Computer-aided detection system for cerebral microbleeds based on magnetic resonance images

Abstract

The invention provides a magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system and belongs to the medical image computer auxiliary detection field. The magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system comprises five portions of an image import module, an image preprocessing module, a characteristic extraction module, an automatic detection module and a cerebral micro-bleeding automatic detection report output module. According to the magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system, the characteristics of T1, T2 and GRET2* images are comprehensively considered, the prior information of the cerebral micro-bleeding of different cerebral positions is obtained through a cerebral micro-bleeding focus prior distribution probability template, and a random forest classifier is combined to perform the automatic detection on the cerebral micro-bleeding focus; the system sensitivity is 0.890 and every case comprises 1.530 false positive focuses in average through a test; the magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system is objective and high in repeatability in comparison with the traditional manual discriminant method and the magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system is accurate and reliable in comparison with the existing computer auxiliary detection method; the operation is simple and convenient, the identification result of the cerebral micro-bleeding focus can be objectively provided, and meanwhile the abundant information is provided for the reference of doctors.

Description

technical field [0001] The invention belongs to the field of computer-aided detection of medical images, and specifically relates to a brain detection system based on texture features of regions of interest in magnetic resonance images (brain parenchyma regions in images), prior distribution probability templates of cerebral microbleeds, and random forest classifiers. Microbleed computer-aided detection system. Background technique [0002] Cerebral microhemorrhage is a kind of subclinical damage of brain parenchyma caused by microvascular disease in the brain and characterized by microhemorrhage. In recent years, the improved detection rate of cerebral microbleeds by new magnetic resonance imaging sequences has further deepened our understanding of cerebral microbleeds. Cerebral microbleeds are common in patients with ischemic stroke or intracranial hemorrhage, and are also common in the elderly. How their appearance affects the prognosis of the disease, and whether their...

AI Technical Summary

Problems solved by technology

[0013] However, the currently known computer-aided detection methods for cerebral microbleeds do not fully consider the information complementarity between different sequence images, and the multi-dimensional image features of cerebral microbleeds need to be further explored.

In addition, all known computer-aided detection methods do not consider the important location information of the prior distribution probability density of cerebral microbleeds

At present, none of the existing methods can achieve automatic identification, and a large number of false positive test results have to be eliminated through manual intervention, and its sensitivity and specificity need to be further improved

Images