Diffusion-weighted MRI has evolved into an accurate indicator of the efficacy of cancer therapy. In pre-clinical models, there is abundant evidence that the apparent diffusion coefficients in tumors increase early, in response to successful therapies. Hence, accurate segmentation of tumors and other pathologies is critical for oncology research.

A major site for metastases in cancer patients is the liver. Due to incoherent motion; diffusion-weighted images of liver are best obtained with echoplanar acquisitions. However, these data suffer from low SNR, fuzzy boundaries due to partial volume effects and anisotropic motion, and poor contrast. In addition, motion occurs between acquisitions at different b-values, precluding direct registration and pixel-by-pixel calculations of apparent diffusion coefficients. The focus of this work was to enable automated segmentation and registration of lesions from echo planar images of the liver.

We developed algorithms for automatic lesion segmentation, and tracking deformations and translations associated with these lesions.

Here is an example of a diffusion-weighted image of the liver, where the lesion is the bright region on the left side of the image:

This work was a collaborative effort with Prof. Robert J. Gillies (Dept. of Biochemistry and Arizona Cancer Center).

Publications:

1. Chetankumar Krishnamurthy, Jeffrey J. Rodriguez, Natarajan Raghunand, Rebecca Theilmann, Nikhil Rajguru, and Robert Gillies, "Automated Lesion Tracking in Echo-Planar Diffusion-Weighted Liver MRI: An Active Contour Based Approach," Intl. Society for Magnetic Resonance in Medicine(ISMRM) 13th Scientific Meeting \& Exhibition, Miami, May 7-13, 2005.
   
   
2. Chetankumar Krishnamurthy, Jeffrey J. Rodriguez, and Robert Gillies, "Automated Segmentation of Liver Metastases in Diffusion-Weighted Echoplanar Images Using Region Growing and Snakes Based on Fuzzy Sobel Edge Detector," in Proc. Intl. Society for Magnetic Resonance in Medicine(ISMRM) Twelfth Scientific Meeting and Exhibition, Kyoto, Japan, May 15-21, 2004.
   
   
3. Chetankumar Krishnamurthy, Jeffrey J. Rodriguez, and Robert J. Gillies, "Snake-Based Liver Lesion Segmentation," in Proc. 2004 IEEE Southwest Symp. on Image Analysis and Intepretation, Lake Tahoe, CA, March 28-30, 2004, pp. 187-191. [ PDF ]