PET molecular imaging computer-aided diagnosis system based on brain symmetry

Abstract

The invention discloses a PET molecular image computer-aided diagnosis system based on brain symmetry. The system comprises an image acquisition and preprocessing module, an asymmetric brain template construction module, a symmetric brain template construction module, a symmetry analysis module and an auxiliary diagnosis module. According to the system, an asymmetric brain template is constructed according to a normal brain PET molecular image, and a symmetric brain template is further constructed; then, registering individual images to a symmetric brain template space to obtain priori knowledge of a symmetric structure, and introducing individual image information by using a symmetric differential homeomorphic algorithm to obtain a voxel-level brain structure symmetric relationship; finally, metabolism or receptor information of the focus area and the symmetrical brain area of the focus area is comprehensively utilized, and the diagnosis capacity of the PET molecular image is improved in an auxiliary mode.

Description

technical field [0001] The invention belongs to the technical field of computer-aided diagnosis of medical images, in particular to a computer-aided diagnosis system and method for PET molecular images based on brain symmetry. Background technique [0002] Positron emission tomography (PET) is a molecular imaging technique that can visualize molecular metabolism, receptors and neurotransmitter activities in vivo, and has been widely used in the diagnosis, differential diagnosis and disease assessment of various neurological diseases and efficacy evaluation. E.g, 18 Fluoro-fluorodeoxyglucose ( 18 F-FDG)PET can detect the abnormal brain glucose metabolism caused by the disease, and has become a routine imaging examination method for the diagnosis of glioma and the preoperative evaluation of refractory epilepsy; 11 C-2β-methyl ester-3β-(4-fluorophenyl)tropane ( 11 C-CFT) PET can visualize the distribution of dopamine transporters in the brain, which is of great value in the...

AI Technical Summary

Problems solved by technology

The current computer-aided diagnosis system for PET molecular imaging includes: 1) ROI analysis, which obtains the standard uptake value (SUV) of symmetrical brain regions through manual drawing or atlas of physicians. According to the asymmetry index (AI) of SUV ) for diagnosis, which has high stability but poor sensitivity; 2) Voxel-based statistics, by comparing the SUV or standard uptake rate (SUVR) of patients and healthy people voxel-by-voxel Differential diagnosis of lesions, which is highly sensitive but ignores valuable information about symmetry of brain uptake

Images