The major goal of this Phase II effort is to develop an adaptive optimization and dosimetric guidance system for prostate seed implant brachytherapy, to be deployed in the operating room for real-time treatment planning and postimplant dosimetry.
The specific aims are (a) to implement accelerated genetic algorithm optimization, (b) to develop automated image segmentation and region recognition tools, and (c) to deliver real-time dosimetric verification and optimized guidance. Seed implant brachytherapy is now widely recognized as a major treatment modality for localized prostate cancer. However, conventional techniques involve three disjoined steps -pre-planning, implantation and postimplant dosimetry -all separated by 1-4 weeks. An uncertainty chain is propogated in these steps, such that any under-dosage is only discovered after the completion of treatment. For this reason, prostate brachytherapy is currently very operator-dependent. This project aims to deliver intelligent technologies in optimization and image processing to enable intraoperative planning and verification of the entire treatment in one step. By providing a what-you-see-is-what-you- get environment, clinician-users will have complete confidence of adequate dosimetry for every implant before leaving the operating room. Societal value is to be achieved through cost savings per patient and reduced local failures and/or morbidities.
PIPER will be marketed as a standalone computer treatment planning system for intraoperative dose optimization and surgical guidance in prostate seed implant brachytherapy. The target users are radiation oncologists, urologists, medical physicists, dosimetrists, and radiologists.
| Liu, Haisong; Cheng, Gang; Yu, Yan et al. (2003) Automatic localization of implanted seeds from post-implant CT images. Phys Med Biol 48:1191-203 |
