Tumor type determination system and method and storage medium
A tumor and type technology, applied in the field of medical image processing, can solve the problem of low accuracy of tumor type determination methods
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] figure 1 It is a structural block diagram of the medical image analysis system provided by Embodiment 1 of the present invention. The system includes an acquisition module 11 and a tumor type determination module 12, the acquisition module 11 is used to acquire one or more sets of medical image data to be analyzed of the subject; the tumor type determination module 12 is used to input the medical image data to be analyzed into the trained In the tumor classification model, to determine the tumor type of the lesions contained in the medical image data to be analyzed.
[0037] The acquiring module 11 can acquire the medical image data to be analyzed through network communication transmission, copying and other means. Among them, the type of medical imaging data to be analyzed is the type of medical imaging data commonly used in clinical tumor diagnosis, such as MRI, CT, PET-CT (Positron Emission Computed Tomography-Computed Tomography, Positron Emission Computed Tomograp...
Embodiment 2
[0048] Figure 6 It is a flow chart of the method for determining the tumor type provided by the second embodiment of the present invention. The technical solution of this embodiment is applicable to the situation where tumor types are automatically determined according to one or more sets of medical image data to be analyzed. The method can be executed by the device for determining the tumor type provided by the embodiment of the present invention, the device can be implemented in the form of software and / or hardware, and configured to be applied in a medical imaging system. The method specifically includes the following steps:
[0049] S101. Acquire one or more sets of medical image data of a subject to be analyzed.
[0050] Among them, the type of medical image data to be analyzed is the type of medical image data commonly used in clinical tumor diagnosis, such as MRI, CT, PET-CT, etc. If there are multiple groups of medical image data to be analyzed of the subject, the ...
Embodiment 3
[0061] Figure 7 It is a flow chart of the tumor classification model training method provided in Embodiment 3 of the present invention. On the basis of the above-mentioned embodiments, the embodiment of the present invention adds the steps of the tumor classification model training method, including:
[0062] S201. Obtain a preset number of medical image data of subjects to be analyzed, and perform tumor type identification on the medical image data of each subject to be analyzed, so as to create a training set sample for training a tumor classification model.
[0063] Exemplarily, the training set used to train the tumor classification model in this embodiment includes 336 samples, each sample includes two sets of magnetic resonance images of a subject, and these two sets of magnetic resonance images are T1-weighted magnetic resonance images and T2-weighted magnetic resonance image. The tumor type is identified for each set of magnetic resonance images of each subject, for...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


