Challenges & Implications of Deep Learning in Healthcare
Deep Learning has made leaps and bounds in several industries around us – products ranging from self-driving cars, voice assistants, fashion recognition engines and enterprise bots are no longer science fiction ideas. Despite the advances in several industries, intelligence in healthcare has seen limited penetration. Other than the giants of IBM, few have taken up building intelligent healthcare enterprise solutions.
Applications of deep learning in healthcare covers a broad range of problems ranging from cancer screening and disease monitoring to personalized treatment suggestions. Various sources of data today - radiological imaging (X-Ray, CT and MRI scans), pathology imaging and recently, genomic sequences have brought an immense amount of data at the physician’s disposal. However, we are still short of tools to convert all this data to useful information. This talk aims to demystify some of the challenges, milestones and current state-of-art in healthcare intelligence today.
Over the course of the talk, I will also cover our solution to Multiple Sclerosis lesion segmentation from Brain MRI, which was awarded for best performance at the IEEE- International Symposium on Biomedical Imaging 2015, New York. We use a 3D convolutional neural network (CNN) with novel sub-sampling and efficient training implementation using sparse convolutional kernels.
- Quick recap on milestones achieved by deep learning and in the healthcare space
- Open challenges in DL for Medicine – Access to data, number of samples, large sizes, variations based on demographics, need for high accuracy solutions
- Solution to our winning IEEE-ISBI challenge entry on Multiple Sclerosis using 3D CNNs
- Current state of art in research & industry – how far are we from complete diagnosis?
Suthirth Vaidya is a co-founder at Predible Health, which develops AI based recognition tools for medical imaging. His team previously won the Grand Challenge at IEEE-International Symposium on Biomedical Imaging 2015 at New York, USA for application of deep learning for segmentation of multiple sclerosis lesions in the brain. He underwent his undergraduate and master’s degree studies from IIT Madras.
- LinkedIn - www.linkedin.com/in/suthirth
- Predible Health - www.predible.co
- Times of India article - http://timesofindia.indiatimes.com/life-style/health-fitness/health-news/IIT-Madras-teams-research-to-help-detect-multiple-sclerosis/articleshow/48326781.cms