Medical (text and image) IR
Abstract: Medical information is produced in massive quantities both targeting health professionals and also for patients, for example on the Internet. Information quality can vary widely and finding trustable information of high quality is not easy. Health topics are some of the most frequently searched topics on the web. Clinical texts are often semi-structured but contain much variability in terms of wording, spelling mistakes and also unusual abbreviations. In addition to free text, medical data include images, videos, signals, and structure data, and often several languages. This means that almost all challenges in information retrieval also occur for medical text.
The presentation will start with medical data production focusing on images and text. It explains information needs and how these needs are situation dependent and subjective. Based on the medical ImageCLEF challenges several scenarios and techniques will be explained to fulfill medical information needs and analyze medical data to create knowledge and help clinical decision making.
Download the slides of the lecture
Short Bio: Henning Müller studied medical informatics at the University of Heidelberg, Germany, then worked at Daimler-Benz research in Portland, OR, USA. From 1998-2002 he worked on his Ph.D. degree at the University of Geneva, Switzerland with a research stay at Monash University, Melbourne, Australia. Since 2002, Henning has been working for the medical informatics service at the University Hospital of Geneva. Since 2007, he has been a full professor at the HES-SO Valais and since 2011; he is responsible for the eHealth unit of the school.
Since 2014, he is also professor at the medical faculty of the University of Geneva. In 2015/2016 he was on sabbatical at the Martinos Center, part of Harvard Medical School in Boston, MA, USA to focus on research. Henning is the coordinator of the ExaMode EU project, was the coordinator of the Khresmoi EU project, scientific coordinator of the VISCERAL EU project and is the initiator of the ImageCLEF benchmark that has run medical tasks since 2004. He has authored over 400 scientific papers with more than 13,000 citations and is in the editorial board of several journals.