Training, validation, and clinical implementation of a deep-learning segmentation model for radiotherapy of loco-regional breast cancer.

Autor: Almberg SS; Department of Radiotherapy, Cancer Clinic, St. Olavs Hospital, Trondheim, Norway. Electronic address: sigrun.saur.almberg@stolav.no., Lervåg C; Department of Oncology, Ålesund Hospital, Ålesund, Norway., Frengen J; Department of Radiotherapy, Cancer Clinic, St. Olavs Hospital, Trondheim, Norway., Eidem M; Department of Radiotherapy, Cancer Clinic, St. Olavs Hospital, Trondheim, Norway., Abramova TM; Department of Oncology, Ålesund Hospital, Ålesund, Norway., Nordstrand CS; Department of Oncology, Ålesund Hospital, Ålesund, Norway., Alsaker MD; Department of Radiotherapy, Cancer Clinic, St. Olavs Hospital, Trondheim, Norway., Tøndel H; Department of Radiotherapy, Cancer Clinic, St. Olavs Hospital, Trondheim, Norway., Raj SX; Department of Radiotherapy, Cancer Clinic, St. Olavs Hospital, Trondheim, Norway., Wanderås AD; Department of Radiotherapy, Cancer Clinic, St. Olavs Hospital, Trondheim, Norway.
Jazyk: angličtina
Zdroj: Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology [Radiother Oncol] 2022 Aug; Vol. 173, pp. 62-68. Date of Electronic Publication: 2022 May 23.
DOI: 10.1016/j.radonc.2022.05.018
Abstrakt: Aim: To train and validate a comprehensive deep-learning (DL) segmentation model for loco-regional breast cancer with the aim of clinical implementation.
Methods: DL segmentation models for 7 clinical target volumes (CTVs) and 11 organs at risk (OARs) were trained on 170 left-sided breast cancer cases from two radiotherapy centres in Norway. Another 30 patient cases were used for validation, which included the evaluation of Dice similarity coefficient and Hausdorff distance, qualitative scoring according to clinical usability, and relevant dosimetric parameters. The manual inter-observer variation (IOV) was also evaluated and served as a benchmark. Delineation of the target volumes followed the ESTRO guidelines.
Results: Based on the geometric similarity metrics, the model performed significantly better than IOV for most structures. Qualitatively, no or only minor corrections were required for 14% and 71% of the CTVs and 72% and 26% of the OARs, respectively. Major corrections were required for 15% of the CTVs and 2% of the OARs. The most frequent corrections occurred in the cranial and caudal parts of the structures. The dose coverage, based on D98 > 95%, was fulfilled for 100% and 89% of the breast and lymph node CTVs, respectively. No differences in OAR dose parameters were considered clinically relevant. The model was implemented in a commercial treatment planning system, which generates the structures in 1.5 min.
Conclusion: Convincing results from the validation led to the decision of clinical implementation. The clinical use will be monitored regarding applicability, standardization and efficiency.
(Copyright © 2022 Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: