|
William M. Wells III(aka Sandy Wells)
Associate Professor Member of the Affiliated Faculty of the Harvard-MIT Division of Health Sciences and Technology Research Scientist, MIT CSAIL |
White Matter Surface |
I am a researcher in medical image analysis with the Surgical Planning Laboratory , a unit of the MRI division of the Radiology Department of Brigham and Women's Hospital. I maintain an active collaboration with the MIT Computer Science and Artificial Intelligence Laboratory, where I work with a talented group of graduate students. I am also affiliated with the Harvard-MIT Division of Health Sciences and Technology , and periodically teach the medical image processing part of HST882 / 6.555: Biomedical Signal and Image Processing .
Modern medical images contain vast amounts of anatomical information. Much of this information is accessible to diagnostic radiologists, in part because people (in contrast to computers) are very good at image interpretation. The anatomical information latent in such images is also valuable for disease and neuroscience research, as well as for drug trials. The quantitative analysis of medical images by computer, however, remains challenging. Among the most basic capabilities of medical image analysis are segmentation , the process of assigning labels to structures in images, and registration , the process of placing different images into anatomical agreement.
My work has focused primarily on the analysis of structural and functional MRI. Areas of research include the segmentation and registration of MRI, with some emphasis on applications in image-guided surgery. The figure on the upper right illustrates the white matter surface of a brain that was segmented from MRI using Adaptive Segmentation of MRI (the "EM Segmenter") .
My research in medical image registration concerns the use of Mutual Information as a criterion for image fusion. This approach has become the de-facto standard for multi-modality problems. Implementations of this method are available in 3D Slicer, our open-source platform for medical image analysis, and in ITK, an NIH sponsored segmentation and registration library.
In addition to morphological analysis, I am also interested in univariate and multivariate analysis of functional MRI.
Multi-modal volume registration by maximization of mutual information. Wells WM, Viola P, Atsumi H, Nakajima S, Kikinis R. Medical Image Analysis. 1996;1:35--52. pdf , html , Citations
Adaptive segmentation of MRI data. Wells WM, Kikinis R, Grimson WEL, Jolesz F. IEEE Transactions on Medical Imaging. 1996;15:429--442. pdf , html , Citations
Statistical approaches to feature-based object recognition. Wells W. International Journal of Computer Vision. 1997;21:63--98. pdf
Alignment by maximization of mutual information. Viola P, Wells WM. International Journal of Computer Vision. 1997;24:137--154. pdf , Citations
Level Set Based Segmentation with Intensity and Curvature Priors. Leventon ME, Faugeras O, Grimson WEL, Wells W. Proceedings Mathematical Methods in Biomedical Image Processing, 2000.
2D-3D Rigid Registration of Fluoroscopy and CT Images Using Mutual Information and Sparsely Sampled Histograms as Density Estimators. Zollei L, Norbash A, Grimson W, Wells W. Proceedings 2001 IEEE conference on Computer Vision and Pattern Recogntion.
An Integrated Visualization System for Surgical Planning and Guidance Using Image Fusion and an Open MR. Gering D, Nabavi A, Kikinis R, Hata N, O'Donnell L, Grimson E, Jolesz F, Black P, Wells WM. JMRI 2001; 13:967-975
Adaptive Entropy Rates for fMRI Time-Series Analysis. Fisher J, Cosman E, Wible C, Wells W. Proceedings of the fourth international conference on Medical Image Computing and Computer Assisted Intervention, Utrecht, 2001
A Unified Statistical and Information Theoretic Framework for Multi-modal Image Registration. Zollei L, Fisher J, Wells WM. Image Processing in Medical Imaging 2003, Ambleside, UK, 2003.
Multiresolution image registration based on Kullback-Leibler distance. Gan R, Wu J, Chung A, Yu S, Wells WM. Proceedings MICCAI, St. Malo, France. 2004.
Mutual Information in a Coupled Multi-Shape Model for Medical Image Segmentation. Tsai A, Wells WM, Tempany C, Grimson E, Willsky A. Medical Image Analysis 2004: 429-445.
Exact MAP Activity Detection in fMRI using a GLM with an Ising Spatial Prior. Cosman E, Fisher J, Wells W. Proceedings MICCAI, St. Malo, France. 2004.
Simultaneous Truth and Performance Level Estimation (STAPLE): An Algorithm for the Validation of Image Segmentation. Warfield S, Zou KH, Wells WM. IEEE Trans Med Imag 2004; 23:903-921.
Coupling Statistical Segmentation and PCA Shape Modeling. Pohl K, Warfield S, Kikinis R, Grimson W, Wells WM. Proceedings MICCAI, St. Malot, France. 2004.
Reproducibility of functional MR imaging: Preliminary results of a prospective multi-institutional stud by the Biomedical Informatics Research Group. Zou KH, Greve DN, Wang M, Pieper SD, Warfield SK, White NS, Manandhar S, Brown GG, Vangel MG, Kikinis R, Wells WM. Radiology 2005 (to appear).
Bayesian Population Modeling of Effective Connectivity. Cosman E, Wells WM. Image Processing in Medical Imaging 2005, Glenwood Springs, Colo. 2005.
Efficient Population Registration of 3D Data. Zollei L, Learned-Miller E, Grimson WEL, Wells W. Proceedings First International Workshop on Computer Vision for Biomedical Image Applications, Beijing, 2005.
A Bayesian Model for Joint Segmentation and Registration. Pohl K, Fisher J, Grimson WEL, Kikinis R, Wells W. Neuroimage (to appear)
William Wells
Department of Radiology
Brigham and Women's Hospital
75 Francis St.
Boston, MA
02115
