Medical Visual Question Answering System

Abstract

Medical imaging is getting a lot of attention in the field of artificial intelligence. Medical image classification is one of the most significant challenges in image recognition. Medical image segmentation is also getting a lot of attention in which the desired organ is segmented. Medical image segmentation helps in the identification of tumours growth and many other diseases. The limitation which motivated us to pursue this field was the lack of interaction with images. If doctors could interact with medical images and just focus on some specific things they are seeking in medical images underdiagnoses would be astonishing. Medical Visual Question Answering System is the domain of Artificial Intelligence which involves computer vision and natural language processing. It is a great contribution to the medical domain focused towards the field of radiology. Our Medical Visual Question Answering System is capable of getting medical images as input from the user along with the clinically relevant questions related to the image and provides the user with the clinically relevant answer. The accuracy achieved by our model is satisfactory