Method and device for identifying brain atrophy

Abstract

The embodiment of the invention provides a method and device for identifying brain atrophy, and relates to the technical field of artificial intelligence, and the method comprises the steps: determining a key frame in a brain image sequence through employing a key frame detection module, detecting key points in the key frame through employing a key point detection module, and determining a first classification index according to the key points in the key frame; segmenting the key frame by adopting an image segmentation module, and determining a second classification index; identifying the brain atrophy according to the first classification index and the second classification index. Different detection modes are adopted according to the characteristics of different classification indexes, so that the detection precision of the classification indexes is improved; the first classification index and the second classification index are used for identifying the brain atrophy, and the accuracy of identifying the brain atrophy is also improved. Secondly, the neural network model is adopted to automatically identify the brain atrophy, and compared with manual measurement and calculation, the artificial dependence is small and the efficiency is high.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of artificial intelligence, and in particular to methods and devices for identifying brain atrophy. Background technique [0002] Cerebral atrophy is an imaging manifestation of organic lesions in the brain tissue that reduces its volume compared to normal. It can be caused by genetics, neurological diseases, poisoning, malnutrition and other factors. Among them, the most common is atrophy of the cerebral cortex, which can be seen as flattening of the brain gyrus, widening of the brain sulci, enlargement of the ventricles and brain cisterns, and weight loss of the brain. In severe cases, it will develop into dementia, language barriers, and loss of intelligence. About 15 million people die from various diseases related to brain atrophy every year in the world, and the death rate is increasing year by year. Brain atrophy-related diseases usually have a long course of disease and slow o...

AI Technical Summary

Problems solved by technology

[0004] Since the current method for diagnosing brain atrophy based on imaging relies on manual measurement and calculation by doctors, which is highly subjective and inefficient, the embodiment of the present invention provides a method and device for identifying brain atrophy

Images