Direct integration of deep learning–based GTV auto-segmentation into a clinical radiotherapy planning system

Physics and Imaging in Radiation Oncology 2026 Open access

Read full text
Authors: Bao Ngoc Huynh, Cecilia Marie Futsaether, Oliver Tomić, Kristian Hovde Liland, Manish Kakar, Taran Paulsen Hellebust, Eirik Malinen, Einar Dale, Karsten Rydén-Eilertsen
DOI: 10.1016/j.phro.2026.100962
Cited by: 1
References: 20

Abstract

Manual Gross Tumor Volume (GTV) delineation for radiotherapy is time‑consuming and prone to inter‑observer variability. Deep Learning (DL)-based auto‑segmentation offers faster and more consistent solutions, but translation into clinical practice remains limited. This study aimed to bridge this gap by integrating an in‑house GTV auto‑segmentation DL model into a radiotherapy Treatment Planning System (TPS). To demonstrate the integration process, a head‑and‑neck GTV segmentation model was successfully deployed and operated seamlessly within the TPS. In this integration, DL‑generated GTV contours were produced in under three minutes, demonstrating the feasibility of DL‑based GTV segmentation in the TPS without disrupting the radiotherapy workflow.

Fields of Study & Subjects

Advanced Radiotherapy Techniques Advanced Neural Network Applications Prostate Cancer Diagnosis and Treatment

Publication details

Journal / source
Physics and Imaging in Radiation Oncology
Publisher
Elsevier BV
Volume
38
Pages
100962–100962
Publication date
1 March 2026
Language
EN