A mining method based on uncertain brain image data

Abstract

The invention realizes a mining method based on uncertain brain image data through the method in the field of artificial intelligence. Radial diffusion coefficient image; use the probabilistic fiber bundle tracking algorithm PICo to extract nerve fiber bundles from anisotropic images; perform image registration of each image with the standard Desikan‑Killiany template, and convert nerve fiber bundles accordingly; After the image and nerve fiber bundles, the nerve fiber strength, geometric features and diffusion tensor features are extracted; the data quality assessment algorithm is designed to evaluate and filter the quality of the feature data; Image processing and analysis, eliminate the impact of data uncertainty on analysis, and combine statistical testing and machine learning algorithms to perform data mining and detection of image features required.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a mining method based on uncertain brain image data. Background technique [0002] The human brain can be divided into many functional regions that are intricately connected and cooperate to accomplish cognitive tasks. For a long time, researchers lacked effective brain quantification methods. It was only in recent decades, with the development of medical imaging technology, such as magnetic resonance imaging, that humans had better means of measuring and quantifying the brain. [0003] In the field of neuroscience, it is of great clinical value to analyze human brain network structure and detect disease-related biomarkers based on brain imaging data, such as MRI images. Although medical imaging technology and brain network reconstruction technology are relatively mature, the data obtained by these technologies are actually quite uncertain. Data uncertainty generally ref...

AI Technical Summary

Problems solved by technology

However, these techniques lack effective means to measure and deal with data uncertainty

Secondly, most of the research objects of existing research methods focus on a single brain network feature, such as nerve fiber strength, and do not support other important features known in the field, such as tensor field diffusion characteristics

Images