Automatic System for Classification and Segmentation of Brain Abnormalities using Deep Learning

Loading...
Thumbnail Image

Date

item.page.authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Brain diseases and tumors are challenging to diagnose and treat. They can appear in a variety of forms, including benign growths to malignant tumors, and can impair neurological functions with severe consequences. Early detection is crucial for successful treatment and management because it allows timely intervention to prevent potential complications. This process relies heavily on diagnostic modalities, with imaging techniques assisting in identifying and characterizing neurological abnormalities. The abnormalities can be diagnosed employing a variety of imaging techniques, such as functional magnetic resonance imaging (fMRI), positron emission tomography scan (PET), magnetic resonance imaging (MRI), computed tomography (CT) scanning, etc. CT scans and MRIs are commonly utilized due to their accessibility and cost-effectiveness. Early diagnosis of brain diseases and tumors makes timely treatment and intervention possible, contributing to significant improvements in patient outcomes. Deep learning and artificial intelligence (AI) technologies have emerged as effective methods for medical imaging analysis, including detecting, diagnosing, and segmenting brain diseases and tumors. Several notable literature gaps in medical imaging classification research need to be addressed and resolved. Traditional classification approaches frequently suffer from limitations that restrict their ability to diagnose and distinguish between multiple types of conditions accurately. These constraints are primarily due to challenges such as feature extraction, image quality variability, results interpretability, and scalability to handle large datasets. The traditional classification methods reliance on manually generated features represents a significant gap. These features are frequently created using domain knowledge and human expertise, which might only capture some of the complex patterns found in medical images.

Description

Keywords

Citation

item.page.endorsement

item.page.review

item.page.supplemented

item.page.referenced