Deep fusion learning-based child brain MRI demyelination auxiliary analysis method

Abstract

The invention discloses a deep fusion learning-based child brain MRI demyelination auxiliary analysis method. The method comprises the following steps of: firstly, preprocessing child demyelination disease data and constructing a data set; designing a deep fusion learning demyelination disease auxiliary model; training the deep fusion learning demyelinating disease auxiliary model through the constructed child demyelinating disease data set; and finally, completing acquisition and feature classification of a high-signal white matter segmentation image through the trained deep fusion learning demyelination disease auxiliary model, and displaying the high-signal white matter segmentation image and a feature classification label through a visual result model. The method provided by the invention not only can assist doctors in clinical diagnosis, but also can greatly improve the rate of image annotation, so that the definite diagnosis time and definite diagnosis cost of patients are greatly shortened and reduced, the patients can be treated in time, neurological function defects left in the prognosis process of the patients are relieved, and a better prognosis effect is obtained.

Description

technical field [0001] The invention belongs to deep learning, computer vision, medical image segmentation and medical image classification, and specifically relates to an auxiliary analysis method for children's brain MRI demyelination by deep fusion learning. Background technique [0002] Central Nervous System Demyelinating Diseases (Central Nervous System Demyelinating Diseases) is a group of diseases characterized by destruction or demyelination of the myelin sheath of the brain and spinal cord, mostly in children and adolescents. The pathological mechanism of demyelinating diseases of the central nervous system is related to the widespread demyelinating lesions caused by white matter damage. Lesions in the white matter of the brain, spinal cord and brainstem, cerebellum and optic neurons are the main causes of clinical symptoms and neurological signs in patients. High incidence of disease and many sequelae. Multiple sclerosis (MS), acute disseminated encephalomyelitis...

AI Technical Summary

Problems solved by technology

The importance of different tissue regions cannot be weighed in separate segmentation-based methods

On the other hand, a single classification method cannot provide pixel-level information, that is, the specific size and scope of the lesion in the image cannot be obtained.

Images