ESTRO 2025 - Abstract Book

S3417

Physics - Machine learning models and clinical applications

ESTRO 2025

Conclusion: Analysis indicates that in routine clinical practice, AIO treatment plans achieved clinical treatment standards without manual intervention in approximately 81.2% of cases. Furthermore, oncologists typically preferred expansions over contractions when contouring the PTV, especially at the boundary between the PTV and rectal area.

Keywords: all-in-one, automated planning, dosimetric metric

References: Almeida, G., & Tavares, J. M. R. S. (2020). Deep Learning in Radiation Oncology Treatment Planning for Prostate Cancer: A Systematic Review. Journal of medical systems , 44 (10), 179. https://doi.org/10.1007/s10916-020-01641-3 Bilimagga, R. S., Anchineyan, P., Nmugam, M. S., Thalluri, S., & Goud, P. S. K. (2022). Autodelineation of organ at risk in head and neck cancer radiotherapy using artificial intelligence. Journal of cancer research and therapeutics , 18 (Supplement), S141 – S145. https://doi.org/10.4103/jcrt.JCRT_1069_20