Koen Van Leemput, Ph.D. Athinoula A. Martinos Center for Biomedical Imaging 149 Thirteenth Street, Suite 2301 Charlestown, MA 02129 USA MIT Computer Science and Artificial Intelligence Laboratory 32 Vassar Street 32-D430 Cambridge, MA 02139 USA Phone: +1-857-756-5723

New: PhD position in medical image analysis (Helsinki+Boston)

Short bio

I am a researcher in medical image computing, with a focus on model-based segmentation and registration of magnetic resonance (MR) images of the brain. I obtained my PhD degree from the medical image computing group in Leuven, Belgium, in 2001. After spending half a year as a visiting researcher at the Helsinki University of Technology, Finland, in 2001, I joined the staff of the Helsinki University Central Hospital, Finland, in 2002. Since 2007 I hold a faculty appointment at the Martinos Center for Biomedical Imaging, Massachusetts General Hospital, and at Harvard Medical School. I am also a research scientist at the MIT Computer Science and Artificial Intelligence Laboratory.

I serve as an associate editor of the IEEE Transactions on Medical Imaging, as a member of the editorial board of the Medical Image Analysis Journal, and as a reviewer for several international medical imaging journals and conferences. I am also a past associate editor of the IEEE Transactions on Information Technology in Biomedicine (2002-2005), and a past program committee member of the MICCAI conference (2007).

Software

• A Java Applet (with source code) demonstrating my Expectation-Maximization approach to partial volume segmentation of brain MRI.
  
  
• A freely available matlab package, EMS, for fully automated segmentation of normal and pathological brain MRI scans. EMS is now pretty old, but still works fine. You'll need to install an ancient version of SPM, SPM99, to get it running though.
  
  

Non-technical overviews

• Visionday 2009 talk, Department of Informatics and Mathematical Modeling, Technical University of Denmark: Generative models for automated brain MRI segmentation - ppt
  
  
• MICCAI 2003 Tutorial: Brain MRI Segmentation Using an Expectation-Maximization Algorithm - pdf
  
  
• My Ph.D. thesis: Quantitative Analysis of Signal Abnormalities in MR Imaging for Multiple Sclerosis and Creutzfeldt-Jakob Disease , K.U.Leuven, May 2001, Leuven, Belgium - pdf
  
  

Selected publications   [More...]

	Automated Segmentation of Hippocampal Subfields from Ultra-High Resolution In Vivo MRI K. Van Leemput, A. Bakkour, T. Benner, G. Wiggins, L.L. Wald, J. Augustinack, B.C. Dickerson, P. Golland, B. Fischl Hippocampus, vol. 19, no. 6, pp. 549-557, June 2009 pdf - atlas mesh movie - mesh deformation movie - deformation movie (only hippo) - MICCAI 2008 CAPH talk
	Encoding Probabilistic Brain Atlases Using Bayesian Inference K. Van Leemput IEEE Transactions on Medical Imaging, vol. 28, no. 6, pp. 822-837, June 2009 Summary and comments pdf - atlas mesh movie (4 subjects) - MICCAI 2006 talk
	Given a set of manual segmentations, the aim of this paper is to learn a probability distribution such that samples drawn from that distribution tend to look like manual segmentations of other subjects. This is useful because such a distribution can then be used as a prior in automated segmentation algorithms. The proposed method extends the usual concept of probabilistic atlases in several ways; for instance, it yields sparse tetrahedral meshes that are less prone to overfitting to the training data than traditional atlases. These atlases are therefore better able to predict the antanomy in unseen subjects, especially when the number of training subjects is small. A Bayesian modeling approach is used throughout. A first level of inference yields a non-rigid group-wise registration algorithm based on a topology preserving deformation prior; the registration criterion is closely related to the so-called congealing criterion. For higher levels of inference, the method does Bayesian model comparison, which is known to be closely related to the Minimum Description Length principle when Gaussian approximations are used. The method explicitly aims at finding the optimal deformation regularization, which involves approximating an integral over all possible deformations. An interesting alternative way to do this, proposed by Stephanie Allassonniere and co-workers, is to side-step the integration by sampling from the deformation posterior in an EM algorithm (although you'd still have to approximate the partition function if the deformation model is not Gaussian, as in our case).
	A Unifying Framework for Partial Volume Segmentation of Brain MR Images K. Van Leemput, F. Maes, D. Vandermeulen, P. Suetens IEEE Transactions on Medical Imaging, vol. 22, no. 1, pp. 105-119, January 2003 pdf - java applet (with source code)
	Automated Segmentation of Multiple Sclerosis Lesions by Model Outlier Detection K. Van Leemput, F. Maes, D. Vandermeulen, A. Colchester, P. Suetens IEEE Transactions on Medical Imaging, vol. 20, no. 8, pp. 677-688, August 2001 pdf - matlab code (EMS)
	Automated Model-Based Tissue Classification of MR Images of the Brain K. Van Leemput, F. Maes, D. Vandermeulen, P. Suetens IEEE Transactions on Medical Imaging, vol. 18, no. 10, pp. 897-908, October 1999 pdf - matlab code (EMS)
	Automated Model-Based Bias Field Correction of MR Images of the Brain K. Van Leemput, F. Maes, D. Vandermeulen, P. Suetens IEEE Transactions on Medical Imaging, vol. 18, no. 10, pp. 885-896, October 1999 pdf - matlab code (EMS)

Stuff worth reading

• Gottfried Schatz: Euro - Blues ("tenure track" or "penured trek"?) - pdf
  
  
• Donald Geman: Ten Reasons Why Conference Papers Should Be Abolished - pdf