Cancer survival analysis system based on multiple tasks and multiple modes

Abstract

The invention discloses a cancer survival analysis system based on multiple tasks and multiple modes, and the system comprises a data importing module which comprises a data loading module and a data preprocessing module; a system training module, comprising a representation learning module, a multi-omics and pathological map fusion module, a multi-task prediction module and a loss function module; and a system prediction module, used for carrying out survival analysis and grading according to the multi-omics data and the pathological map of the cancer patient. According to the invention, the deep learning technology and the multi-task learning technology are combined with the multi-omics and pathological map data, so that the complementary characteristics among the multi-modal data can be captured, and the sharing relevance among multiple tasks can also be captured, thereby forming a cancer survival analysis system based on multiple tasks and multiple modalities, and providing automatic survival analysis and cancer grading results.

Description

technical field [0001] The invention relates to the technical field of cancer survival analysis and grading, in particular to a multi-task and multi-modal cancer survival analysis system. Background technique [0002] With the development of next-generation sequencing technology, it is more and more convenient to obtain patient omics data, such as genomics, transcriptomics, proteomics, epigenomics and other multi-omics data. Different omics is a description of patients at different molecular levels. The fusion of multiple omics can better understand the patient's disease development status, thereby providing more accurate and efficient diagnosis and prognosis results. Imaging data has been widely used to analyze the condition of cancer patients. With the development of imaging technology and computer technology in recent decades, pathological pictures are stored in electronic devices through various tools and technologies, making it possible to read patient pathological pic...

AI Technical Summary

Problems solved by technology

Now radiogenomics has expanded from the scope of cancer to mental diseases such as Alzheimer's disease and schizophrenia, but it is still difficult to integrate highly heterogeneous data such as multi-omics data and pathological maps;

Images