A clustering‐based approach to address correlated features in predicting genitourinary toxicity from MRI‐guided prostate SBRT
These findings underscore the superiority of the clustering method in mitigating correlation bias and enhancing predictive model accuracy. The current model also achieves state of the art (SOTA) performance in predicting GU toxicity in MRI-guided prostate SBRT. Correlating dose features to feature cluster centroids reveals the importance of hot spot control on urethra, trigone, and rectal wall to reduce toxicity risk.
Authors
- Pouyan Rezapoor
- James Lamb (ORCID: https://orcid.org/0000-0002-0440-4972)
- Minsong Cao (ORCID: https://orcid.org/0000-0003-4705-6629)
- Ting Martin (ORCID: https://orcid.org/0000-0002-0053-7874)
- Dan Ruan (ORCID: https://orcid.org/0000-0003-3400-7684)
- Beth K. Neilsen (ORCID: https://orcid.org/0000-0002-4859-6486)
- Ke Sheng (ORCID: https://orcid.org/0000-0002-6696-5409)
- Hengjie Liu (ORCID: https://orcid.org/0000-0001-5890-2291)
- Michael L. Steinberg (ORCID: https://orcid.org/0000-0002-4292-5824)
- Amar U. Kishan (ORCID: https://orcid.org/0000-0002-4836-8483)
- Yingli Yang
- Jonathan Pham (ORCID: https://orcid.org/0000-0002-5676-6561)
- Zachary Taylor (ORCID: https://orcid.org/0000-0002-8729-5694)
Institutions
- University of California, Los Angeles (US)
- University of California, San Francisco (US)
- University of Washington (US)
- Ruijin Hospital (CN)
- Seattle University (US)
- Aalto University (FI)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-04-23
- DOI
- https://doi.org/10.1002/mp.17834
- Citations
- 2
- Primary Topic
- Prostate Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 3.04
Funders
- Academy of Finland
- Aalto-Yliopisto
- University of California, Los Angeles