Medical Computer Vision 2012          

Workshop @ MICCAI 2012 | October 5th, 2012



This workshop aims at exploring the use of modern computer vision technology in tasks such as automatic segmentation and registration, localization of anatomical features and detection of anomalies. It emphasizes questions of harvesting, organizing and learning from large-scale medical imaging data sets and general-purpose automatic understanding of medical images. We are especially interested in modern, scalable and efficient algorithms which generalize well to previously unseen images and which can potentially be applied to large-scale data sets arising, for example, from longitudinal studies with significant populations, acquired through wide field-of-view imaging sequences with high-resolution, or being compiled over time in hospital-scale databases. 

We encourage the submission of original papers that propose new methodology strongly motivated by a clinical application. Submissions will be at the interface of computer vision, machine learning and medical imaging analysis, transitioning 2D computer vision methods to 3D medical imaging data, or approaches that solve established tasks in medical image analysis through algorithms from computer vision.

Proceedings are planned to be published in Springer LNCS

Best paper prizes:

  1. 1.Lombaert et al. Group-wise spectral log-demons framework for atlas construction

  2. 2.Donner et al. Fast anatomical structure localization using top-down image patch regression

  3. 3.Gass et al. Semi-supervised segmentaiton using multiple hypotheses from a single atlas.


  1. Accepted papers are online

  1. Submission site open: Submisson Site

  1. Invited Speakers: Nikos Paragios (Ecole Centrale Paris), Nassir Navab (TU München)

  1. The best submission will be awarded a Best Scientific Paper Prize sponsored by GE Global Research and the EU project KHRESMOI.

We encourage the submissions dealing with the following methodological topics:

  1. Computer vision approaches that are scalable and efficient in the 2D and 3D domain

  2. How to deal with incomplete-, weak- or noisy annotation of training examples

  3. Data driven models for image segmentation and quantification

  4. Learning approaches for registration, calibration and related image transforms

  5. Anatomical structure localization through object recognition and categorization

  6. Developing 3D image descriptors and interest points for object localization

  7. Generative models of 3D image scenes relying on, or complementing, population atlases of anatomy or function

Applications of these technologies that push the boundaries of what current medical software applications can deliver in both clinical and research medical settings, are encourage, for example

  1. Semantic anatomy parsing, semantic navigation and visualization

  2. Applications of web-driven techniques to structure medical data sets.

  3. Image indexing, data organization, data harvesting.

  4. Real-time medical image applications. 

Important dates:

  1. Submission of full papers (8-10 pages LNCS format): June 29th 2012

  2. Notification of acceptance: July 9th 2012

  3. Submission of camera ready papers: TBA

  4. Workshop: 1 day workshop during MICCAI 2010, Octobre 5th, 2012


Bjoern Menze (ETH Zurich; CSAIL, MIT)

Georg Langs (CIR, Medical University Vienna; CSAIL, MIT)

Albert Montillo (GE Global Research)

Zhuowen Tu (LONI UCLA)

Antonio Criminisi (Microsoft Research)

Program Committee:

Leo Grady (Siemens Corporate Research)

Daniel Rueckert (Imperial College London)

Ender Konukoglu (Microsoft Research)

Ben Glocker (Microsoft Research)

Victor Lempitsky (Yandex)

Darko Zikic (Microsoft Research)

Kilian Pohl (University of Pennsylvenia)

Jan Margeta (INRIA)

Koen Van Leemput (Harvard MGH, DTU)

Rachid Deriche (INRIA)

Matthew Blaschko (Ecole Centrale Paris)

Cagatay Demiralp (Brown University)

Hayit Greenspan (Tel Aviv University)

Michael Kelm (Siemens Corporate Research)

Yefeng Zheng (Siemens Corporate Research)

Sebatian Ourselin (University College London)

Juan Eugenio Iglesias (Harvard MGH)

Juergen Gall (Max-Planck Gesellschaft Tübingen)

Ron Kikinis (Harvard BWH)

Christos Davatzikos (University of Pennsylvenia)

Christian Barillot (IRISA Rennes)

Tom Vercauteren (Mauna Kea Technology)

Helmut Grabner (ETH Zurich)

Horst Bischof (TU Graz)

Alison Noble (Oxford)

Tammy Riklin Raviv (Harvard BWH)

Michael Wels (Siemens Corporate Research)

Paul Suetens (KU Leuven)

Milan Sonka (University of Iowa)

Marleen de Bruijne (EMC Rotterdam, University of Copenhagen)

Kayhan Batmanghelich (CSAIL, MIT)

Lin Yang (University of Kentucky)

Bjoern Menze, René Donner, Tobias Gass, Herve Lombaert, Georg Langs

Nikos Paraiogos, Nicolas Ayache and Antonio Criminisi engaged in a lively discussion with the audience on the role of computer vision in medical imaging