The watershed algorithm: a method to segment noisy PET transmission images

Attenuation correction is essential to PET imaging but often requires impractical acquisition times. Segmentation of short, noisier transmission scans has been proposed as a solution. We report that a 3D morphological tool-the watershed algorithm-is well adapted for segmenting even two-minute PET transmission images. The technique is non-iterative, fast and fully 3D. It inherently ensures class continuity and eliminates outliers. Pre-filtering the data induced smoother class edges, showing that a multi-resolution approach could be used to deal with the partial volume effect and excessive noise in the data. The algorithm was tested on two-minute scans of a torso phantom and on a human study.