CN114663512A - Medical image accurate positioning method and system based on organ coding - Google Patents
Medical image accurate positioning method and system based on organ coding Download PDFInfo
- Publication number
- CN114663512A CN114663512A CN202210349691.0A CN202210349691A CN114663512A CN 114663512 A CN114663512 A CN 114663512A CN 202210349691 A CN202210349691 A CN 202210349691A CN 114663512 A CN114663512 A CN 114663512A
- Authority
- CN
- China
- Prior art keywords
- organ
- coding
- medical image
- image
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10104—Positron emission tomography [PET]
-
- 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
- G06T2207/30096—Tumor; Lesion
Abstract
The invention discloses a medical image accurate positioning method and a system based on organ coding, which comprises the steps of constructing an organ coding table, obtaining a medical image, predicting the medical image through a trained organ coding model to obtain organ coding information, wherein the organ coding model is a deep learning model; acquiring organ position information based on the organ coding information and the organ coding table; automatic segmentation of organs in medical images is performed based on organ position information. Through the mode of coding each medical image, the convolutional neural network is adopted for training, each medical image can be accurately positioned, and finally, effective segmentation or target region segmentation of organs is effectively carried out.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a medical image accurate positioning technology based on organ coding.
Background
The role and position of radiotherapy in tumor treatment are increasingly prominent, and the radiotherapy has become one of the main means for treating malignant tumors. High-precision delineation of a tumor radiotherapy target area, an organ-at-risk target area and the like is a precondition and a key technology for successful implementation of precise radiotherapy. In this process, automatic segmentation of the OAR (organs at risk) is an important critical step of the radiation therapy planning system. Before automatic segmentation, if the medical image to be outlined can be quickly given the position of the medical image to be outlined, the extra time brought by blindly calling all organ segmentation algorithms can be greatly reduced. For the automatic segmentation of tumors, by judging the human body part covered by the input medical image, the computer-aided diagnosis technology can provide better auxiliary diagnosis results by combining with the analysis and calculation of a computer through the iconography, the medical image processing technology and other possible physiological and biochemical means.
Therefore, it is very important to determine the human body part covered by the medical image. The part identification method commonly used in the medical image at present comprises the following steps: automatic identification based on DICOM header file information: the DICOM header file information causes difficulty in accurately identifying part information due to different standards of various devices or operators and has no guarantee; based on CT image gray value characteristic distribution method; a machine learning method based on two-dimensional Haar image features and an AdaBoost classifier comprises the following steps: and respectively carrying out piecewise linear distribution on labels of the head, neck, chest, lung and abdomen cavity of the human body according to a preselected key point, inputting the labels and the medical image into a neural network for training to obtain a pre-trained regression network, and determining the human body part covered by the medical image by using the regression network to realize the identification of the human body part covered in the medical image.
However, the conventional method for recognizing a human body part has the following problems: although the DICOM header information includes information of CT scanning sites, it is unreliable to identify the body sites to which the medical images belong through the DICOM header information due to modeling differences or scanning mode differences of different hospitals. 2, the method based on CT value image can only identify CT image, and can not identify MR; 3, the detection result is not high in precision and is easy to make mistakes. And 4, additional labeling is required, the classification is less, the single medical image cannot be accurately obtained, and the accurate positioning cannot be realized.
Based on this, it is necessary to provide a method for accurately positioning medical images based on organ encoding, aiming at the problems of the conventional technology.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a medical image accurate positioning method and system based on organ coding, which can accurately position each medical image by adopting a convolution neural network for training in a mode of coding each medical image and finally effectively perform effective segmentation or target area segmentation of organs.
In order to achieve the technical purpose, the invention provides the following technical scheme:
a medical image accurate positioning method based on organ coding comprises the following steps:
constructing an organ coding table and acquiring a medical image, and predicting the medical image through a trained organ coding model to obtain organ coding information, wherein the organ coding model is a deep learning model;
acquiring organ position information based on the organ code information and an organ code table, wherein the organ position information is used for realizing automatic segmentation of organs in the medical image.
Optionally, the obtaining process of the trained organ coding model includes:
acquiring a medical image training set, and training an organ coding model through the medical image training set to obtain a trained organ coding model, wherein the organ coding model is a convolutional neural network model, and the medical image training set comprises medical images used for training and organ coding information corresponding to the medical images used for training.
Optionally, before predicting the medical image by the trained organ coding model, the method further includes:
preprocessing the medical image to obtain a preprocessed medical image, and taking the preprocessed medical image as the input of a trained organ coding model;
wherein the medical image comprises a PET image, a PET/CT image, a PET/MRI image, an MRI image, a CT image and an SCT image; the preprocessing includes interpolation processing.
Optionally, the convolutional neural network model adopts a ResNet34-UNet model.
Optionally, the constructing process of the organ code table includes:
selecting a plurality of organs as coding elements, and sequencing the coding elements to obtain the organ coding table.
Optionally, the organ coding information is a sequence including 0 and 1, where the medical image includes an organ in the organ coding table, an organ position corresponding to the organ coding table in the organ coding information is marked as 1, and otherwise, a corresponding organ position is marked as 0.
In order to better achieve the technical object, the present invention further provides a medical image precise positioning system based on organ coding, comprising: the device comprises an acquisition module, a position module and a segmentation module;
the acquisition module is used for constructing an organ coding table, acquiring a medical image, and predicting the medical image through a trained organ coding model to obtain the organ coding information, wherein the organ coding model is a deep learning model;
the position module is used for acquiring organ position information based on the organ coding information and an organ coding table, wherein the organ position information is used for realizing automatic segmentation of organs in the medical image.
Optionally, the obtaining module includes a first obtaining module;
the first acquisition module is used for acquiring a medical image training set, and training an organ coding model through the medical image training set to obtain a trained organ coding model, wherein the organ coding model is a convolutional neural network model, and the medical image training set comprises medical images used for training and organ coding information corresponding to the medical images used for training.
Optionally, the acquiring module further includes a second acquiring module
The second acquisition module is used for preprocessing the medical image to obtain a preprocessed medical image, and the preprocessed medical image is used as the input of a trained organ coding model;
wherein the medical image comprises a PET image, a PET/CT image, a PET/MRI image, an MRI image, a CT image and an SCT image; the preprocessing includes interpolation processing.
Optionally, the obtaining module further includes a third obtaining module,
the third obtaining module is used for selecting a plurality of organs as coding elements and sequencing the coding elements to obtain the organ coding table.
The invention has the following technical effects:
the invention relates to an organ coding-based medical image accurate positioning algorithm, which is characterized in that compared with a traditional method for marking images according to part identification, each medical image can be accurately coded by using an organ coding mode, and then trained by using a convolutional neural network and adopting a current popular coding and decoding mode to obtain a trained network model for accurately positioning new medical images. The invention solves the problems that the traditional part recognition algorithm has low recognition rate and can not accurately obtain a single medical image by using an organ coding mode.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is an overall flowchart of a medical image accurate positioning method based on organ coding according to an embodiment of the present invention.
Fig. 2 is a schematic view of abdominal CT organ coding provided in the embodiment of the present invention.
Fig. 3 is a schematic view of organ coding of pelvic part CT according to an embodiment of the present invention.
Fig. 4 is a schematic view of a whole-body CT organ coding provided by the embodiment of the present invention.
Fig. 5 is a network structure diagram for accurately positioning medical images based on organ coding according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of an encoding module and a decoding module according to an embodiment of the present invention.
FIG. 7 shows CT encoded prediction results according to an embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
In order to solve the problems existing in the prior art, the invention provides the following scheme:
example one
As shown in fig. 1, the present invention provides a method for accurately positioning medical images based on organ coding, comprising:
acquiring a medical image to be identified, inputting the medical image into a trained organ coding model for prediction, and obtaining organ coding information;
acquiring the accurate position of the medical image according to the organ coding information and the organ coding table;
using the position information to achieve automatic organ segmentation or target segmentation;
the organ coding network model used, the training process is as follows: coding the medical image by using the organ code according to the task requirement, and acquiring coding information of a medical image training set as a label; image augmentation of tagged data; training the convolutional neural network; predicting by using the trained model;
for the purpose of making the present application more apparent in the technical solutions and advantages thereof, the present application is described in further detail below, with specific embodiments as follows:
acquiring a medical image to be identified, wherein the medical image comprises any one or more than two of a PET image, a PET/CT image, a PET/MRI image, an MRI image, a CT image and an SCT image; the method for acquiring the medical images is to directly connect with an imaging device to import the images, or export the medical images to a DICOM file (for example, export the CT images to the CT DICOM file, export the MRI images to the MRI DICOM file, export the PET images to the PET DICOM file, etc.) through a clinical PACS system of a hospital, and the DICOM file is opened to acquire the medical images of the sequence;
inputting the medical image into a trained organ coding model for prediction to obtain organ coding information; in this embodiment, the preprocessing includes interpolation processing, so that the resolution of the medical image after interpolation processing is the same as the resolution of the training image of the convolutional neural network model. In this embodiment, the convolutional neural network model adopts a convolutional neural network model based on deep learning, and in this embodiment, the convolutional neural network model adopts a ResNet34-UNet model;
acquiring the accurate position of the medical image according to the organ coding information and the organ coding table; and searching an organ coding table corresponding to the task according to the organ coding result predicted by the convolutional neural network, and corresponding the organ coding result to the lower part of the corresponding organ in the related organ coding table, so that accurate information of which organs are contained in each medical image at the position shot by the current medical image can be determined.
Using the position information to achieve automatic organ segmentation or target segmentation; according to the predicted organ information in each piece of medicine, guiding automatic organ segmentation or target area segmentation;
for the organ coding model used, the training process is as follows:
according to task requirements, organ coding is carried out on training data to serve as training labels; according to task requirements, selecting n required organs as coding elements, and sequencing the organs to generate a corresponding organ coding table. For each medical image, judging whether the medical image contains the organ, if so, marking the position of the organ as 1, and if not, marking the position of the organ as 0. According to the method, for each medical image, a corresponding n-bit 01 label can be obtained;
the label will be used for training; carrying out data augmentation processing on the training data; the data augmentation mode comprises operations of image scaling, rotation, shearing, noise addition, image enhancement, elastic deformation and the like, so that the generalization capability of the convolutional neural network model is enhanced.
Training by using a convolutional neural network; and inputting the training image after data enhancement into the convolutional neural network model for training to obtain the trained convolutional neural network model.
Predicting by using the trained model; taking abdominal organ delineation as an example, the task needs to delineate 9 organs, namely, skin, liver, left kidney, right kidney, bladder, rectum, left femoral head, right femoral head and spinal cord, of abdominal organs, sort the 9 organs, and sequentially encode each medical image; taking fig. 2 and fig. 3 as an example, each medical image generates a unique label, and these data are used as a training set to be trained by using a convolutional neural network, in this example, fig. 5 shows a network structure of ResNet34-Unet,
FIG. 6Encoder-Decoder layer description. The trained weights can be used to predict new medical images, and fig. 7 shows the prediction process for the final result using the prediction model.
Similarly, as shown in fig. 4, the present invention can be used to accurately locate medical images for any other part of the body.
Example two
In order to better achieve the technical object, the present invention further provides a medical image precise positioning system based on organ coding, comprising: the device comprises an acquisition module, a position module and a segmentation module;
the acquisition module is used for constructing an organ coding table, acquiring a medical image, and predicting the medical image through a trained organ coding model to obtain the organ coding information, wherein the organ coding model is a deep learning model;
the position module is used for acquiring organ position information based on the organ code information and an organ code table, wherein the organ position information is used for realizing automatic segmentation of organs in the medical image.
Optionally, the obtaining module includes a first obtaining module;
the first acquisition module is used for acquiring a medical image training set, and training an organ coding model through the medical image training set to obtain a trained organ coding model, wherein the organ coding model is a convolutional neural network model, and the medical image training set comprises medical images used for training and organ coding information corresponding to the medical images used for training.
Optionally, the acquiring module further includes a second acquiring module
The second acquisition module is used for preprocessing the medical image to obtain a preprocessed medical image, and the preprocessed medical image is used as the input of a trained organ coding model;
wherein the medical image comprises a PET image, a PET/CT image, a PET/MRI image, an MRI image, a CT image and an SCT image; the preprocessing includes interpolation processing.
Optionally, the obtaining module further includes a third obtaining module,
the third obtaining module is used for selecting a plurality of organs as coding elements and sequencing the coding elements to obtain the organ coding table.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A medical image accurate positioning method based on organ coding is characterized by comprising the following steps:
constructing an organ coding table and acquiring a medical image, and predicting the medical image through a trained organ coding model to obtain organ coding information, wherein the organ coding model is a deep learning model; ' Qiyi
Acquiring organ position information based on the organ code information and an organ code table, wherein the organ position information is used for realizing automatic segmentation of organs in the medical image.
2. The method for accurately positioning medical images based on organ coding according to claim 1, wherein:
the acquisition process of the trained organ coding model comprises the following steps:
acquiring a medical image training set, and training an organ coding model through the medical image training set to obtain a trained organ coding model, wherein the organ coding model is a convolutional neural network model, and the medical image training set comprises medical images used for training and organ coding information corresponding to the medical images used for training.
3. The method for accurately positioning medical images based on organ coding according to claim 1, wherein:
before predicting the medical image through the trained organ coding model, the method further comprises the following steps:
preprocessing the medical image to obtain a preprocessed medical image, and taking the preprocessed medical image as the input of a trained organ coding model;
wherein the medical image comprises a PET image, a PET/CT image, a PET/MRI image, an MRI image, a CT image and an SCT image; the preprocessing includes interpolation processing.
4. The method for accurately positioning medical images based on organ coding according to claim 2, wherein:
the convolutional neural network model uses the ResNet34-UNet model.
5. The method for accurately positioning medical images based on organ coding according to claim 1, wherein:
the construction process of the organ code table comprises the following steps:
selecting a plurality of organs as coding elements, and sequencing the coding elements to obtain the organ coding table.
6. The method for accurately positioning medical images based on organ coding according to claim 1, wherein:
the organ coding information is a sequence containing 0 and 1, wherein if the medical image contains the organ in the organ coding table, the organ position corresponding to the organ coding table in the organ coding information is marked as 1, otherwise, the corresponding organ position is marked as 0.
7. The positioning system based on the organ coding-based medical image precise positioning method of any one of claims 1-6, is characterized in that: the method comprises the following steps:
the device comprises an acquisition module, a position module and a segmentation module;
the acquisition module is used for constructing an organ coding table, acquiring a medical image, and predicting the medical image through a trained organ coding model to obtain the organ coding information, wherein the organ coding model is a deep learning model;
the position module is used for acquiring organ position information based on the organ code information and an organ code table, wherein the organ position information is used for realizing automatic segmentation of organs in the medical image.
8. The system for accurately positioning medical image based on organ coding according to claim 7, wherein:
the acquisition module comprises a first acquisition module;
the first acquisition module is used for acquiring a medical image training set, and training an organ coding model through the medical image training set to obtain a trained organ coding model, wherein the organ coding model is a convolutional neural network model, and the medical image training set comprises medical images used for training and organ coding information corresponding to the medical images used for training.
9. The system for accurately positioning medical image based on organ coding according to claim 7, wherein:
the acquisition module further comprises a second acquisition module;
the second acquisition module is used for preprocessing the medical image to obtain a preprocessed medical image, and the preprocessed medical image is used as the input of a trained organ coding model;
wherein the medical image comprises a PET image, a PET/CT image, a PET/MRI image, an MRI image, a CT image and an SCT image; the preprocessing includes interpolation processing.
10. The organ-coding-based medical image precise positioning system of claim 8, wherein:
the acquisition module further comprises a third acquisition module;
the third acquisition module is used for selecting a plurality of organs as coding elements and sequencing the coding elements to obtain the organ coding table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210349691.0A CN114663512B (en) | 2022-04-02 | 2022-04-02 | Medical image accurate positioning method and system based on organ coding |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210349691.0A CN114663512B (en) | 2022-04-02 | 2022-04-02 | Medical image accurate positioning method and system based on organ coding |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114663512A true CN114663512A (en) | 2022-06-24 |
| CN114663512B CN114663512B (en) | 2023-04-07 |
Family
ID=82034310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210349691.0A Active CN114663512B (en) | 2022-04-02 | 2022-04-02 | Medical image accurate positioning method and system based on organ coding |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114663512B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160210743A1 (en) * | 2015-01-20 | 2016-07-21 | Siemens Aktiengesellschaft | Method and computer and imaging apparatus for evaluating medical image data |
| US20170076451A1 (en) * | 2015-09-11 | 2017-03-16 | Siemens Healthcare Gmbh | Diagnostic system and diagnostic method |
| US20170193289A1 (en) * | 2015-12-31 | 2017-07-06 | Microsoft Technology Licensing, Llc | Transform lightweight skeleton and using inverse kinematics to produce articulate skeleton |
| CN109523556A (en) * | 2018-09-30 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | Vehicle part dividing method and device |
| CN111444686A (en) * | 2020-03-16 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Medical data labeling method, device, storage medium and computer equipment |
| CN113592857A (en) * | 2021-08-25 | 2021-11-02 | 桓由之 | Method for identifying, extracting and labeling graphic elements in medical image |
| US20210353260A1 (en) * | 2018-07-26 | 2021-11-18 | Koninklijke Philips N.V. | Ultrasound system with automated dynamic setting of imaging parameters based on organ detection |
| CN114092439A (en) * | 2021-11-18 | 2022-02-25 | 深圳大学 | Multi-organ instance segmentation method and system |
-
2022
- 2022-04-02 CN CN202210349691.0A patent/CN114663512B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160210743A1 (en) * | 2015-01-20 | 2016-07-21 | Siemens Aktiengesellschaft | Method and computer and imaging apparatus for evaluating medical image data |
| US20170076451A1 (en) * | 2015-09-11 | 2017-03-16 | Siemens Healthcare Gmbh | Diagnostic system and diagnostic method |
| US20170193289A1 (en) * | 2015-12-31 | 2017-07-06 | Microsoft Technology Licensing, Llc | Transform lightweight skeleton and using inverse kinematics to produce articulate skeleton |
| US20210353260A1 (en) * | 2018-07-26 | 2021-11-18 | Koninklijke Philips N.V. | Ultrasound system with automated dynamic setting of imaging parameters based on organ detection |
| CN109523556A (en) * | 2018-09-30 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | Vehicle part dividing method and device |
| CN111444686A (en) * | 2020-03-16 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Medical data labeling method, device, storage medium and computer equipment |
| CN113592857A (en) * | 2021-08-25 | 2021-11-02 | 桓由之 | Method for identifying, extracting and labeling graphic elements in medical image |
| CN114092439A (en) * | 2021-11-18 | 2022-02-25 | 深圳大学 | Multi-organ instance segmentation method and system |
Non-Patent Citations (2)
| Title |
|---|
| BO CHENG等: ""Robust multi-label transfer feature learning for early diagnosis of Alzheimer"s disease"", 《BRAIN IMAGING AND BEHAVIOR》 * |
| 孟祥海: ""基于改进Unet的脑腹部多模态影像分割"", 《中国优秀硕士学位论文全文数据库·医药卫生科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114663512B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11386557B2 (en) | Systems and methods for segmentation of intra-patient medical images | |
| CN108778416B (en) | Systems, methods, and media for pseudo-CT generation from MR data using tissue parameter estimation | |
| CN108770373B (en) | pseudo-CT generation from MR data using a feature regression model | |
| Chen et al. | Fast and accurate craniomaxillofacial landmark detection via 3D faster R-CNN | |
| CN112365980B (en) | Brain tumor multi-target auxiliary diagnosis and prospective treatment evolution visualization method and system | |
| Peng et al. | Segmentation of lung in chest radiographs using hull and closed polygonal line method | |
| CN110689521B (en) | Automatic identification method and system for human body part to which medical image belongs | |
| Kim et al. | Automation of spine curve assessment in frontal radiographs using deep learning of vertebral-tilt vector | |
| Huang et al. | Mtl-abs 3 net: Atlas-based semi-supervised organ segmentation network with multi-task learning for medical images | |
| CN115063397A (en) | Computer-aided image analysis method, computer device and storage medium | |
| CN114663512B (en) | Medical image accurate positioning method and system based on organ coding | |
| Hong et al. | A distance transformation deep forest framework with hybrid-feature fusion for cxr image classification | |
| Yang et al. | Automatic segmentation of head-neck organs by Multi-mode CNNs for radiation therapy | |
| CN116485853A (en) | Medical image registration method and device based on deep learning neural network | |
| Zhang et al. | Fully convolutional network-based multi-output model for automatic segmentation of organs at risk in thorax | |
| Kim et al. | Longitudinal brain MR image modeling using personalized memory for alzheimer’s disease | |
| Dréan et al. | Inter-individual organ-driven CT registration for dose mapping in prostate cancer radiotherapy | |
| Soh et al. | HUT: Hybrid UNet transformer for brain lesion and tumour segmentation | |
| Alshamrani et al. | Automation of Cephalometrics Using Machine Learning Methods | |
| CN113823382A (en) | Method and device for analyzing hematopoietic side effects of tumor radiotherapy | |
| Su et al. | Prioritization of liver MRI for distinguishing focal lesions | |
| CN115148341B (en) | AI structure sketching method and system based on body position recognition | |
| Fajar et al. | Cephalometric Landmark Detection on Cephalograms using Regression CNN | |
| Liu et al. | Few-shot learning for auromatic intracranial hematoma segmentation | |
| Sallam | Deep Structure Base On Convolutional Neural Networks For Identificatio Of Chest Diesases |
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 |