Deep Learning for Medical Image Analysis
Deep learning has attracted great attention in the medical imaging community as a promising solution for automated, fast and accurate medical image analysis, which is mandatory for quality healthcare. Convolutional neural networks and its variants have become the most preferred and widely used deep learning models in medical image analysis. U-Net is another popular architecture especially for biomedical imaging. It consists of a contraction and expansion path to pixel-wise predict the dataset. This model is better than previously available medical image segmentation approaches. However again, it fails to produce the promising results with 3D voxels. For that, an incremental version of U-Net, Multiplanar U-Net has been developed in 2019. In this talk, the speaker will discuss about multi-planar 3D knee MRI segmentation architectures, which is one of the U-Net inspired models.
Date and Time
Location
Hosts
Registration
- Date: 18 Feb 2025
- Time: 09:30 AM UTC to 10:30 AM UTC
-
Add Event to Calendar
Speakers
Dr. Sandeep Singh Sengar of Cardiff Metropolitan University, United Kingdom
Deep Learning for Medical Image Analysis
Deep learning has attracted great attention in the medical imaging community as a promising solution for automated, fast and accurate medical image analysis, which is mandatory for quality healthcare. Convolutional neural networks and its variants have become the most preferred and widely used deep learning models in medical image analysis. U-Net is another popular architecture especially for biomedical imaging. It consists of a contraction and expansion path to pixel-wise predict the dataset. This model is better than previously available medical image segmentation approaches. However again, it fails to produce the promising results with 3D voxels. For that, an incremental version of U-Net, Multiplanar U-Net has been developed in 2019. In this talk, we will discuss about multi-planar 3D knee MRI segmentation architectures, which is one of the U-Net inspired models.
Biography:
Dr. Sandeep Singh Sengar is a Senior Lecturer and the Head of Computer Vision and Artificial Intelligence at Cardiff Metropolitan University, United Kingdom. He also serves as the Cluster Leader for Computer Vision/Image Processing and represents the British Computer Society. Prior to his current role, Dr. Sengar was a Postdoctoral Research Fellow in the Machine Learning Section of the Computer Science Department at the University of Copenhagen, Denmark, the country's top-ranked university. In 2022, he was a visiting researcher at University College Dublin, the second-ranked university in Ireland. Dr. Sengar earned his Ph.D. in Computer Vision from the Indian Institute of Technology (ISM) Dhanbad and his M.Tech. from Motilal Nehru National Institute of Technology, Allahabad, India. He is a Fellow of the UK Higher Education Academy and a Senior Member of IEEE. His research focuses on Machine/Deep Learning, Computer Vision, and Image/Video Processing. Dr. Sengar has an extensive publication record in leading international journals and conferences. He has published in top-tier venues such as MIE, NCAA, CVIP, EFMI, IJCAI, BMVC, and JVCAIR. He is a member of the editorial boards for Signal, Image and Video Processing and the International Journal of Imaging Systems and Technology. He also serves on the Board of Studies at Universal AI University in Mumbai, India, and reviews research grant proposals for EPSRC UK, NMRC Singapore, and Cardiff Met. Additionally, Dr. Sengar is a Ph.D. examiner for several prestigious institutions, including the University of South Wales, the Indian Institutes of Technology and the National Institutes of Technology in India. He has played key roles in international conferences, such as serving as an organizing chair and distinguished guest. He has delivered expert talks worldwide at prestigious institutions, including Trinity College Dublin, University College Dublin, the Technical University of Denmark, multiple Indian Institutes of Technology, Cardiff University, and several others.