Assoc. Prof. Dr. Jude Hemanth (Karunya University, India)
Artificial Intelligence techniques such as Artificial Neural Networks (ANN) and Fuzzy logic theory have gained significant attraction from all domains of practical applications. One of the prime application areas is the medical field in which medical image processing needs the assistance of AI based approaches for better performance of the system. The performance of the AI based medical image analysis approaches are judged based on the accuracy and convergence rate (time requirement). However, the million dollar question is whether the conventional AI based systems can satisfy both these performance measures in the same single approach. The answer is a big NO which clearly reveals the scope of improvement in the conventional AI based medical image processing approaches.
In this talk, I propose several innovative ANN and fuzzy based approaches for medical image analysis. The innovative ANN and fuzzy based approaches are developed by performing suitable modifications in the training algorithms and architecture of conventional ANN and fuzzy approaches. The efficiency of the proposed approach is explored in the context of abnormality detection in Magnetic Resonance (MR) brain tumor images. The algorithms will be clearly detailed along with the case study based on my research work.
This talk will definitely trigger a spark in the minds of young researchers working/beginning to work in the area of AI to develop an innovative system on their own. This talk also will serve as an ideal platform for a newcomer to understand the interesting aspects of AI towards medical perspective.