Brain tumor multi-target auxiliary diagnosis and prospective treatment evolution visualization method and system

Abstract

The invention provides a brain tumor multi-target auxiliary diagnosis and prospective treatment evolution visualization method and system. The brain tumor multi-target auxiliary diagnosis and prospective treatment evolution visualization method comprises the steps: acquiring and preprocessing paired brain tumor multi-target multi-mode MRI data before and after treatment; carrying out tumor regionsegmentation on the preprocessed paired brain tumor multi-target multi-mode MRI data before and after treatment through a 3DU-net convolutional neural network, and obtaining a growth characteristic label L = {l1, l2, l3,..., ln} through an imaging omics method; and performing feature extraction on the sum through a multi-channel convolutional neural network and then performing SE fusion operationto obtain deep learning features and input the deep learning features into a prediction model to obtain a brain tumor multi-target growth prediction label, inputting the brain tumor multi-target growth prediction label into a trained prospective treatment visualization model to obtain a final brain tumor region-of-interest growth evolution image, and inserting the brain tumor region-of-interest growth evolution image into a non-brain tumor region Ibackground to complete a brain tumor prospective treatment visualization task. The method and system in the invention has higher clinical practicability.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a method and system for visualization of multi-target auxiliary diagnosis and prospective treatment evolution of brain tumors. Background technique [0002] Brain tumors are common tumors in the human body. Central neurologists use information such as multimodal magnetic resonance imaging (MRI) of the patient's brain to diagnose the patient's illness. At present, the gold standard for accurate diagnosis of brain tumors is still histopathological examination and genetic testing, but tumor biopsy is an invasive operation, the operation risk is high, and it cannot accurately reflect the internal heterogeneity of tumor tissue; in the era of medical digitalization , Computer Assisted Diagnosis (CAD) technology can combine multimodal MRI images of the brain (including: T1-weighted imaging (T1), T1-weighted enhanced imaging (T1C), T2-weighted imaging (T2), water...

AI Technical Summary

Problems solved by technology

[0004] Although these models play a certain role in promoting the assistance of brain tumors, these models have certain deficiencies: (a) problems such as insufficient data lead to fewer researches on auxiliary diagnosis based on multi-disease classification, and the classification results are poor; ( b) There is a lack of multi-target therapy evaluation model; (c) Compared with the current CAD system for brain tumors, most auxiliary diagnosis systems only focus on auxiliary diagnosis, while the auxiliary treatment system only conducts retrospective digital quantitative evaluation, and cannot pre-treatment Perform prospective visual efficacy assessment

Images