Can Deep Learning-Based Auto-Contouring Software Achieve Accurate Pelvic Volume Delineation in Volumetric Image-Guided Radiotherapy for Prostate Cancer? A Preliminary Multicentric Analysis
Current Oncology · 2025
DOI: 10.3390/curroncol32060321 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Current Oncology, 2025. Verfasst von Cristiano Grossi und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oncology, University of Turin School of Medicine, 10126 Turin, Italy. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Deep Learning, Radiotherapy, Image-Guided, Pelvis. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Radiotherapy (RT) is a mainstay treatment for prostate cancer (PC). Accurate delineation of organs at risk (OARs) is crucial for optimizing the therapeutic window by minimizing side effects. Manual segmentation is time-consuming and prone to inter-operator variability. This study investigates the performance of Limbus® Contour® (LC), a deep learning-based auto-contouring software, in delineating pelvic structures in PC patients.
Methods
We evaluated LC’s performance on key structures (bowel bag, bladder, rectum, sigmoid colon, and pelvic lymph nodes) in 52 patients. We compared auto-contoured structures with those manually delineated by radiation oncologists using different metrics.
Results
LC achieved good agreement for the bladder (median Dice: 0.95) and rectum (median Dice: 0.83). However, limitations were observed for the bowel bag (median Dice: 0.64) and sigmoid colon (median Dice: 0.6), with inclusion of irrelevant structures. While the median Dice for pelvic lymph nodes was acceptable (0.73), the software lacked sub-regional differentiation, limiting its applicability in certain other oncologic settings.
Conclusions
LC shows promise for automating OAR delineation in prostate radiotherapy, particularly for the bladder and rectum. Improvements are needed for bowel bag, sigmoid colon, and lymph node sub-regionalization. Further validation with a broader and larger patient cohort is recommended to assess generalizability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Oncology, University of Turin School of Medicine, 10126 Turin, Italy.
- Department of Radiation Oncology, Umberto Parini Hospital, 11100 Aosta, Italy.
- Department of Radiation Oncology, Mauriziano Umberto I Hospital, 10128 Turin, Italy.
- Department of Medical Physics, Mauriziano Umberto I Hospital, 10128 Turin, Italy.
- Department Oncology, University of Turin School of Medicine, Mauriziano Umberto I Hospital, 10128 Turin, Italy.
ORCID-Profile: Fernando Munoz, Andrea Brignoli, Maria Grazia Ruo Redda
Zitieren
APA
Grossi, C., Munoz, F., Bonavero, I., Ngassam, E. J. T., Garibaldi, E., Airaldi, C., Celia, E., Nassisi, D., Brignoli, A., Trino, E., Bianco, L., Leardi, S., Bongiovanni, D., Valero, C., & Redda, M. G. R. (2025). Can Deep Learning-Based Auto-Contouring Software Achieve Accurate Pelvic Volume Delineation in Volumetric Image-Guided Radiotherapy for Prostate Cancer? A Preliminary Multicentric Analysis. Current Oncology. https://doi.org/10.3390/curroncol32060321
Vancouver
Grossi C, Munoz F, Bonavero I, Ngassam EJT, Garibaldi E, Airaldi C, et al. Can Deep Learning-Based Auto-Contouring Software Achieve Accurate Pelvic Volume Delineation in Volumetric Image-Guided Radiotherapy for Prostate Cancer? A Preliminary Multicentric Analysis. Current Oncology. 2025. doi:10.3390/curroncol32060321
BibTeX
@article{Grossi2025,
author = {Grossi, Cristiano and Munoz, Fernando and Bonavero, Ilaria and Ngassam, Eulalie Joelle Tondji and Garibaldi, Elisabetta and Airaldi, Claudia and Celia, Elena and Nassisi, Daniela and Brignoli, Andrea and Trino, Elisabetta and Bianco, Lavinia and Leardi, Silvia and Bongiovanni, Diego and Valero, Chiara and Redda, Maria Grazia Ruo},
title = {Can Deep Learning-Based Auto-Contouring Software Achieve Accurate Pelvic Volume Delineation in Volumetric Image-Guided Radiotherapy for Prostate Cancer? A Preliminary Multicentric Analysis},
journal = {Current Oncology},
year = {2025},
doi = {10.3390/curroncol32060321}
}
EUVIMED