image data of the knee joint; inputting the nuclear magnetic resonance image data into a preset image segmentation network model for cartilage region segmentation, and obtaining a two-dimensional medical image of a cartilage body position region output by the image segmentation network model; the image segmentation network model is obtained by training samples, namely sample skeleton image data and cartilage region segmentation results corresponding to the sample skeleton image data; constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data; and determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine the damage degree of the target cartilage.
The processor-readable storage medium can be any available medium or data storage device that can be accessed by a processor, including, but not limited to, magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid State Disks (SSDs)), etc.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. An intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning is characterized by comprising the following steps:
acquiring magnetic resonance image data of the knee joint;
inputting the nuclear magnetic resonance image data into a preset image segmentation network model for cartilage region segmentation, and obtaining a two-dimensional medical image of a cartilage body position region output by the image segmentation network model; the image segmentation network model is obtained by training samples, namely sample skeleton image data and cartilage region segmentation results corresponding to the sample skeleton image data;
constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data;
determining a target cartilage in the three-dimensional medical image, and analyzing the target cartilage to determine the damage degree of the target cartilage;
the analyzing the target cartilage to determine the damage degree of the target cartilage comprises: performing qualitative analysis on the target cartilage, judging whether the target cartilage is knee osteoarthritis or not, if so, identifying the outline of the target cartilage with a defect region, determining the number of pixels of the defect region in the outline, classifying cartilage damage degrees according to the ratio of the number of pixels of the defect region to the number of pixels of a total region of the target cartilage, and determining a first damage degree of the target cartilage; alternatively, the first and second electrodes may be,
identifying the contour of a defect area of the target cartilage, determining the cartilage thickness of the defect area, identifying the maximum thickness of the target cartilage, grading the cartilage defect degree according to the thickness ratio between the cartilage thickness of the defect area and the maximum thickness of the target cartilage, and determining the second damage degree of the target cartilage.
2. The intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning of claim 1, wherein the qualitative analysis of the target cartilage to determine whether the target cartilage is knee osteoarthritis comprises:
performing defect detection on the target cartilage by using the image segmentation network model, judging whether the target cartilage has a defect area, and if so, judging that the target cartilage has knee osteoarthritis; if not, judging that the target cartilage does not have knee osteoarthritis.
3. The intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning of claim 1, wherein the image segmentation network model comprises: the system comprises a medical image segmentation module based on an attention mechanism and a Point Rend network module;
the attention mechanism-based medical image segmentation module is used for positioning a target position area in a nuclear magnetic resonance image and segmenting the nuclear magnetic resonance image based on the boundary of the target position area;
the Point Rend network module is used for reclassifying the boundary after the segmentation processing to obtain a boundary segmentation result meeting a preset condition; and outputting a two-dimensional medical image of the cartilage body position area based on the boundary segmentation result.
4. An intelligent three-dimensional diagnosis system for osteoarthritis based on deep learning, which is characterized by comprising:
an image data acquisition unit for acquiring nuclear magnetic resonance image data of the knee joint;
the image segmentation processing unit is used for inputting the nuclear magnetic resonance image data into a preset image segmentation network model to segment the cartilage region and obtaining a two-dimensional medical image of the cartilage body position region output by the image segmentation network model; the image segmentation network model is obtained by training a sample based on sample bone image data and a cartilage region segmentation result corresponding to the sample bone image data;
the three-dimensional reconstruction unit is used for constructing and obtaining a corresponding three-dimensional medical image based on the two-dimensional medical image of the cartilage body position area and the nuclear magnetic resonance image data;
a cartilage damage degree determining unit, configured to determine a target cartilage in the three-dimensional medical image, and analyze the target cartilage to determine a damage degree of the target cartilage;
the cartilage damage degree determination unit is specifically configured to: performing qualitative analysis on the target cartilage, judging whether the target cartilage is knee osteoarthritis or not, if so, identifying the outline of the target cartilage with a defect region, determining the number of pixels of the defect region in the outline, classifying cartilage damage degrees according to the ratio of the number of pixels of the defect region to the number of pixels of a total region of the target cartilage, and determining a first damage degree of the target cartilage; the method comprises the steps of identifying the outline of a defect area of target cartilage, determining the cartilage thickness of the defect area, identifying the maximum thickness of the target cartilage, classifying cartilage defect degrees according to the thickness ratio between the cartilage thickness of the defect area and the maximum thickness of the target cartilage, and determining a second damage degree of the target cartilage.
5. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the intelligent three-dimensional diagnosis method for osteoarthritis based on deep learning according to any one of claims 1 to 3 when executing the computer program.
6. A processor-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the intelligent deep learning-based three-dimensional osteoarthritis diagnosis method according to any one of claims 1 to 3.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210680643.XA CN115131300B (en) | 2022-06-15 | 2022-06-15 | Intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning |
| PCT/CN2023/071147 WO2023241031A1 (en) | 2022-06-15 | 2023-01-08 | Deep learning-based three-dimensional intelligent diagnosis method and system for osteoarthritis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210680643.XA CN115131300B (en) | 2022-06-15 | 2022-06-15 | Intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115131300A CN115131300A (en) | 2022-09-30 |
| CN115131300B true CN115131300B (en) | 2023-04-07 |
Family
ID=83378972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210680643.XA Active CN115131300B (en) | 2022-06-15 | 2022-06-15 | Intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115131300B (en) |
| WO (1) | WO2023241031A1 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115131300B (en) * | 2022-06-15 | 2023-04-07 | 北京长木谷医疗科技有限公司 | Intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning |
| CN116071372B (en) * | 2022-12-30 | 2024-03-19 | 北京长木谷医疗科技股份有限公司 | Knee joint segmentation method, knee joint segmentation device, electronic equipment and storage medium |
| CN116228903B (en) * | 2023-01-18 | 2024-02-09 | 北京长木谷医疗科技股份有限公司 | High-definition CT image reconstruction method based on CSA module and deep learning model |
| CN115810015B (en) * | 2023-02-09 | 2023-05-23 | 慧影医疗科技(北京)股份有限公司 | Automatic knee joint segmentation method, system, medium and equipment based on deep learning |
| CN116798613B (en) * | 2023-08-23 | 2023-11-28 | 山东大学齐鲁医院(青岛) | Knee osteoarthritis diagnosis method based on arthroscopy imaging |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021031066A1 (en) * | 2019-08-19 | 2021-02-25 | 中国科学院深圳先进技术研究院 | Cartilage image segmentation method and apparatus, readable storage medium, and terminal device |
| WO2022037696A1 (en) * | 2020-08-21 | 2022-02-24 | 张逸凌 | Bone segmentation method and system based on deep learning |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7920730B2 (en) * | 2005-10-07 | 2011-04-05 | Siemens Medical Solutions Usa, Inc. | Automatic bone detection in MRI images |
| CN110097546B (en) * | 2019-04-30 | 2021-04-13 | 北京大学第三医院 | Method and device for evaluating defects of knee joint cartilage tissues |
| CN111178428B (en) * | 2019-12-27 | 2024-03-22 | 上海联影智能医疗科技有限公司 | Cartilage damage classification method, cartilage damage classification device, computer equipment and storage medium |
| CN113392895A (en) * | 2021-06-09 | 2021-09-14 | 瓴域影诺(北京)科技有限公司 | Knee joint cartilage damage detection method and system |
| CN113689402B (en) * | 2021-08-24 | 2022-04-12 | 北京长木谷医疗科技有限公司 | Deep learning-based femoral medullary cavity form identification method, device and storage medium |
| CN115131300B (en) * | 2022-06-15 | 2023-04-07 | 北京长木谷医疗科技有限公司 | Intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning |
-
2022
- 2022-06-15 CN CN202210680643.XA patent/CN115131300B/en active Active
-
2023
- 2023-01-08 WO PCT/CN2023/071147 patent/WO2023241031A1/en unknown
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021031066A1 (en) * | 2019-08-19 | 2021-02-25 | 中国科学院深圳先进技术研究院 | Cartilage image segmentation method and apparatus, readable storage medium, and terminal device |
| WO2022037696A1 (en) * | 2020-08-21 | 2022-02-24 | 张逸凌 | Bone segmentation method and system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115131300A (en) | 2022-09-30 |
| WO2023241031A1 (en) | 2023-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115131300B (en) | Intelligent three-dimensional diagnosis method and system for osteoarthritis based on deep learning | |
| CN111553892B (en) | Lung nodule segmentation calculation method, device and system based on deep learning | |
| Xu et al. | DeepLN: a framework for automatic lung nodule detection using multi-resolution CT screening images | |
| US20170004619A1 (en) | System and method for automatic pulmonary embolism detection | |
| Alksas et al. | A novel computer-aided diagnostic system for accurate detection and grading of liver tumors | |
| CN109191451B (en) | Abnormality detection method, apparatus, device, and medium | |
| US11471096B2 (en) | Automatic computerized joint segmentation and inflammation quantification in MRI | |
| Diao et al. | Weakly supervised framework for cancer region detection of hepatocellular carcinoma in whole-slide pathologic images based on multiscale attention convolutional neural network | |
| Yao et al. | Texture synthesis based thyroid nodule detection from medical ultrasound images: interpreting and suppressing the adversarial effect of in-place manual annotation | |
| CN111445443B (en) | Early acute cerebral infarction detection method and device | |
| CN110738633B (en) | Three-dimensional image processing method and related equipment for organism tissues | |
| Kaliyugarasan et al. | Pulmonary nodule classification in lung cancer from 3D thoracic CT scans using fastai and MONAI | |
| Ben-Cohen et al. | Liver lesion detection in CT using deep learning techniques | |
| Chang et al. | utilization of a convolutional neural network for automated detection of lytic spinal lesions on body CTs | |
| Zhou et al. | Improved breast lesion detection in mammogram images using a deep neural network | |
| Zhang et al. | Dynamic feature learning for COVID-19 segmentation and classification | |
| Nakamoto et al. | Three-dimensional conditional generative adversarial network-based virtual thin-slice technique for the morphological evaluation of the spine | |
| Qu et al. | Deep learning on digital mammography for expert-level diagnosis accuracy in breast cancer detection | |
| CN112651960A (en) | Image processing method, device, equipment and storage medium | |
| CN111402219A (en) | Old cerebral infarction detection method and device | |
| Bhushan | Liver cancer detection using hybrid approach-based convolutional neural network (HABCNN) | |
| Kim et al. | Applications of Artificial Intelligence in Mammography from a Development and Validation Perspective. | |
| CN115359060B (en) | Focus example segmentation method and device for pneumonia CT image | |
| Cao et al. | Automatic lung segmentation algorithm on chest X-ray images based on fusion variational auto-encoder and three-terminal attention mechanism. Symmetry 2021; 13 (5): 814 | |
| KR102647251B1 (en) | Method for evaluating low limb alignment and device for evaluating low limb alignment using the same |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100176 2201, 22 / F, building 1, yard 2, Ronghua South Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee after: Beijing Changmugu Medical Technology Co.,Ltd. Patentee after: Zhang Yiling Address before: 100176 2201, 22 / F, building 1, yard 2, Ronghua South Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee before: BEIJING CHANGMUGU MEDICAL TECHNOLOGY Co.,Ltd. Patentee before: Zhang Yiling |
|
| CP01 | Change in the name or title of a patent holder |