CN110298820A - Image analysis methods, computer equipment and storage medium - Google Patents
Image analysis methods, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110298820A CN110298820A CN201910451758.XA CN201910451758A CN110298820A CN 110298820 A CN110298820 A CN 110298820A CN 201910451758 A CN201910451758 A CN 201910451758A CN 110298820 A CN110298820 A CN 110298820A
- Authority
- CN
- China
- Prior art keywords
- medical image
- network
- analyzed
- morphological structure
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003703 image analysis method Methods 0.000 title claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 136
- 201000010099 disease Diseases 0.000 claims abstract description 124
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 124
- 238000000034 method Methods 0.000 claims abstract description 58
- 230000000877 morphologic effect Effects 0.000 claims description 134
- 230000011218 segmentation Effects 0.000 claims description 47
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 17
- 238000002372 labelling Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 abstract description 15
- 210000000038 chest Anatomy 0.000 description 22
- 238000010191 image analysis Methods 0.000 description 22
- 230000003902 lesion Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 210000000056 organ Anatomy 0.000 description 8
- 238000011976 chest X-ray Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 6
- 239000000284 extract Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 201000003144 pneumothorax Diseases 0.000 description 4
- 206010056342 Pulmonary mass Diseases 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000002591 computed tomography Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 210000004072 lung Anatomy 0.000 description 2
- 238000002600 positron emission tomography Methods 0.000 description 2
- 238000002601 radiography Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 210000000115 thoracic cavity Anatomy 0.000 description 2
- 206010063045 Effusion Diseases 0.000 description 1
- 206010035664 Pneumonia Diseases 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000002216 heart Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 210000001370 mediastinum Anatomy 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
- 230000001902 propagating effect Effects 0.000 description 1
- 230000002685 pulmonary effect Effects 0.000 description 1
- 206010039722 scoliosis Diseases 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 201000008827 tuberculosis Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- 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
- G06T2207/20—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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
This application involves a kind of image analysis methods, computer equipment and storage medium, due to being analyzed from the kinds of Diseases of medical image to be analyzed, kinds of Diseases analysis network is corresponded to calling, and the whole process that medical image is analyzed is analyzed by the analysis network handles of calling, it is that computer equipment executes automatically, the analysis result of medical image to be analyzed can be obtained without artificial interference for overall process, in this way, disease is diagnosed according to rabat using this method, the efficiency for analyzing medical image to be analyzed can not only be greatly improved, it can also guarantee precision of analysis.
Description
Technical Field
The present application relates to the field of medical technology, and in particular, to an image analysis method, a computer device, and a storage medium.
Background
Because the X-ray photograph has the characteristics of convenience, simplicity and economy, the X-ray photograph becomes the priority for chest examination.
Chest radiographs imaged by X-ray are an important means widely used in clinical diagnosis, and can be used to examine diseases of the thorax (including ribs, thoracic vertebrae, soft tissues, etc.), thoracic cavity, lung tissues, mediastinum, heart, etc. Generally, when a chest film is used for diagnosing chest diseases, a doctor needs to read each case and give a diagnosis report, or the doctor firstly reads the film and then classifies the diseases, and then inputs the chest film into analysis software corresponding to the disease types to obtain corresponding diagnosis results.
However, the prior art methods for diagnosing diseases based on chest radiographs have a problem of low efficiency.
Disclosure of Invention
In view of the above, it is necessary to provide an image analysis method, a computer device and a storage medium for solving the technical problem of the prior art that the diagnosis method for diseases based on chest radiographs is inefficient.
In a first aspect, an embodiment of the present application provides an image analysis method, including:
inputting the medical image to be analyzed into a disease classification network to obtain the disease types of the medical image to be analyzed in different disease types;
calling an analysis network corresponding to the disease category;
and analyzing the medical image to be analyzed through an analysis network to obtain an analysis result.
In one embodiment, the analysis network includes at least one of a classification network, a segmentation network, and a detection network.
In one embodiment, the analyzing the medical image to be analyzed through the analysis network to obtain an analysis result includes:
extracting characteristic information of a target morphological structure in a medical image to be analyzed;
and analyzing the medical image to be analyzed according to the characteristic information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed to obtain an analysis result.
In one embodiment, before analyzing the medical image to be analyzed according to the feature information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed, the method includes:
calling a preset segmentation network, and segmenting all morphological structures in the medical image to be analyzed to obtain segmentation results of all morphological structures;
and determining the position information of the target morphological structure in the medical image to be analyzed according to the segmentation result of each morphological structure.
In one embodiment, the extracting feature information of the target morphological structure in the medical image to be analyzed includes:
calling a target morphological structure detection network corresponding to the disease type, detecting a target morphological structure in the medical image to be analyzed, and labeling the target morphological structure to obtain a labeling result of the target morphological structure; the labeling result comprises the characteristic information of the target morphological structure;
or,
calling a target morphological structure segmentation network corresponding to the disease type, and segmenting the target morphological structure to obtain a segmentation result of the target morphological structure; the segmentation result includes feature information of the target morphological structure.
In one embodiment, the analyzing the medical image to be analyzed according to the feature information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed to obtain an analysis result includes:
calling a preset report template, and generating an analysis report according to the disease type of the medical image to be analyzed, the characteristic information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed; the analysis report is used for characterizing the analysis result of the target morphological structure.
In one embodiment, the method for training the disease classification network includes:
acquiring a plurality of sample medical images and a gold standard of a corresponding disease type of each sample medical image;
inputting a plurality of sample medical images and the gold standard of the corresponding disease type of each sample medical image into an initial disease classification network for training;
and iteratively updating the network parameters of the initial disease classification network according to the gold standard of the corresponding disease type of each sample medical image until the disease classification network is obtained.
In one embodiment, the training method for the analysis network includes:
acquiring a plurality of sample medical images and a gold standard of a target morphological structure analysis result in each sample medical image;
inputting a plurality of sample medical images and a gold standard of a target morphological structure analysis result in each sample medical image into an initial analysis network for training;
and iteratively updating the network parameters of the initial analysis network according to the golden standard of the target morphological structure analysis result in each sample medical image until the analysis network is obtained.
In a second aspect, an embodiment of the present application provides an image analysis apparatus, including:
the type module is used for inputting the medical image to be analyzed into the disease classification network to obtain the disease types of the medical image to be analyzed in various different disease types;
the calling module is used for calling the analysis network corresponding to the disease type;
and the analysis module is used for analyzing the medical image to be analyzed through the analysis network to obtain an analysis result.
In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of any one of the methods provided in the embodiments of the first aspect when executing the computer program.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of any one of the methods provided in the embodiments of the first aspect.
According to the image analysis method, the computer equipment and the storage medium, the whole process from the disease type analysis of the medical image to be analyzed to the calling of the corresponding disease type analysis network and the analysis of the medical image to be analyzed through the called analysis network is automatically executed by the computer equipment, and the analysis result of the medical image to be analyzed can be obtained without manual interference in the whole process.
Drawings
Fig. 1 is an application environment diagram of an image analysis method according to an embodiment;
fig. 2 is a schematic flowchart of an image analysis method according to an embodiment;
fig. 3 is a schematic flowchart of an image analysis method according to an embodiment;
fig. 4 is a schematic flowchart of an image analysis method according to an embodiment;
FIG. 5 is a complete diagram of an image analysis method according to an embodiment;
fig. 6 is a schematic flowchart of an image analysis method according to an embodiment;
fig. 7 is a schematic flowchart of an image analysis method according to an embodiment;
FIG. 8 is a diagram illustrating a neural network training process, according to an embodiment;
fig. 9 is a block diagram illustrating an exemplary image analysis apparatus;
fig. 10 is a block diagram illustrating an exemplary image analysis apparatus;
fig. 11 is a block diagram illustrating an exemplary image analysis apparatus;
fig. 12 is a block diagram illustrating an exemplary image analysis apparatus;
fig. 13 is a block diagram of an image analysis apparatus according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The image analysis method provided by the embodiment of the application can be applied to the application environment shown in fig. 1, wherein the computer device comprises a processor, a memory, a network interface and a database which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data of the image analysis method. The network interface of the computer device is used for communicating with other external devices through network connection. The computer program is executed by a processor to implement an image analysis method.
The embodiment of the application provides an image analysis method, computer equipment and a storage medium, and aims to solve the technical problem that the method for diagnosing diseases according to chest radiographs in the prior art is low in efficiency. The following describes in detail the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems by embodiments and with reference to the drawings. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. It should be noted that in the image analysis method provided in the embodiment of the present application, the execution subject in fig. 2 to fig. 8 is a computer device, wherein the execution subject may also be an image analysis apparatus, and the apparatus may be implemented as part or all of the image analysis by software, hardware, or a combination of software and hardware.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments.
In an embodiment, fig. 2 provides an image analysis method, and this embodiment relates to a specific process in which a computer device invokes a corresponding analysis network to analyze a medical image to be analyzed according to a disease type of the medical image to be analyzed, as shown in fig. 2, the method includes:
s101, inputting the medical image to be analyzed into a disease classification network to obtain the disease types of the medical image to be analyzed in different disease types.
In this embodiment, the medical image to be analyzed may be an acquired image of any part of a human body, such as a Computed Tomography (CT) image, a Positron Emission Tomography (PET) image, an X-ray image, and the like, which is not limited in this embodiment. 1, the medical image to be analyzed may be pre-stored in the computer device, or may be input by the computer device in real time by other devices, which is not limited in this embodiment. The disease classification network is a network model which is trained in advance and can analyze the disease types of various medical images. The disease category includes, but is not limited to, cardiac shadow enlargement, pneumothorax, mass, pulmonary nodule, lung effusion, pneumonia, tuberculosis, scoliosis, etc.
For example, in practical applications, taking the medical image to be analyzed as an X-ray film of the chest as an example, the computer device inputs the X-ray film of the chest into a pre-trained disease classification network, and the output result of the disease classification network is the disease category of the X-ray film of the chest in various disease categories.
S102, calling an analysis network corresponding to the disease type.
Based on the disease type of the medical image to be analyzed determined in S101, the computer device invokes an analysis network corresponding to the disease type, where the analysis network is a pre-trained network model for performing detailed analysis on the lesion in the medical image to be analyzed, and the analysis network may be only one neural network or may be formed by multiple neural networks according to specific content to be analyzed, which is not limited in this embodiment. The method for invoking the analysis network by the computer device is automatically invoked according to a preset program, and the specific content of the set program is not specifically limited in this embodiment.
S103, analyzing the medical image to be analyzed through an analysis network to obtain an analysis result.
In this step, based on the analysis network called in the step S102 corresponding to the disease category, the computer device inputs the medical image to be analyzed into the analysis network, that is, analyzes the medical image to be analyzed through the analysis network, and an output result of the analysis network is an analysis result of a focus in the medical image to be analyzed. For example, if the medical image to be analyzed is a chest X-ray film, the information of the location, shape, size, etc. of the lesion in the chest X-ray film can be analyzed through the analysis network.
In the image analysis method provided by the embodiment, the whole process from the disease type analysis of the medical image to be analyzed to the calling of the corresponding disease type analysis network and the analysis of the medical image to be analyzed through the called analysis network is automatically executed by the computer equipment, and the analysis result of the medical image to be analyzed can be obtained in the whole process without manual interference.
The analysis network mentioned in the above embodiment may be formed by only one network model or a plurality of network models according to different analysis directions of actual needs. Based on the above embodiments, an embodiment is provided wherein the analysis network comprises only one network model, and in one embodiment the analysis network comprises at least one of a classification network, a segmentation network, and a detection network. For example, if the analysis network is a classification network, when the computer device analyzes the medical image to be analyzed through the classification network, the computer device may classify the disease degree of the lesion in the medical image to be analyzed, for example, analyze that the lesion in the medical image to be analyzed belongs to mild, moderate or severe degree, or classify other contents, which is not limited in this embodiment. If the analysis network is a segmentation network, when the computer device analyzes the medical image to be analyzed through the segmentation network, the computer device may segment the lesion form in the medical image to be analyzed, or segment other content, which is not limited in this embodiment. If the analysis network is a detection network, when the computer device analyzes the medical image to be analyzed through the detection network, the computer device may detect specific feature information of a focus in the medical image to be analyzed, or may detect other content, which is not limited in this embodiment. Optionally, the classification network includes, but is not limited to, Resnet, densenert, SENET, and the like; detection networks include, but are not limited to, fast-RCNN, YOLO-V3, Retianet, etc.; segmented networks include, but are not limited to, U-net, V-net, Linknet, and the like.
Based on the above embodiments, two specific examples are provided, and in one example, the medical image is in a classification network of disease types, and if it is determined that the disease type is a lung nodule, the lung nodule detection network is automatically invoked, and the medical image is detected by using the lung nodule detection network. In another example, the medical image is in a classification network of disease types, if the disease type is determined to be pneumothorax, a pneumothorax segmentation network is automatically called, and the medical image is segmented by the pneumothorax segmentation network.
Also, based on the foregoing embodiment, in another embodiment, an embodiment is provided in which the analysis network includes a plurality of network models, as shown in fig. 3, where the step S103 includes:
s201, extracting characteristic information of a target morphological structure in the medical image to be analyzed.
In this embodiment, after the computer device calls the analysis network corresponding to the disease type in the step S102, the process of analyzing the medical image to be analyzed through the analysis network may specifically be to extract feature information of a target morphological mechanism in the medical image to be analyzed, for example, the computer device may extract feature information of a target morphological structure from the medical image to be analyzed through a pre-trained target morphological segmentation network or a pre-trained target morphological detection network, or may extract the feature information in other manners, which is not limited in this embodiment.
S202, analyzing the medical image to be analyzed according to the characteristic information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed to obtain an analysis result.
In this step, based on the feature information of the target morphological structure extracted in the step S201, the computer device analyzes the medical image to be analyzed and obtains an analysis result by combining the position information of the target morphological structure in the medical image to be analyzed. The position information of the target morphological structure information in the medical image to be analyzed is determined by the computer equipment according to all morphological structures in the medical image to be analyzed.
In the image analysis method provided by this embodiment, the computer device analyzes the medical image to be analyzed according to the feature information of the target morphological structure in the medical image to be analyzed and the position information of the target morphological structure in the entire medical image, so that the obtained analysis result can accurately reflect the condition of the target morphological structure (lesion), and the medical image to be analyzed can be objectively and accurately analyzed.
Optionally, for a manner that a computer device extracts feature information of a target morphological structure through a pre-trained network, an embodiment of the present application provides an image analysis method, where the step S201 includes: calling a target morphological structure detection network corresponding to the disease type, detecting a target morphological structure in the medical image to be analyzed, and labeling the target morphological structure to obtain a labeling result of the target morphological structure; the labeling result comprises the characteristic information of the target morphological structure; or calling a target morphological structure segmentation network corresponding to the disease type, and segmenting the target morphological structure to obtain a segmentation result of the target morphological structure; the segmentation result includes feature information of the target morphological structure.
In this embodiment, if the computer device calls the target morphological structure detection network corresponding to the disease type, the target morphological structure in the medical image to be analyzed is detected, and the detected target morphological structure is labeled, where the labeling result includes feature information of the target morphological structure, for example, when an X-ray film of a chest radiograph is input to the detection network corresponding to the disease type, a lesion in the X-ray film of the chest radiograph and feature information such as a size and a form of the lesion may be detected, and based on the detected feature information, the computer device labels the lesion and displays the detected feature information in the labeling result. Similarly, if the computer device calls a target morphological structure segmentation network corresponding to a disease type, the target morphological structure in the medical image to be analyzed is segmented, wherein the segmentation result includes feature information of the target morphological structure, for example, if an X-ray film of a chest radiography is input to the segmentation network corresponding to the disease type, the lesion in the X-ray film of the chest radiography can be segmented, and the feature information of the lesion is displayed in the segmentation result. In the above two cases, the specific content of the feature information of the target morphological structure extracted by the computer device may include other information besides the listed information such as size and morphology, which is not limited in this embodiment.
In the image analysis method provided by the embodiment, the computer device automatically extracts the target morphological structure feature information in the medical image to be analyzed, and the target morphological structure feature information is extracted through the pre-trained network model, so that the efficiency and the accuracy of extracting the target morphological structure feature information can be improved.
Optionally, an embodiment of the present application provides an image analysis method, which is a specific process of acquiring, by a computer device, position information of a target morphological structure in a medical image to be analyzed, as shown in fig. 4, and the method includes:
s301, calling a preset segmentation network, and segmenting all morphological structures in the medical image to be analyzed to obtain segmentation results of all the morphological structures.
In this embodiment, the preset segmentation network is used to segment all morphological structures in the medical image to be analyzed, for example, taking the medical image to be analyzed as a chest X-ray film, the computer device inputs the chest X-ray film into the pre-trained segmentation network to obtain the segmentation results of all organs in the medical image to be analyzed.
S302, according to the segmentation result of each morphological structure, the position information of the target morphological structure in the medical image to be analyzed is determined.
Based on the segmentation results of the morphological structures determined in step S301, that is, the segmentation results of all organs in the medical image to be analyzed, the computer device determines specific position information of the target morphological structure (lesion) in the medical image to be analyzed according to all the organs that are segmented, for example, the position information may be embodied in the form of coordinates, or embodied in the form of upper, middle, lower, and equal orientation words and distance parameters, which is not limited in this embodiment.
In the image analysis method provided by the embodiment, computer equipment firstly segments all organs in the medical image to be analyzed, and then determines the position information of the focus from the segmented result, so that the position information of the focus can be more accurate, and the objectivity and the accuracy of the analysis result can be ensured.
Regarding an implementation manner of the step S202 in the embodiment of fig. 3, an embodiment of the present application provides an image analysis method, where the step S202 includes: calling a preset report template, and generating an analysis report according to the disease type of the medical image to be analyzed, the characteristic information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed; the analysis report is used for characterizing the analysis result of the target morphological structure.
In this embodiment, the preset report template represents a corpus that is set by a program in advance and quantitatively describes an analysis result, and the specific program is not limited in this embodiment, and based on the preset report template, the computer device inputs information of the disease type of the medical image to be analyzed obtained in step S101, the feature information of the target morphological structure extracted in step S201, and the position information of the target morphological structure in the medical image to be analyzed into the preset template, so as to generate an analysis report carrying these information. For example, the analysis report may include a quantitative description of the location, size, and morphology information of the disease present on a chest X-ray. Therefore, the extracted target morphological structure information in the medical image to be analyzed is displayed in a report form by adopting the preset language library, so that a doctor can conveniently diagnose a disease according to the analysis report, and a diagnosis object can conveniently and visually know the diagnosis result.
Illustratively, based on all the embodiments described above, the present application provides a complete method for analyzing a chest X-ray film, as shown in fig. 5, the method comprising: the method comprises the steps of firstly inputting chest X-ray images into a pre-training disease classification network to obtain common diseases existing in chest pictures, inputting the chest pictures into a pre-training detection or segmentation network corresponding to the diseases according to different diseases in the chest pictures to further obtain information of focus size, shape and the like, meanwhile, inputting the chest pictures into a pre-training organ segmentation network to obtain a chest picture organ segmentation result so as to generate position information of the focus in the chest picture organ in an intelligent report, and then combining a preset report template according to the obtained disease information and the organ segmentation result to generate a diagnosis report.
In addition, the training process of the disease classification network and the analysis network in the above embodiments will be described below by two embodiments, in one embodiment, the present application provides an image analysis method, as shown in fig. 6, where the training method of the disease classification network includes:
s401, a plurality of sample medical images and the gold standard of the corresponding disease type of each sample medical image are obtained.
In this embodiment, the sample medical image represents a training sample when training the disease classification network, and the sample medical image may be a CT image, a PET image, an X-ray film, and the like of any part of a human body, which is not limited in this embodiment. Wherein the gold standard of the corresponding disease category of each sample medical image represents the determined accurate disease category of each sample medical image. In practical application, the manner in which the computer device directly obtains the plurality of sample medical images and the respective corresponding disease category gold standard may be that the images are transmitted by other devices, or the images are directly obtained from a database, which is not limited in this embodiment.
S402, inputting a plurality of sample medical images and the gold standard of the corresponding disease type of each sample medical image into an initial disease classification network for training.
Based on the training data obtained in step S401, the computer device inputs the plurality of sample medical images and the gold standard of the corresponding disease category of each sample medical image into the initial disease classification network for training.
And S403, iteratively updating the network parameters of the initial disease classification network according to the gold standard of the corresponding disease type of each sample medical image until the disease classification network is obtained.
In this step, the computer device trains an initial disease classification network, and iteratively updates network parameters of the network until a disease classification network is obtained. For example, during training, the output result of the initial disease classification network may be compared with the gold standard of the corresponding disease category of each sample medical image, or a loss function established according to the gold standard of the corresponding disease category of each sample medical image, and the parameters of the initial disease classification network may be iteratively updated through back propagation of the loss function.
In another embodiment, an embodiment of the present application provides an image analysis method, as shown in fig. 7, the method for training an analysis network includes:
s501, obtaining a plurality of sample medical images and a gold standard of a target morphological structure analysis result in each sample medical image.
In this embodiment, the sample medical images may refer to the description in the embodiment of fig. 6, which is not repeated herein, and the gold standard of the analysis result of the target morphological structure in each sample medical image represents an accurate analysis result of the target morphological structure in each sample medical image. Similarly, the manner of acquiring a plurality of sample medical images and the target morphological structure analysis result by the computer device is the same as that in the embodiment shown in fig. 6, and the details of this embodiment are not repeated herein.
And S502, inputting a plurality of sample medical images and the golden standard of the target morphological structure analysis result in each sample medical image into an initial analysis network for training.
Based on the training data obtained in step S501, the computer device inputs the plurality of sample medical images and the gold standard of the target morphological structure analysis result in each sample medical image into the initial analysis network for training.
And S503, iteratively updating the network parameters of the initial analysis network according to the golden standard of the target morphological structure analysis result in each sample medical image until the analysis network is obtained.
In this step, the computer device trains an initial analysis network and iteratively updates network parameters of the network until an analysis network is obtained. For example, during training, the analysis network output result may be compared with the gold standard of the target morphological structure analysis result of each sample medical image, or a loss function established according to the gold standard of the target morphological structure analysis result of each sample medical image, and the parameters of the initial analysis may be iteratively updated through back propagation of the loss function.
Illustratively, as shown in fig. 8, a network training method is provided, wherein the training method can be applied to training of any one of the networks in the embodiments of the present application. The method comprises the following steps: inputting training samples with true value labels into a deep learning network (such as a classification, detection or segmentation network), comparing the output of the deep learning network with the true value to calculate a loss value, reversely propagating the loss value to update parameters of the deep learning network, continuously and iteratively training the updated network parameters on a training set according to the method, stopping iteration after preset iteration times are reached, and obtaining any one of the neural network models.
In the training process of the disease classification network and the analysis network provided in the embodiment, the initial network is trained through a plurality of sample data and corresponding gold standards, parameters of the iterative network are continuously updated, and the accuracy of the finally obtained network is greatly ensured.
It should be understood that although the various steps in the flow charts of fig. 2-8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-8 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 9, there is provided an image analysis apparatus including: a type module 10, a calling module 11 and an analysis module 12, wherein,
the type module 10 is used for inputting the medical image to be analyzed into a disease classification network to obtain the disease types of the medical image to be analyzed in various disease types;
the calling module 11 is used for calling an analysis network corresponding to the disease type;
and the analysis module 12 is configured to analyze the medical image to be analyzed through an analysis network to obtain an analysis result.
The implementation principle and technical effect of the image analysis apparatus provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, the analysis network comprises at least one of a classification network, a segmentation network, and a detection network.
In one embodiment, as shown in fig. 10, there is provided an image analysis apparatus, wherein the analysis module 12 includes: an extraction unit 121 and an analysis unit 122, wherein,
an extracting unit 121, configured to extract feature information of a target morphological structure in a medical image to be analyzed;
the analysis unit 122 is configured to analyze the medical image to be analyzed according to the feature information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed, so as to obtain an analysis result.
The implementation principle and technical effect of the image analysis apparatus provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, as shown in fig. 11, there is provided an image analysis apparatus, wherein the analysis module 12 further includes:
the segmentation unit 123 is configured to invoke a preset segmentation network, and segment all morphological structures in the medical image to be analyzed to obtain a segmentation result of each morphological structure;
a location unit 124, configured to determine location information of the target morphological structure in the medical image to be analyzed according to the segmentation result of each morphological structure.
The implementation principle and technical effect of the image analysis apparatus provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In an embodiment, the extracting unit 121 is specifically configured to invoke a target morphological structure detection network corresponding to a disease type, detect a target morphological structure in a medical image to be analyzed, and label the target morphological structure to obtain a labeling result of the target morphological structure; the labeling result comprises the characteristic information of the target morphological structure; or calling a target morphological structure segmentation network corresponding to the disease type, and segmenting the target morphological structure to obtain a segmentation result of the target morphological structure; the segmentation result includes feature information of the target morphological structure.
The implementation principle and technical effect of the image analysis apparatus provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In an embodiment, the analysis unit 122 is specifically configured to invoke a preset report template, and generate an analysis report according to the disease type of the medical image to be analyzed, the feature information of the target morphological structure, and the position information of the target morphological structure in the medical image to be analyzed; the analysis report is used for characterizing the analysis result of the target morphological structure.
The implementation principle and technical effect of the image analysis apparatus provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, as shown in fig. 12, there is provided an image analysis apparatus including: a first acquisition module 13, a first input module 14 and a first training module 15, wherein,
a first obtaining module 13, configured to obtain a plurality of sample medical images and a gold standard of a corresponding disease category of each sample medical image;
a first input module 14, configured to input a plurality of sample medical images and a gold standard of a corresponding disease category of each sample medical image into an initial disease classification network for training;
and the first training module 15 is configured to iteratively update the network parameters of the initial disease classification network according to the gold standard of the corresponding disease type of each sample medical image until a disease classification network is obtained.
The implementation principle and technical effect of the image analysis apparatus provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, as shown in fig. 13, there is provided an image analysis apparatus including: a second acquisition module 16, a second input module 17 and a second training module 18, wherein,
a second obtaining module 16, configured to obtain a plurality of sample medical images and a gold standard of a target morphological structure analysis result in each sample medical image;
a second input module 17, configured to input a plurality of sample medical images and a gold standard of a target morphological structure analysis result in each sample medical image into an initial analysis network for training;
and the second training module 18 is configured to iteratively update the network parameters of the initial analysis network according to the gold standard of the target morphological structure analysis result in each sample medical image until the analysis network is obtained.
The implementation principle and technical effect of the image analysis apparatus provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
For the specific limitations of the image analysis apparatus, reference may be made to the limitations of the image analysis method above, and details are not repeated here. All or part of the modules in the image analysis device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, the internal structure of which may be as described above in fig. 1. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an image analysis method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 1 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
inputting the medical image to be analyzed into a disease classification network to obtain the disease types of the medical image to be analyzed in different disease types;
calling an analysis network corresponding to the disease category;
and analyzing the medical image to be analyzed through an analysis network to obtain an analysis result.
The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
inputting the medical image to be analyzed into a disease classification network to obtain the disease types of the medical image to be analyzed in different disease types;
calling an analysis network corresponding to the disease category;
and analyzing the medical image to be analyzed through an analysis network to obtain an analysis result.
The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An image analysis method, comprising:
inputting the medical image to be analyzed into a disease classification network to obtain the disease types of the medical image to be analyzed in different disease types;
calling an analysis network corresponding to the disease category;
and analyzing the medical image to be analyzed through the analysis network to obtain an analysis result.
2. The method of claim 1, wherein analyzing the network comprises at least one of classifying the network, splitting the network, and detecting the network.
3. The method according to claim 1, wherein the analyzing the medical image to be analyzed through the analysis network to obtain an analysis result comprises:
extracting characteristic information of a target morphological structure in the medical image to be analyzed;
and analyzing the medical image to be analyzed according to the characteristic information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed to obtain an analysis result.
4. The method according to claim 3, wherein before the analyzing the medical image to be analyzed according to the feature information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed, the method comprises:
calling a preset segmentation network, and segmenting all morphological structures in the medical image to be analyzed to obtain segmentation results of all morphological structures;
and determining the position information of the target morphological structure in the medical image to be analyzed according to the segmentation result of each morphological structure.
5. The method according to claim 3 or 4, wherein the extracting feature information of the target morphological structure in the medical image to be analyzed comprises:
calling a target morphological structure detection network corresponding to the disease type, detecting a target morphological structure in the medical image to be analyzed, and labeling the target morphological structure to obtain a labeling result of the target morphological structure; the labeling result comprises the characteristic information of the target morphological structure;
or,
calling a target morphological structure segmentation network corresponding to the disease type, and segmenting the target morphological structure to obtain a segmentation result of the target morphological structure; the segmentation result includes feature information of the target morphological structure.
6. The method according to claim 3 or 4, wherein the analyzing the medical image to be analyzed according to the feature information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed to obtain an analysis result comprises:
calling a preset report template, and generating an analysis report according to the disease type of the medical image to be analyzed, the feature information of the target morphological structure and the position information of the target morphological structure in the medical image to be analyzed; the analysis report is used for characterizing the analysis result of the target morphological structure.
7. The method of claim 1, wherein the training of the disease classification network comprises:
acquiring a plurality of sample medical images and a gold standard of a corresponding disease type of each sample medical image;
inputting the plurality of sample medical images and the gold standard of the corresponding disease category of each sample medical image into an initial disease classification network for training;
and iteratively updating the network parameters of the initial disease classification network according to the gold standard of the corresponding disease category of each sample medical image until the disease classification network is obtained.
8. The method of claim 1, wherein the training method of the analysis network comprises:
obtaining a plurality of sample medical images and a gold standard of a target morphological structure analysis result in each sample medical image;
inputting the plurality of sample medical images and the gold standard of the target morphological structure analysis result in each sample medical image into an initial analysis network for training;
and iteratively updating the network parameters of the initial analysis network according to the golden standard of the target morphological structure analysis result in each sample medical image until the analysis network is obtained.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 8 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910451758.XA CN110298820A (en) | 2019-05-28 | 2019-05-28 | Image analysis methods, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910451758.XA CN110298820A (en) | 2019-05-28 | 2019-05-28 | Image analysis methods, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110298820A true CN110298820A (en) | 2019-10-01 |
Family
ID=68027259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910451758.XA Pending CN110298820A (en) | 2019-05-28 | 2019-05-28 | Image analysis methods, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298820A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111161239A (en) * | 2019-12-27 | 2020-05-15 | 上海联影智能医疗科技有限公司 | Medical image analysis method, device, storage medium and computer equipment |
| CN111325725A (en) * | 2020-02-19 | 2020-06-23 | 京东方科技集团股份有限公司 | Retina image recognition method and device, electronic equipment and storage medium |
| CN111415743A (en) * | 2020-03-17 | 2020-07-14 | 北京推想科技有限公司 | Pneumonia classification method, pneumonia classification device, pneumonia classification medium and electronic equipment |
| CN112396589A (en) * | 2020-11-24 | 2021-02-23 | 上海联影智能医疗科技有限公司 | Medical image recognition-based disease detection method, electronic device and readable medium |
| CN112508918A (en) * | 2020-12-11 | 2021-03-16 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN113553460A (en) * | 2021-08-13 | 2021-10-26 | 北京安德医智科技有限公司 | Image retrieval method and device, electronic device and storage medium |
| CN113628154A (en) * | 2020-04-23 | 2021-11-09 | 上海联影智能医疗科技有限公司 | Image analysis method, image analysis device, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040101181A1 (en) * | 2002-07-12 | 2004-05-27 | University Of Chicago | Automated method and system for computerized image analysis prognosis |
| CN1971565A (en) * | 2005-09-29 | 2007-05-30 | 通用电气公司 | Method, system and apparatus for automatically generating a disease severity index |
| CN101040800A (en) * | 2005-09-29 | 2007-09-26 | 通用电气公司 | System, method and device for diagnosing illness based on classification index |
| CN103473569A (en) * | 2013-09-22 | 2013-12-25 | 江苏美伦影像系统有限公司 | Medical image classification method based on SVM |
| CN107644419A (en) * | 2017-09-30 | 2018-01-30 | 百度在线网络技术（北京）有限公司 | Method and apparatus for analyzing medical image |
| CN109241903A (en) * | 2018-08-30 | 2019-01-18 | 平安科技（深圳）有限公司 | Sample data cleaning method, device, computer equipment and storage medium |
-
2019
- 2019-05-28 CN CN201910451758.XA patent/CN110298820A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040101181A1 (en) * | 2002-07-12 | 2004-05-27 | University Of Chicago | Automated method and system for computerized image analysis prognosis |
| CN1971565A (en) * | 2005-09-29 | 2007-05-30 | 通用电气公司 | Method, system and apparatus for automatically generating a disease severity index |
| CN101040800A (en) * | 2005-09-29 | 2007-09-26 | 通用电气公司 | System, method and device for diagnosing illness based on classification index |
| CN103473569A (en) * | 2013-09-22 | 2013-12-25 | 江苏美伦影像系统有限公司 | Medical image classification method based on SVM |
| CN107644419A (en) * | 2017-09-30 | 2018-01-30 | 百度在线网络技术（北京）有限公司 | Method and apparatus for analyzing medical image |
| CN109241903A (en) * | 2018-08-30 | 2019-01-18 | 平安科技（深圳）有限公司 | Sample data cleaning method, device, computer equipment and storage medium |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111161239A (en) * | 2019-12-27 | 2020-05-15 | 上海联影智能医疗科技有限公司 | Medical image analysis method, device, storage medium and computer equipment |
| CN111161239B (en) * | 2019-12-27 | 2024-02-27 | 上海联影智能医疗科技有限公司 | Medical image analysis method, device, storage medium and computer equipment |
| CN111325725A (en) * | 2020-02-19 | 2020-06-23 | 京东方科技集团股份有限公司 | Retina image recognition method and device, electronic equipment and storage medium |
| WO2021164640A1 (en) * | 2020-02-19 | 2021-08-26 | 京东方科技集团股份有限公司 | Retinal image recognition method and apparatus, electronic device, and storage medium |
| US11967181B2 (en) | 2020-02-19 | 2024-04-23 | Boe Technology Group Co., Ltd. | Method and device for retinal image recognition, electronic equipment, and storage medium |
| CN111415743A (en) * | 2020-03-17 | 2020-07-14 | 北京推想科技有限公司 | Pneumonia classification method, pneumonia classification device, pneumonia classification medium and electronic equipment |
| CN113628154A (en) * | 2020-04-23 | 2021-11-09 | 上海联影智能医疗科技有限公司 | Image analysis method, image analysis device, computer equipment and storage medium |
| CN112396589A (en) * | 2020-11-24 | 2021-02-23 | 上海联影智能医疗科技有限公司 | Medical image recognition-based disease detection method, electronic device and readable medium |
| CN112508918A (en) * | 2020-12-11 | 2021-03-16 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN113553460A (en) * | 2021-08-13 | 2021-10-26 | 北京安德医智科技有限公司 | Image retrieval method and device, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298820A (en) | Image analysis methods, computer equipment and storage medium | |
| Sermesant et al. | Applications of artificial intelligence in cardiovascular imaging | |
| KR101818074B1 (en) | Artificial intelligence based medical auto diagnosis auxiliary method and system therefor | |
| JP7279015B2 (en) | Evaluation of density in mammography | |
| CN110334722B (en) | Image classification method and device, computer equipment and storage medium | |
| CN111160367B (en) | Image classification method, apparatus, computer device, and readable storage medium | |
| CN112070119B (en) | Ultrasonic section image quality control method, device and computer equipment | |
| CN111210401B (en) | Automatic aortic detection and quantification from medical images | |
| KR102289277B1 (en) | Medical image diagnosis assistance apparatus and method generating evaluation score about a plurality of medical image diagnosis algorithm | |
| Nurmaini et al. | Accurate detection of septal defects with fetal ultrasonography images using deep learning-based multiclass instance segmentation | |
| CN111080584A (en) | Quality control method for medical image, computer device and readable storage medium | |
| JP7170000B2 (en) | LEARNING SYSTEMS, METHODS AND PROGRAMS | |
| US20210202072A1 (en) | Medical image diagnosis assistance apparatus and method for providing user-preferred style based on medical artificial neural network | |
| US11996182B2 (en) | Apparatus and method for medical image reading assistant providing representative image based on medical use artificial neural network | |
| JP2020171687A (en) | Systems and methods for processing 3d anatomical volumes based on localization of 2d slices thereof | |
| CN114092475B (en) | Focal length determining method, image labeling method, device and computer equipment | |
| CN111080583A (en) | Medical image detection method, computer device and readable storage medium | |
| CN111223158B (en) | Artifact correction method for heart coronary image and readable storage medium | |
| CN114332132A (en) | Image segmentation method and device and computer equipment | |
| CN111863204A (en) | Mammary gland disease AI auxiliary diagnosis method and system based on molybdenum target X-ray photographic examination | |
| CN112102235A (en) | Human body part recognition method, computer device, and storage medium | |
| CN111128348A (en) | Medical image processing method, device, storage medium and computer equipment | |
| KR20210054140A (en) | Medical image diagnosis assistance apparatus and method using a plurality of medical image diagnosis algorithm for endoscope images | |
| CN110570425A (en) | Lung nodule analysis method and device based on deep reinforcement learning algorithm | |
| CN113989231A (en) | Method and device for determining kinetic parameters, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191001 |