Brief Profile:
Dr. Sandeep Singh Sengar is a Lecturer in Computer Science at Cardiff Metropolitan University, United Kingdom. Before joining this position, he worked as a Postdoctoral Research Fellow at the Machine Learning Section of Computer Science Department, University of Copenhagen, Denmark (a rank #1 university of Denmark). He holds a Ph.D. degree in Computer Science and Engineering from Indian Institute of Technology (ISM), Dhanbad, India and an M. Tech. degree in Information Security from Motilal Nehru National Institute of Technology, Allahabad, India. He has more than seven years of research and teaching experience (excluding PhD duration). Dr. Sengar’s current research interests include Medical Image Segmentation, Motion Segmentation, Visual Object Tracking, Object Recognition, and Video Compression. His broader research interests include Machine/Deep Learning, Computer Vision, Image/Video Processing and its applications. He has published several research articles in reputed international journals and conferences in the field of Computer Vision and Image Processing. He is a Reviewer of several reputed International Transactions, Journals, and conferences including IEEE Transactions on Systems, Man and Cybernetics: Systems, Pattern Recognition, Neural Computing and Applications, Neurocomputing. He has also served as a Technical Program Committee member in many reputed International Conferences. He has organized several special sessions and given keynote presentations at International Conferences. In addition to these, he has also given many expert talks in reputed organizations. He always believes in collaborative opportunities.
Title of Talk:
Intelligent Biomedical Image Analysis
Abstract of Talk:
Medical image segmentation is the part of computer vision and its target is to label each pixel of an object of interest in medical images. An end to end deep learning approach, Convolutional Neural Networks have shown state-of-the-art performance for automated medical image segmentation. However, it doesn’t perform well in case of complex environments. U-Net is another popular deep learning architecture especially for biomedical imaging. In this talk, a concise overview of the modern deep learning model applied in computer vision specifically in medical image analysis is provided and the key tasks performed by deep learning model, i.e., classification and segmentation are shown. Furthermore, we will discuss the thoroughly evaluated deep learning framework for segmentation of arbitrary medical image volumes. Our discussed framework requires no human interaction, no task-specific information, and is based on a fixed model topology and a fixed hyper parameter set.