Abstract

Validation of computer-aided detection and intervention procedures for prostate cancer is still a challenging issue. Despite the increasing accuracy of prostate image analysis tools, in vivo and in silico validations are necessary before they can be deployed in clinical routine. In this study, we developed a statistical atlas of prostate morphology for construction of realistic digital and physical phantoms. We have been interested in modeling the gland's zonal anatomy as defined by the peripheral zone and the central gland. Magnetic Resonance Imaging studies from 30 patients were used. Mean shape and most relevant deformations for prostate structures were computed using principal component analysis. The resulting statistical atlas has been used in image simulation and the design of a physical phantom of the prostate.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call