Author ORCID Identifier
Date of Graduation
Doctor of Philosophy (PhD)
Steven J. Frank
Mark D. Pagel
Rajat J. Kudchadker
Aradhana M. Venkatesan
David T. A. Fuentes
Prostate cancer is the second most common cancer in men and the second-leading cause of cancer death in men. Brachytherapy is a highly effective treatment option for prostate cancer, and is the most cost-effective initial treatment among all other therapeutic options for low to intermediate risk patients of prostate cancer. In low-dose-rate (LDR) brachytherapy, verifying the location of the radioactive seeds within the prostate and in relation to critical normal structures after seed implantation is essential to ensuring positive treatment outcomes.
One current gap in knowledge is how to simultaneously image the prostate, surrounding anatomy, and radioactive seeds within the prostate after implantation for subsequent dosimetry using MRI. This would enable MRI to be used throughout the entire LDR prostate brachytherapy treatment workflow. A second gap in knowledge is how to accurately and automatically identify and localize the implanted radioactive seeds in the post-implant MRI. Such a technology would reduce the time and expertise required to perform seed localization for post-implant dosimetry. A third gap in knowledge is how to accurately and automatically contour the prostate and surrounding anatomy in the post-implant MRI, which would help streamline the process for performing post-implant dosimetry.
The research conducted attempts to fill the current gaps in knowledge by: (1) developing an MRI pulse sequence and acquisition protocol that enables high resolution and high SNR MRIs of the implanted radioactive seed markers, prostate, and surrounding anatomy with a single pulse sequence (using fully balanced steady-state free precession) and without an encdorectal coil for post-implant quality assessment; (2) developing a computer vision technique for automatically identifying the implanted radioactive seeds in post-implant MRIs; and (3) developing a computer vision technique to automatically contour the prostate, rectum, seminal vesicles, external urinary sphincter, and bladder in post-implant MRIs. These developments would mitigate the uncertainties with the use of MRI in the post-implant setting, reduce the barriers for the utilization of MRI in post-implant quality assessment, reduce the time and resources required to perform post-implant quality assessment with precision, and help expand the access of MRI-assited radiosurgery (MARS) for LDR prostate brachytherapy from major academic hospitals to the community setting.
MRI, prostate, brachytherapy, low-dose-rate, deep learning, machine learning, compressed sensing, parallel imaging, image quality
Artificial Intelligence and Robotics Commons, Biomedical Engineering and Bioengineering Commons, Data Science Commons, Medical Biophysics Commons, Numerical Analysis and Scientific Computing Commons, Radiation Medicine Commons, Radiology Commons, Signal Processing Commons, Software Engineering Commons, Translational Medical Research Commons