【电气论坛】How Deep Learning, Human Vision and Medical Imaging benefit from each other (IGBSG 2019) 国际会议专题报告（6）
How Deep Learning, Human Vision and Medical Imaging benefit from each other
主 讲 人
Prof. B.M.ter Haar Romeny
B. M.ter Haar Romeny is (since Dec 2017) emeritus professor in Biomedical Image Analysis at Eindhoven University of Technology in the Netherlands. He acquired his MSc in Applied Physics from Delft University of Technology and PhD from Utrecht University. He co-established the Image Sciences Institute in Utrecht, before moving to Eindhoven as full professor in 2001.
His research interests focus on biologically inspired image analysis algorithms, multi-valued 3D visualization, especially brain connectivity and computer-aided diagnosis (in particular for diabetes), and image guided surgery, directed towards neurosurgery. He is President of the Dutch Society for Pattern Recognition and Image Processing, and has been President of the Dutch Society for Biophysics & Biomedical Engineering and the Dutch Society of Clinical Physics. He initiated the ‘Scale-Space’ conference series in 1997 (now SSVM). He is reviewer for many journals, conferences and science foundations, and organized many Summer Schools. Prof. Romeny is Senior Member of IEEE, Fellow of EAMBES, Board member of IAPR, and Honorary Chair Professor at NTUST. He is an awarded teacher, and a frequent keynote lecturer.
Artificial Intelligence sees breakthroughs everywhere. It enables self-driving cars, face identification, speech recognition, intelligent design everywhere, and diagnosis in healthcare. However it is largely a black box, and much of the applications are still quite heuristic. There are many striking similarities with human vision. Just as in many other fields, many discoveries are done in modern brain research. These findings give important clues to understand the mechanisms of deep neural nets. Medical imaging sees performance come close or even better than human experts. Here, like everywhere else, the availability of big data is key. We discuss the example of large-scale retinal screening for diabetes detection in detail to illustrate the beneficial coherence between the topics discussed above.