CVPR 2012 - Workshop on Medical Computer Vision


Workshop on Medical Computer Vision at CVPR 2012, Providence, RI
Date: post-conference, June 21 2012
Registration: via IEEE CVPR


This workshop aims at exploring the use of modern computer vision and image recognition technology in tasks such as semantic anatomy parsing, automatic segmentation and quantification, anomaly detection and categorization, data harvesting, semantic navigation and visualization, data organization and clustering, and general-purpose automatic understanding of medical images. Excitingly new health-related applications where computer vision plays a role of technology enabler are also strongly encouraged (e.g., Behavior Imaging and the Study of Autism). Another exciting aspect of real world applications is that computer vision and machine learning techniques and principles have made successful clinical products for 3D imaging based cancer detection and diagnosis; automatic navigation and indexing of large scale medical database and even next generation smart medical scanners. We are especially interested in modern, scalable and efficient algorithms which can be applied e.g. to large longitudinal studies, high-resolution n-dimensional datasets and in hospital-scale databases.

The focus is on principled approaches which go beyond the limits of current model-driven image analysis, are provably efficient and which generalize well to previously unseen images; we are also interested in emerging applications which go beyond the analysis of individual clinical studies and specific diagnostic tasks – a current focus of many computational methods in medical imaging. We encourage the submission of original papers at the interface of computer vision, machine learning, and medical imaging analysis, to push the boundaries of what current medical software applications can deliver in both clinical and research medical settings.


Submission - April 15 2012 (Submission)
Decisions - April 25 2012   April 28 2012 
Camera Ready - May 02 2012
Workshop - June 21 2012


8:30~8:35        Opening Mark
8:35~9:20        Invited Talk: Prof. Linda Shapiro (University of Washington)
9:20~10:05      Invited Talk: Dr. Kevin Zhou (Siemens Corporate Research & Technology)

10:05~10:20    Coffee

10:20~10:40    Object Localization in Medical Images based on Graphical Model with Contrast and Interest-Region Terms
10:40~11:00    Color-Based Hybrid Reconstruction for Endoscopy
11:00~11:20    Randomness and Sparsity Induced Codebook Learning with Application to Cancer Image Classification
11:20~11:35    Segmentation and Removal of Pulmonary Arteries, Veins and Left Atrial Appendage for Visualizing Coronary and Bypass Arteries
11:35~11:50    Automatic Detection of Liver Lesion from 3D Computed Tomography Images
11:50~12:05    Learning Features on Robotic Surgical Tools
12:05~12:20    Atlas-based segmentation of brain MRI using random walks

12:20~1:40     Lunch

1:40~2:25      Invited Talk: Prof. Greg Hager (Johns Hopkins University)
2:25~3:20      Invited Talk: Prof. Zhuowen Tu (Microsoft Research Asia, & UCLA)

3:30~3:50      Fast and Accurate Global Geodesic Registrations using Knee MRI from the Osteoarthritis Initiative
3:50~4:10      Fully Automated 3D Colon Segmentation for Early Detection of Colorectal Cancer based on Convex Formulation of the Active Contour Model
4:10~4:25      Realistic 3D Reconstruction of the Human Teeth using Shape from Shading with Shape Priors
4:25~4:40      Combining Laplacian eigenmaps and vesselness filters for vessel segmentation in X-ray angiography
4:40~4:55      Multiple Kernel Learning Based Modality Classification for Medical Images
4:55~5:10      Temporally Consistent Diffeomorphic Motion Estimation with Mutual Information: Application to Echocardiographic Sequences

5:10~5:40      Panel Discussion: How computer vision can help solve better medical imaging problems, or meaningful challenging medical applications for computer vision?

Paper submission


Le Lu (Siemens Corporate Research)
Yiqiang Zhan  (Siemens Medical Solutions)
Georg Langs (Medical University of Vienna, MIT)
Bjoern Menze (ETH Zurich) 
Zhuowen Tu  (UCLA, Microsoft Research Asia)
Program Committee:
Antonio Criminisi (MSR Cambridge)
Pascal Fua (EPFL)
Jurgen Gall (Max Planck Tubingen)
James Gee (UPenn)
Bogdan Georgescu (Siemens SCR)
Leo Grady (Siemens SCR)
Greg Hager (JHU)
Junzhou Huang (UTA)
Michael Kelm (Siemens SCR)
Georg Langs (MU Vienna, MIT)
Jianming Liang (ASU)
Le Lu (Siemens SCR)
Bjoern Menze (ETHZ)
Nassir Navab (TUM)
Alison Noble (Oxford)
Jens Rittscher (GE Global Research)
Dinggang Shen (UNC)
Yonggang Shi (UCLA)
Matthias Scheider (ETHZ)
Zhuowen Tu (UCLA, MSR Asia)
Pingkun Yan (OPTIMAL Center CAS)
Yiqiang Zhan (Siemens Healthcare)
Yefeng Zheng (Siemens SCR)
Invited Talks:
Up to four invited talks (to be finalized)