MICCAI 2018 Daily - Tuesday

Phil’s picks of the day: 09:30-09:45 (M-107) Instance Segmentation and Tracking with Cosine Embeddings and Recurrent Hourglass Networks 10:00-10:15 (M-121) Predicting Cancer with a Recurrent Visual Attention Model for Histopathology Images 17:45-18:00 (T-27) TextRay: Mining Clinical Reports to Gain a Broad Understanding of Chest X-rays [ see our review at page 4 ] (an imaging method for skin lesions using immersion fluid or cross- polarised light), its application for skin cancer detection, and teaching methods for it. After finding his way back to programming after med- school he is now working on and machine-learning backed methods to make physicians more efficient and accurate. “ This is my first MICCAI conference, and I am a co-organizer of the ISIC challenge & workshop on Thursday. As a collaboration between the Medical University of Vienna and the University of Queensland we collected a unique set of over 10,000 dermatoscopic images with examples of almost any important class of pigmented skin lesions . These images were used in the ISIC 2018 challenge where we eventually had more than 300 final test-set submissions for three different tasks. I really hope the images will push forward research in the field! ” Phil’s Picks For today, Tuesday 18 2 Tuesday Philipp Tschandl is a dermatologist at the Medical University of Vienna currently pursuing a Post-Doc Fellowship at the School of Computing Science at Simon Fraser University (Burnaby, Canada) for machine learning applications in the dermatologic field. He became MD in 2012 and finished his PhD dealing with mutations in nevus-associated melanomas in 2016. His main scientific work is about dermatoscopy