Demyelinating and ischemic brain diseases: detection algorithm through regular magnetic resonance images

Abstract

This work presents the advance to development of an algorithm for automatic detection of demyelinating lesions and cerebral ischemia through magnetic resonance images, which have contributed in paramount importance in the diagnosis of brain diseases. The sequences of images to be used are T1, T2, and FLAIR. Brain demyelination lesions occur due to damage of the myelin layer of nerve fibers; and therefore this deterioration is the cause of serious pathologies such as multiple sclerosis (MS), leukodystrophy, disseminated acute encephalomyelitis. Cerebral or cerebrovascular ischemia is the interruption of the blood supply to the brain, thus interrupting; the flow of oxygen and nutrients needed to maintain the functioning of brain cells. The algorithm allows the differentiation between these lesions.

MR Images, Brain Lesions, and Deep Learning

“…Hence, neuroimaging plays a fundamental role in understanding how the brain and the nervous system function [3] and discover how structural or functional anatomical alteration is correlated with different neurological disorders [4] and brain lesions. Currently, research on artificial intelligence (AI) and diverse techniques of imaging constitutes a crucial tool for studying the brain [5][6][7][8][9][10][11] and aids the physician to optimize the time-consuming tasks of detection and segmentation of brain anomalies [12] and also to better interpret brain images [13] and analyze complex brain imaging data [14].…”

“…There are three types of ischemic stroke according to the Bamford clinical classification system [24]: (1) partial anterior circulation syndrome (PACS), where the middle/anterior cerebral regions are affected; (2) lacunar anterior circulation syndrome (LACS), where the occlusion is present in vessels that provide blood to the deep-brain regions; and (3) total anterior circulation stroke (TACS), when middle/anterior cerebral regions are affected due to a massive brain stroke [24,25]. Ischemic stroke is a common cerebrovascular disease [1,26,27] and one of the principal causes of death and disability in low-and middle-income countries [1,4,6,7,[27][28][29]. In developed countries, brain ischemia is responsible for 75-80% of strokes, and 10-15% are attributed to a hemorrhagic brain stroke [4,25].…”

“…A demyelination disease is described as the loss of myelin with relative preservation of axons [8,22,29]. Love [22] notes that there are demyelinating diseases in which axonal degeneration occurs first and the degradation of myelin is secondary [7,22]. Accurate diagnosis classifies the demyelinating diseases of the central nervous system (CNS) according to the pathogenesis into "demyelination due to inflammatory processes, demyelination caused by developed metabolic disorders, viral demyelination, hypoxic-ischemic forms of demyelination and demyelination produced by focal compression" [22].…”

Magnetic resonance brain images algorithm to identify demyelinating and ischemic diseases

“…Thus, several MRI images provided by the Universidad Técnica Particular de Loja Hospital (H-UTPL), in Ecuador show evidence that their patients suffer brain disorders, and many of them pathologies identified as demyelinating (BD) and ischemia (BI) 3 . For that reason, there is an increasing and still unmet need for an even better classification between BD and BI, in order to derive better understanding, classification and assessment of disease progression and treatment therapeutic efficacy.…”

“…Thereby, this paper presents the results of a classification algorithm processing images 3 . Whose main objective is identifying and differentiate between demyelination and ischemic brain diseases, through the automatic detection, classification and identification of their features found in the MRI.…”