Prostate boundary segmentation from 2D ultrasound images

Outlining, or segmenting, the prostate is a very important task in the assi gnment of appropriate therapy and dose for cancer treatment; however, manua l outlining is tedious and time-consuming. In this paper, an algorithm is d escribed for semiautomatic segmentation of the prostate from 2D ultrasound images. The algorithm uses model-based initialization and the efficient dis crete dynamic contour. Initialization requires the user to select only four points from which the outline of the prostate is estimated using cubic int erpolation functions and shape information. The estimated contour is then d eformed automatically to better fit the image. The algorithm can easily seg ment a wide range of prostate images, and contour editing tools are include d to handle more difficult cases. The performance of the algorithm with a s ingle user was compared to manual outlining by a single expert observer. Th e average distance between semiautomatically and manually outlined boundari es was found to be less than 5 pixels (0.63 mm), and the accuracy and sensi tivity to area measurements were both over 90%. (C) 2000 American Associati on of Physicists in Medicine. [S0094-2405(00)-01508-X].