VISCERAL Visual Concept Extraction Challenge in Radiology
Funded by the European Union FP7
Team: Markus Krenn, Georg Langs, René Donner, Matthias Dorfer, Markus Holzer
Project partners: Vienna University of Technology, University of Applied Sciences Western Switzerland, Medical University of Vienna, ETH Zürich, University of Heidelberg, Catalan Agency for Health Information
Objectives: VISCERAL will be organising two benchmarks on the processing of large-scale 3D radiology images making use of an innovative cloud-based evaluation approach.
We will define and execute a targeted benchmark framework to speed up progress towards:
- Automated anatomy identification and pathology identification in 3D (MRI, CT) and 4D (MRI with a time component) radiology images.
- Similar case retrieval for these images and the reports associated with them.
Benchmark 1: Identification, localization and segmentation. The Benchmark tasks will be organ identification and the segmentation of bones, inner organ and relevant substructures. (Benchmark Dates: August to November 2013)
Benchmark 2: Retrieval. The Benchmark task will be the retrieval of similar cases based on both visual information and radiology reports. (Benchmark Dates: May to August 2014)