Can Deep Learning-Based Auto-Contouring Software Achieve Accurate Pelvic Volume Delineation in Volumetric Image-Guided Radiotherapy for Prostate Cancer? A Preliminary Multicentric Analysis

Can Deep Learning-Based Auto-Contouring Software Achieve Accurate Pelvic Volume Delineation in Volumetric Image-Guided Radiotherapy for Prostate Cancer? A Preliminary Multicentric Analysis

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 investi...

Full description

Saved in:
Bibliographic Details
Main Authors: Cristiano Grossi, Fernando Munoz, Ilaria Bonavero, Eulalie Joelle Tondji Ngassam, Elisabetta Garibaldi, Claudia Airaldi, Elena Celia, Daniela Nassisi, Andrea Brignoli, Elisabetta Trino, Lavinia Bianco, Silvia Leardi, Diego Bongiovanni, Chiara Valero, Maria Grazia Ruo Redda
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Current Oncology
Subjects:
auto-contouring
organs at risk
deep learning
segmentation
prostate cancer
pelvic lymph nodes
Online Access:https://www.mdpi.com/1718-7729/32/6/321
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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<sup>®</sup> Contour<sup>®</sup> (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.
ISSN:1198-0052
1718-7729

Similar Items