MEDICAL IMAGE ENHANCEMENT THROUGH DEEP LEARNING METHODS

摘要

In recent years, machine learning algorithms are commonly used in the field of digital image processing for interpreting images based on domain specific knowledge in terms of different aspects like image classification, object/pattern recognition, clinical image diagnosing, traffic control systems, satellite imaging, geomorphological and agriculture sectors etc. to analyse ROI from large amount of captured electronic images via different modalities. Machine Learning (ML) is an outlet of Artificial Intelligence (AI). It has ability to learn by itself without any extra effort like explicit programming. In this paper, we will deliberate the emerged expanse of ML - Deep Learning (DL) which is basically a group of concepts with high level of data abstraction. Its application areas are especially analytical study of medical images such as anatomical structure detection, image registration and enhancement, computer aided disease diagnosis, tissue segmentation, and so on. DL based architecture provides exhilarating results with moral accuracy and enhanced performance for medical image segmentation and classification.