https://doi.org/10.1140/epjp/s13360-024-05660-8
Review
Perspectives for using artificial intelligence techniques in radiation therapy
1
Department of Radiation Oncology, LMU University Hospital, LMU Munich, Marchioninistrasse 15, 81377, Munich, Bavaria, Germany
2
German Cancer Consortium (DKTK), partner site Munich, a partnership between DKFZ and LMU University Hospital Munich, Marchioninistrasse 15, 81377, Munich, Bavaria, Germany
3
Bavarian Cancer Research Center (BZKF), Marchioninistrasse 15, 81377, Munich, Bavaria, Germany
a
guillaume.landry@med.uni-muenchen.de
Received:
6
February
2024
Accepted:
14
September
2024
Published online:
9
October
2024
The integration of artificial intelligence (AI) techniques into radiation therapy (RT) represents a unique opportunity to significantly enhance accuracy, efficiency and outcomes of radiation treatments. This article addresses the comprehensive application of AI across various stages of the RT workflow, highlighting its potential to transform RT from the initial treatment planning to treatment delivery. We explore the advancements AI-driven algorithms offer in automatic segmentation of organs-at-risk and target volumes, which are critical for optimizing dose distributions. The generation and application of synthetic computed tomography (CT) images for cone-beam CT-based adaptive RT and magnetic resonance imaging (MRI)-guided RT are discussed in detail, emphasizing AI’s capability in image correction and translation. Moreover, the article examines AI’s role in dose calculation and treatment planning and how AI techniques can contribute to motion management during treatment delivery. In a concluding outlook section, future directions and opportunities for AI techniques in RT are discussed.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
