当前位置: 科学研究> 学术动态>

【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)

点击:1082次 发布人:kyb 发布时间:2019-09-04 17:00:47


How Deep Learning, Human   Vision and Medical Imaging benefit from each other





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.