Automated process spots subtle tumor changes

Researchers at the Mayo Clinic in Rochester, MN, and the University of Southern California have developed automated techniques to better document changes to brain tumors occurring over time.

The researchers at the Mayo Clinic described the most common approaches to change detection, ranging from manual inspection, measurement sampling, and volumetrics to warping and temporal analysis (J Digital Imaging, e-pub 29 June 2004).

The paper suggests a number of technical approaches for separating acquisition-related changes from pathology-related changes, including preacquisition registration of scans, scaling correction, subvoxel registration, and change computation.