Cloud-Based Benchmarking of Medical Image Analysis

Allan Hanbury is Senior Researcher at the TU Wien, Austria, and was the coordinator of the EU-funded VISCERAL project on evaluation of algorithms on big data. His research interests include data science, information retrieval, multimodal information retrieval, and the evaluation of information retrieval systems and algorithms.Henning Müller is professor in computer sciences at the HES-SO, Sierre, Switzerland and in medicine at the University of Geneva, Switzerland. His research focuses on medical information retrieval, the organization of data science challenges and multimodal data analysis for big data and the underlying computing infrastructures.Georg Langs is the Head of the Computational Imaging Research Lab (CIR) at the Medical University of Vienna, Austria, and is also affiliated with the Medical Vision Group at CSAIL, Massachusetts Institute of Technology, USA. His main research interests are in neuroimaging, machine learning and medical image analysis.

• VISCERAL: Evaluation-as-a-Service for Medical Imaging.- Using the Cloud as a Platform for Evaluation and Data Preparation.- Ethical and Privacy Aspects of Using Medical Image Data.- Annotating Medical Image Data.- Datasets created in VISCERAL.- Evaluation Metrics for Medical Organ Segmentation and Lesion Detection.- VISCERAL Anatomy Benchmarks for Organ Segmentation and Landmark Localisation: Tasks and Results.- Retrieval of Medical Cases for Diagnostic Decisions: VISCERAL Retrieval Benchmark.- Automatic Atlas-Free Multi-Organ Segmentation of Contrast-Enhanced CT Scans.- Multi-organ Segmentation Using Coherent Propagating Level Set Method Guided by Hierarchical Shape Priors and Local Phase Information.- Automatic Multi-organ Segmentation using Hierarchically-Registered Probabilistic Atlases.- Multi-Atlas Segmentation Using Robust Feature-Based Registration.- Combining Radiology Images and Clinical Meta-data for Multimodal Medical Case-based Retrieval.- Text and Content-based Medical Image Retrieval in the VISCERAL Retrieval Benchmark.