Dr. Taufiq Hasan of Bangladesh University of Engineering and Technology (BUET)

Chest radiography is one of the most frequently performed medical imaging examinations globally. However, there is a significant shortage of expert radiologists, especially in low- and middle-income countries (LMICs). Artificial Intelligence (AI) based automatic analysis of X-ray images and medical imaging modalities has thus been a critical area of research and innovation in recent times. However, traditional deep learning-based X-ray image analysis is faced with several challenges. This talk highlights the following three key challenges and discusses our novel solutions. (i) Deep learning model performance degrades due to the variability of X-ray images collected from different source domains. (ii) Traditional models do not have explicit knowledge about human anatomical structures within the images, which is vital for accurate disease diagnosis. (iii) Radiographic projection creates superimposed images with overlapping anatomical structures that are difficult to disentangle. The talk will present our recent research findings and algorithmic advances addressing these three challenges. Proposed algorithms are evaluated and compared to state-of-the-art methods. Experimental evaluations were conducted using well-known benchmark data sources, including the NIH, MIMIC, and Stanford CheXpert. The talk will conclude with a discussion on possible future directions in this area to further improve the automatic analysis of X-ray images.

Biography:

Dr. Taufiq Hasan (Senior Member, IEEE) completed his BSc. and MSc. in Electrical and Electronic Engineering (EEE) from Bangladesh University of Engineering and Technology (BUET) and his Ph.D. in Electrical Engineering from the University of Texas at Dallas (UTD). He worked as a Research Scientist at the Robert Bosch Research and Technology Center, Palo Alto, CA. Dr. Hasan is currently an Associate Professor of the Department of Biomedical Engineering at BUET, where he leads the mHealth research group. He co-invented the OxyJet CPAP, a low-cost, non-invasive ventilator device for hypoxemic COVID-19 patients, which was the first medical device designed, developed, and regulatory approved in Bangladesh. He holds 20+ peer-reviewed research papers and several US patents/patent applications. His research interests include biomedical signal and medical image analysis using deep learning, and innovative medical device design for low-resource healthcare settings.

Dr. Hasan is also an adjunct faculty member at the Center for Bioengineering Innovation and Design (CBID), Johns Hopkins University, Baltimore, MD.

Email:

Address:Bangladesh University of Engineering and Technology, Dhaka, BD, Bangladesh