Keynote Speaker 1

Dr. Nilanjan Dey

  • Asst. Professor, Dept. of IT, Techno India College of Technology, India. Visiting Fellow, WC Laboratory, Department of Biomedical Engineering, University of Reading, UK, Ambassador - IFIP InterYIT, India.

Specialization: Medical Imaging, Machine learning, Computer Aided Diagnosis, Data Mining

Biography: Nilanjan Dey is an Assistant Professor in Department of Information Technology at Techno India College of Technology, Kolkata, India. He is a visiting fellow of the Biomedical Engineering, School of Biological Sciences,

The University of Reading, UK.. He is a Visiting Professor at Duy Tan University, Vietnam; He was an honorary Visiting Scientist at Global Biomedical Technologies Inc., CA, USA (2012-2015). He was awarded his PhD. from Jadavpur University in 2015.

He has authored/edited more than 75 books with Elsevier, Wiley, CRC Press and Springer, and published more than 300 papers (H-Index 41). He is the Editor-in-Chief of International Journal of Ambient Computing and Intelligence, IGI Global (Scopus Q2, ESCI), Associated Editor of IEEE Access and International Journal of Information Technology, Springer. He is the Series Co-Editor of Springer Tracts in Nature-Inspired Computing, Springer, Series Co-Editor of Advances in Ubiquitous Sensing Applications for Healthcare, Elsevier, Series Editor of Computational Intelligence in Engineering Problem Solving and Intelligent Signal processing and data analysis, CRC.

He is the Indian Ambassador of International Federation for Information Processing – Young ICT Group. He is among the top 5 most published academics in the field of Computer Science in India (2014-19) [Sci_Val Scopus].

Title: Computer-aided Detection and Diagnosis in Medical Imaging

Abstract: Advancement in medical imaging modalities results in huge varieties of images engaged in different management phases, namely prognosis, diagnosis, and treatment. In clinical practice, imaging has reserved a vital role to assist physicians and medical experts in decision-making. However, the counterpart that the physician faces is the complexity to deal with a large amount of data and image contents. Mainly, the interpretation is based on the physician’s observations, which is tedious, subject to error, and highly dependent on the skills and experience of the clinicians. Accordingly, emerging demand for automated tools become essential for detecting, quantifying, and classifying the disease for an accurate diagnosis. Computer-aided diagnosis (CAD) is an emergent research area that aims to meet the physicians’ demands, to speed up the diagnostic process, to reduce diagnostic errors, and to improve the quantitative evaluation. It is primarily based on medical images that provide direct visualization of the bodies and information ranging from functional activities, anatomical information, to the cellular and molecular expressions.

This talk provides a state-of-the-art sight in medical imaging applied to CAD. It highlights the  different imaging modalities, such as Magnetic Resonance Imaging, Computed Tomography, Positron Emission Tomography, and Ultrasound. The talk emphasizes on the ability of CAD to improve the diagnostic accuracy and different future directions as an opening that gathers the clinicians and engineers for an accurate diagnosis.

Keynote Speaker 2

Dr. Suresh Manandhar

  • Director, Nepal Applied Mathematics and Informatics Institute, Nepal.

Specialization: Natural language processing (NLP): unsupervised learning of morphology, syntax and semantics; Deep learning for NLP and medical image processing.

Biography: Suresh Manandhar is an AI scientist with over 30 years in the field with interest in machine learning and natural language processing. He was head of AI research group at University of York until 2019, where he successfully   supervised   over   20   doctoral   students   and   published   over   120   papers. He is currently Director of NAAMII AI research centre, Nepal.

He has a wide range of interests in topics related   to   natural   language   processing   and   applications   of   machine   learning.   Some   of   his   current research themes are deep learning models for compositional distributional semantics, deep learning for medical  image   processing,   community   discovery   using   content   and  link   analysis,   answering   complex questions, unsupervised learning of morphology, named entities and semantic relations. He  co-chaired the international research competitions in Semantic Evaluations  SemEval 2012  and  SemEval 2013. He currently serves on the editorial boards of the Journal of Natural Language Engineering and Journal of Applied Intelligence.

Title: Attention based models for image and multi modal data analysis

Abstract: Attention based models have been hugely successful within current deep learning applications. In this talk, I will describe some of our recent work in medical image processing and stock market data analysis. We develop a novel attention based architecture for deep CNNs (convolutional neural networks) that incorporates separate encoder-decoder pipelines for attention masks and for feature extraction. We demonstrate this hybrid architecture is ideally suited for fine grained image segmentation tasks achieving state of the art performance in medical image segmentation. In the second part of the talk, I will describe our current work on multi modal time series data analysis. I will illustrate how a hierarchical attention based model can be employed to focus only on the news relevant for specific stocks. The hierarchical model permits attention over specific sentences and secondly on specific words within a sentence. Our evaluation on stock market data shows that the model outperforms existing statistical methods for predicting stock volatility.