Guidance on selecting and evaluating AI auto-segmentation systems in clinical radiotherapy: insights from a six-vendor analysis
Physical and Engineering Sciences in Medicine · 2025-03 · 48 (1) · 301-316
DOI: 10.1007/s13246-024-01513-x ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical and Engineering Sciences in Medicine, online erschienen am 13.01.2025. Verfasst von Branimir Rusanov und 16 weiteren Autor:innen. Beteiligte Einrichtung: School of Physics, Mathematics and Computing, The University of Western Australia, Crawley, WA, Australia. branimir.rusanov@research.uwa.edu.au. Hauptthemen laut MEDLINE: Artificial Intelligence, Commerce, Radiotherapy. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Government, University of Western Australia.
Abstract (Originalsprache)
Artificial Intelligence (AI) based auto-segmentation has demonstrated numerous benefits to clinical radiotherapy workflows. However, the rapidly changing regulatory, research, and market environment presents challenges around selecting and evaluating the most suitable solution. To support the clinical adoption of AI auto-segmentation systems, Selection Criteria recommendations were developed to enable a holistic evaluation of vendors, considering not only raw performance but associated risks uniquely related to the clinical deployment of AI. In-house experience and key bodies of work on ethics, standards, and best practices for AI in Radiation Oncology were reviewed to inform selection criteria and evaluation strategies. A retrospective analysis using the criteria was performed across six vendors, including a quantitative assessment using five metrics (Dice, Hausdorff Distance, Average Surface Distance, Surface Dice, Added Path Length) across 20 head and neck, 20 thoracic, and 19 male pelvis patients for AI models as of March 2023. A total of 47 selection criteria were identified across seven categories. A retrospective analysis showed that overall no vendor performed exceedingly well, with systematically poor performance in Data Security & Responsibility, Vendor Support Tools, and Transparency & Ethics. In terms of raw performance, vendors varied widely from excellent to poor. As new regulations come into force and the scope of AI auto-segmentation systems adapt to clinical needs, continued interest in ensuring safe, fair, and transparent AI will persist. The selection and evaluation framework provided herein aims to promote user confidence by exploring the breadth of clinically relevant factors to support informed decision-making.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Physics, Mathematics and Computing, The University of Western Australia, Crawley, WA, Australia. branimir.rusanov@research.uwa.edu.au.
- Department of Radiation Oncology, Sir Charles Gairdner Hospital, Nedlands, WA, Australia. branimir.rusanov@research.uwa.edu.au.
- Center for Advanced Technologies in Cancer Research, Perth, WA, Australia. branimir.rusanov@research.uwa.edu.au.
- School of Physics, Mathematics and Computing, The University of Western Australia, Crawley, WA, Australia.
- Department of Radiation Oncology, Sir Charles Gairdner Hospital, Nedlands, WA, Australia.
- Center for Advanced Technologies in Cancer Research, Perth, WA, Australia.
Förderung
- Australian Government
- University of Western Australia
Zitieren
APA
Rusanov, B., Ebert, M. A., Sabet, M., Rowshanfarzad, P., Barry, N., Kendrick, J., Alkhatib, Z., Gill, S., Dass, J., Bucknell, N., Croker, J., Tang, C., White, R., Bydder, S., Taylor, M., Slama, L., & Mukwada, G. (2025). Guidance on selecting and evaluating AI auto-segmentation systems in clinical radiotherapy: insights from a six-vendor analysis. Physical and Engineering Sciences in Medicine, 48(1), 301-316. https://doi.org/10.1007/s13246-024-01513-x
Vancouver
Rusanov B, Ebert MA, Sabet M, Rowshanfarzad P, Barry N, Kendrick J, et al. Guidance on selecting and evaluating AI auto-segmentation systems in clinical radiotherapy: insights from a six-vendor analysis. Physical and Engineering Sciences in Medicine. 2025;48(1):301-316. doi:10.1007/s13246-024-01513-x
BibTeX
@article{Rusanov2025,
author = {Rusanov, Branimir and Ebert, Martin A and Sabet, Mahsheed and Rowshanfarzad, Pejman and Barry, Nathaniel and Kendrick, Jake and Alkhatib, Zaid and Gill, Suki and Dass, Joshua and Bucknell, Nicholas and Croker, Jeremy and Tang, Colin and White, Rohen and Bydder, Sean and Taylor, Mandy and Slama, Luke and Mukwada, Godfrey},
title = {Guidance on selecting and evaluating AI auto-segmentation systems in clinical radiotherapy: insights from a six-vendor analysis},
journal = {Physical and Engineering Sciences in Medicine},
year = {2025},
volume = {48},
number = {1},
pages = {301--316},
doi = {10.1007/s13246-024-01513-x}
}
EUVIMED