We are glad to announce that Ramakrishna Mission Vivekananda Educational and Research Institute (RKMVERI) will be conducting a special colloquium on “AIDIAS: Artificial Intelligence based Diagnostic and Analytical Systems” on 03 Nov 2023, 12 noon at Seminar Hall, Narendrapur Campus.

Speaker : Dr. Saikat Chakrabarti, Professor & Senior Principal Scientist, CSIR-IICB, Kolkata
Co-ordinator: Prof. Abhijit Chakrabarti

Abstract

Artificial intelligence is a technology using which we can create intelligent systems that can simulate human intelligence whereas machine learning is a subfield of artificial intelligence, which enables machines to learn from past data or experiences without being explicitly programmed. These are two related technologies and sometimes people use them as a synonym for each other. Machine learning (ML) and deep learning (DL) are two very critical components for development of an artificial intelligent system/apparatus. ML and DL are software and algorithms that need to be trained with existing data and information so that it can identify/predict and/or distinguish the categories for which they have been trained. However, based on the training and prediction if the system can take independent decisions related to the outcome of the prediction then it can be qualified as artificial intelligent system.

In our laboratory we developed image processing and deep learning based methods for automatic detection and clinical outcome prediction of haemorrhagic stroke regions from brain computer tomography (CT) images and automatic detection of Alzheimer’s disease (AD) and other dementias using magnetic resonance image (MRI) scans. In this talk, I will briefly discuss about the systems that are capable of detection of a disease (stroke/AD) status from brain CT/MRI images without any manual intervention.

Further, we will also talk about potential of ML in identification of biomarker and correct molecular interaction pattern/pose for protein-protein and protein-small molecule interactions. Identification of novel biomarker and correct protein-protein and protein-small molecule interaction is very critical for drug development protocols. Hence, our approach and algorithms will be quite useful for new drug target and drug discovery initiatives.