Clinical adoption of deep learning target auto-segmentation for radiation therapy: challenges, clinical risks, and mitigation strategies
BJR|Artificial Intelligence · 04.03.2024 · 1 (1)
DOI: 10.1093/bjrai/ubae015 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift BJR|Artificial Intelligence, online erschienen am 25.10.2024. Verfasst von Alessia De Biase und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, University Medical Centre Groningen (UMCG), Groningen, 9700 RB, The Netherlands. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Radiation therapy is a localized cancer treatment that relies on precise delineation of the target to be treated and healthy tissues to guarantee optimal treatment effect. This step, known as contouring or segmentation, involves identifying both target volumes and organs at risk on imaging modalities like CT, PET, and MRI to guide radiation delivery. Manual segmentation, however, is time-consuming and highly subjective, despite the presence of contouring guidelines. In recent years, automated segmentation methods, particularly deep learning models, have shown promise in addressing this task. However, challenges persist in their clinical use, including the need for robust quality assurance (QA) processes and addressing clinical risks associated with the use of the models. This review examines the challenges and considerations of the clinical adoption of deep learning target auto-segmentation in radiotherapy, focused on the target volume. We discuss potential clinical risks (eg, over- and under-segmentation, automation bias, and appropriate trust), mitigation strategies (eg, human oversight, uncertainty quantification, and education of clinical professionals), and we highlight the importance of expanding QA to include geometric, dose-volume, and outcome-based performance monitoring. While deep learning target auto-segmentation offers significant potential benefits, careful attention to clinical risks and rigorous QA measures are essential for its successful integration in clinical practice.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiation Oncology, University Medical Centre Groningen (UMCG), Groningen, 9700 RB, The Netherlands.
- Data Science Centre in Health (DASH), University Medical Centre Groningen (UMCG), Groningen, 9700 RB, The Netherlands.
- Department of Radiation Oncology, The Netherlands Cancer Institute, Amsterdam, 1006 BE, The Netherlands.
- Department of Radiation Oncology, Catharina Hospital Eindhoven, Eindhoven, 5602 ZA, The Netherlands.
- Department of Electrical Engineering, Technical University Eindhoven, Eindhoven, 5600 MB, The Netherlands.
ORCID-Profile: Alessia De Biase, Nanna Maria Sijtsema, Tomas Janssen, Coen Hurkmans, Charlotte Brouwer, Peter van Ooijen
Zitieren
APA
De Biase, A., Sijtsema, N. M., Janssen, T., Hurkmans, C., Brouwer, C., & van Ooijen, P. (2024). Clinical adoption of deep learning target auto-segmentation for radiation therapy: challenges, clinical risks, and mitigation strategies. BJR|Artificial Intelligence, 1(1). https://doi.org/10.1093/bjrai/ubae015
Vancouver
De Biase A, Sijtsema NM, Janssen T, Hurkmans C, Brouwer C, van Ooijen P. Clinical adoption of deep learning target auto-segmentation for radiation therapy: challenges, clinical risks, and mitigation strategies. BJR|Artificial Intelligence. 2024;1(1). doi:10.1093/bjrai/ubae015
BibTeX
@article{DeBiase2024,
author = {De Biase, Alessia and Sijtsema, Nanna Maria and Janssen, Tomas and Hurkmans, Coen and Brouwer, Charlotte and van Ooijen, Peter},
title = {Clinical adoption of deep learning target auto-segmentation for radiation therapy: challenges, clinical risks, and mitigation strategies},
journal = {BJR|Artificial Intelligence},
year = {2024},
volume = {1},
number = {1},
doi = {10.1093/bjrai/ubae015}
}
EUVIMED