Prof. Henning Muller: "Medical 3D data retrieval"
Abstract:
Medical tomographic data is produced in enormous quantities and currently very little of the knowledge stored in past cases has been exploited as data is only used in the context of single patients. In difference to object retrieval, tomographic data represents solid texture and the texture variation inside objects is usually more important than shapes of structures. The presentation will describe methods for retrieval of solid medical 3D texture in several applications and ways to better exploit existing medical data.
The VISCERAL challenge in medical image segmentation and retrieval will be presented that has the goal to bring medical 3D data analysis towards big data. Several terabytes of data will be made available to the scientific community to first identify important body parts and then retrieve similar cases for challenges that will be run inside the cloud.
Henning Muller
obtained his Masters degree in medical informatics from Heidelberg
University, Germany, in 1997 and his PhD on multimedia information
retrieval from Geneva University, Switzerland in 2002. During this time
he also worked for Daimler Benz research and technology North America
in Portland, Oregon, USA, and at Monash University in Melbourne,
Australia. After his PhD Henning has worked in the medical informatics
service of the University and University hospitals of Geneva,
Switzerland, where he finished his habilitation in 2008. Since 2007 he
has been a professor at the University of Applied Sciences Western
Switzerland in Sierre, Switzerland. Henning leads the ImageCLEF
benchmark on multilingual and multimodal information retrieval. He has
published over 300 scientific articles on visual and 3D information
analysis and is currently in the editorial board of five journals. He
has participated in several EU projects and has initiated several
national projects. Currently, Henning is coordinator of the Khresmoi EU
project on medical information retrieval and scientific coordinator of
the VISCERAL project
and leads a team of ten persons the MedGIFT group of the HES-SO.
Medical tomographic data is produced in enormous quantities and currently very little of the knowledge stored in past cases has been exploited as data is only used in the context of single patients. In difference to object retrieval, tomographic data represents solid texture and the texture variation inside objects is usually more important than shapes of structures. The presentation will describe methods for retrieval of solid medical 3D texture in several applications and ways to better exploit existing medical data.
The VISCERAL challenge in medical image segmentation and retrieval will be presented that has the goal to bring medical 3D data analysis towards big data. Several terabytes of data will be made available to the scientific community to first identify important body parts and then retrieve similar cases for challenges that will be run inside the cloud.
