Association between Artificial Intelligence-Derived Tumor Volume and Oncologic Outcomes for Localized Prostate Cancer Treated with Radiation Therapy

Background: Although clinical features of multi-parametric magnetic resonance imaging (mpMRI) have been associated with biochemical recurrence in localized prostate cancer, such features are subject to inter-observer variability. Objective: To evaluate whether the volume of the dominant intraprostatic lesion (DIL), as provided by a deep learning segmentation algorithm, could provide prognostic information for patients treated with definitive radiation therapy (RT). Design, Setting, and Participants: Retrospective study of 438 patients with localized prostate cancer who underwent an endorectal coil, high B-value, 3-Tesla mpMRI and were treated with RT between 2010 and 2017. Intervention: RT. Outcome Measurements and Statistical Analysis: Biochemical recurrence and metastasis risk, assessed with a cause-specific Cox regression and time-dependent receiver operating characteristic analysis. Results and Limitations: The artificial intelligence (AI) model identified DILs with an area under the receiver operating characteristic curve (AUROC) of 0.827 at the patient level. For the 233 patients with available PI-RADS scores, with a median follow-up of 5.6 years, AI-defined DIL volume was significantly associated with biochemical failure (adjusted hazard ratio 1.54, 95% confidence interval 1.09-2.17, p=0.014) after adjustment for PI-RADS score. Among all 438 patients with a median follow-up of 6.9 years, the AUROC for predicting 7-year biochemical failure for AI volume (0.790) was similar to that for an expanded National Comprehensive Cancer Network (NCCN+) category (p=0.17). The AUROC for predicting 7-year metastasis for AI volume trended towards being higher compared to NCCN+ categories (0.854 vs 0.769, p=0.06). Conclusions: A deep learning algorithm could identify the DIL with good performance. AI-defined DIL volume may be able to provide prognostic information independent of the NCCN+ risk group or other radiologic factors for patients with localized prostate cancer treated with RT. ### Competing Interest Statement Jonathan Leeman: research funding from ViewRay and NH TherAguix, outside this work Kent Mouw: advisory board for Riva Therapeutics and UroGen; honoraria from UpToDate; research funding from Pfizer; and ownership equity for Riva Therapeutics, all outside this work Peter Orio: personal fees from Palette Life Sciences and Theragenics, outside this work Paul Nguyen: advisory board for Blue Earth, Boston Scientific, Bayer, Novartis, and Nanocan; research funding from Janssen and Astellas; and ownership equity for Nanocan and Telerad Oncology, outside this work Martin King: research funding from Palette Life Sciences and Bayer, outside this work ### Funding Statement This study was not funded by an outside entity. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: IRB of Dana-Farber/Harvard Cancer Center gave ethical approval for this work. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors.