Speaker: Dr Gregory Slabaugh, Dept of Computer Science, City, University of London
Research Centre: Research Centre for Machine Learning
Title: Applications of deep learning in medical imaging
Recent advances in deep learning have shown incredible progress in computer vision -- in some cases, exceeding human performance. In this talk, I’ll present some of our recent and work-in-progress research in applying deep learning methods to medical imaging. First, I will provide a basic review of convolutional neural networks, including variants with deconvolutional layers for image segmentation. I will then describe our work in x-ray image analysis of cervical spine images, to identify the cervical vertebrae and their shape, important for computed-aided diagnosis of injury. If time permits I will also describe recent work in functional magnetic resonance imaging (fMRI) designed to diagnose ADHD from brain connectivity signals.
Dr Greg Slabaugh is a Senior Lecturer in the Department of Computer Science at City, University of London, where he founded and leads the Computer Vision Group, consisting of a team of researchers in computer vision, with applications to medical imaging, computer graphics, and human computer interaction. He has co-authored over 100 peer-reviewed papers and has been granted 36 patents for his work in image analysis and shape modelling, and his work has been funded by the European Union, the EPSRC, and Innovate UK. Recent work by the Computer Vision Group has won awards at workshops at top tier conferences, including CVPR 2016 and MICCAI 2016. Dr Slabaugh earned a PhD (highest honours) in Electrical Engineering from Georgia Institute of Technology in Atlanta, USA. He has roughly a decade's experience working in industry, holding research positions at Medicsight and Siemens. This work includes several launched medical device products including computer-aided detection of pre-cancerous lesions in the colon (including CE marking and FDA approval), segmentation of lesions in MR and ultrasound images, ultrasound image enhancement, and computer-aided design of hearing aids. He is a Senior Member of IEEE and served as an Associate Editor of IEEE Signal Processing Magazine.
Share this event
When and where
6.00pm - 7.00pmWednesday 18th October 2017