The delineation of dominant intraprostatic gross tumor volumes (GTVs) on multi-parametric magnetic resonance imaging (mpMRI) can be subject to inter-observer variability. We evaluated whether deep learning artificial intelligence (AI)-segmented GTVs can provide a similar degree of intraprostatic boosting with external beam radiation therapy (EBRT) as radiation oncologist (RO)-delineated GTVs.
We identified 124 patients who underwent mpMRI followed by EBRT between 2010-2013. A reference GTV was delineated by a RO, and approved by a board-certified radiologist. We trained an AI algorithm for GTV delineation on 89 patients, and tested the algorithm on 35 patients, each with at least 1 PI-RADS 4-5 lesion (46 total lesions). We then asked 5 additional ROs to independently delineate GTVs on the test set. We compared lesion detectability and geometric accuracy of the GTVs from AI and 5 ROs against the reference GTV. Then, we generated EBRT plans (77Gy prostate) that boosted each observer-specific GTV to 95 Gy. We compared reference GTV dose (D98%) across observers utilizing a mixed-effects model.
On a lesion-level, AI GTV exhibited a sensitivity of 82.6% and positive predictive value of 86.4%. Respective ranges among the 5 RO GTVs were 84.8%-95.7% and 95.1%-100.0%. Among 30 GTVs mutually identified by all observers, no significant differences in Dice coefficient were detected between AI and any of the 5 ROs. Across all patients, only 2 of 5 ROs had a reference GTV D98% that significantly differed from that of AI by 2.56 (p = 0.02) and 3.20 (p = 0.003) Gy. The presence of false negative (-5.97 Gy; p < 0.001), but not false positive (p = 0.24) lesions was associated with reference GTV D98%.
AI-segmented GTVs demonstrate potential for intraprostatic boosting, though the degree of boosting may be adversely impacted by false negative lesions. Prospective review of AI-segmented GTVs remains essential.
International journal of radiation oncology, biology, physics. 2023 Jul 28 [Epub ahead of print]
James M G Tsui, Christopher E Kehayias, Jonathan E Leeman, Paul L Nguyen, Luke Peng, David D Yang, Shalini Moningi, Neil Martin, Peter F Orio, Anthony V D'Amico, Jeremy S Bredfeldt, Leslie K Lee, Christian V Guthier, Martin T King
Department of Radiation Oncology, Brigham and Women's Hospital/Dana-Farber Cancer Institute, Boston, MA, 02115; Department of Radiation Oncology, McGill University Health Centre, Montreal, QC H4A 3J1., Department of Radiation Oncology, Brigham and Women's Hospital/Dana-Farber Cancer Institute, Boston, MA, 02115., Department of Radiology, Brigham and Women's Hospital/Dana-Farber Cancer Institute, Boston, MA, 02115., Department of Radiation Oncology, Brigham and Women's Hospital/Dana-Farber Cancer Institute, Boston, MA, 02115. Electronic address: .
PubMed http://www.ncbi.nlm.nih.gov/pubmed/37517600