William M. Wells III

(aka Sandy Wells)

Professor of Radiology
Department of Radiology
Harvard Medical School and
Brigham and Women's Hospital

Member of the Affiliated Faculty of the Harvard-MIT Division of Health Sciences and Technology

Research Scientist, MIT CSAIL

My BWH web page

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, Harvard Medical School. I maintain an active collaboration with the MIT Computer Science and Artificial Intelligence Laboratory, where I have worked 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, including 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.

I recently organized the 2013 meeting of Information Processing In Medical Imaging (IPMI 2013) , held near Monterey California June 29 - July 3.


My publications, with citation info, via Goole Scholar

My publications via the SPL Publications Database (some with pdf)

Contact info:

William Wells
Department of Radiology
Brigham and Women's Hospital
75 Francis St.
Boston, MA

Directions to my office at Brigham and Womens Hosptial.
MIT office: 32-D462