Prof. (Dr.) Debotosh Bhattacharjee

Title: Medical Image Analysis for Computer-Assisted Diagnosis System

Abstract: During the last few decades, there is a steady study on diagnostic approaches from invasive technology to non-invasive sensing technology. Non-invasive medical imaging is basically a technique to visualize the organs physiology beneath the skin surface without any physical contact with the patient. Non-invasive medical imaging technology has gained much attention and emerged as a promising tool to assist clinicians for early screening, diagnostic and monitoring purposes. Early detection of disease plays a crucial role in the successful rehabilitation of the patient.

Traditionally the task of diagnosis of cancer is laid on the shoulders of the pathologists. This process of manual inspection is highly dependent on the expertise of the pathologists and are time-consuming since it requires more laboratory work. This necessitates the use of computer-assisted diagnosis (CAD) system based on analysis of images for accurate cancer prediction. However, the accuracy of detection solely depends on the sensitivity of the imaging modality. The images from the various modalities are much more complex to understand because of their irregular shape, structure, artifact and unwanted noise. So, call of the hour is to develop some high-level image processing techniques to detect the presence of abnormalities in the images. Basically, analysis of the images starts with some low-level operations like de-noising, manual cropping of unwanted regions and image enhancement which are followed by segmentation of the discriminative affected areas from the whole image. Segmentation of the abnormal regions is a classical problem in medical image analysis, where minor variation between segmented regions and the actual anatomy can lead to misdiagnosis of the patients. Mainly segmentation and classification both are accomplished through feature-based approaches. Features may be handcrafted or learned, but both have their own merits and demerits. Handcrafted features can be handled by low resource, few training samples but require domain knowledge. However, learned features need a large number of training samples, high power computing facility but with almost no domain knowledge. So far accuracy is concerned, it depends on the availability of training samples, computing resources, and domain knowledge.

Short Bio: Debotosh Bhattacharjee (SM ’11) received the Master of Computer Science and Engineering and the Ph. D(Engineering) degrees from Jadavpur University, India, in 1997 and 2004 respectively.  He was associated with different institutes in various capacities until March 2007. After that, he joined his Alma Mater, Jadavpur University as a Reader in the Department of Computer Science and Engineering. Currently, he is working as a full professor in the same department. He has successfully discharged the duties of coordinating an evening master’s course, M. Tech. in Computer Technology from August 2008 to August 2016.

His research interests pertain to the applications of machine learning techniques for Face Recognition, Gait Analysis, Hand Geometry Recognition, and Diagnostic Image Analysis. He has authored or coauthored more than 250 journals, conference publications, including several book chapters in the areas of Biometrics and Medical Image Processing.  Two US patents have been granted on his works.

Prof. Bhattacharjee has been granted sponsored projects by the Govt. of India funding agencies like Department of Biotechnology(DBT), Department of Electronics and Information Technology (DeitY), University Grants Commission(UGC) with a total amount of around `2 Crore.

For postdoctoral research, Dr. Bhattacharjee has visited different universities abroad like the University of Twente, The Netherlands;  Instituto Superior Técnico, Lisbon, Portugal; University of Bologna, Italy; ITMO National Research University, St. Petersburg, Russia; University of Ljubljana, Slovenia; Northumbria University, Newcastle Upon Tyne, UK and Heidelberg University, Germany.

He is a life member of Indian Society for Technical Education (ISTE, New Delhi), Indian Unit for Pattern Recognition and Artificial Intelligence (IUPRAI), and a senior member of IEEE (USA).

Full Professor, Department of Computer Science and Engineering, Jadavpur University, India
Jadavpur University, Kolkata, India