Surrogate-free machine learning-based organ dose reconstruction for pediatric abdominal radiotherapy
Physics in Medicine and Biology, vol. 65, pp. 245021
Abstract
To study radiotherapy-related adverse effects, detailed dose information (3D distribution) is needed for accurate dose-effect modeling. For childhood cancer survivors who underwent radiotherapy in the pre-CT era, only 2D radiographs were acquired, thus 3D dose distributions must be reconstructed from limited information. State-of-the-art methods achieve this by using 3D surrogate anatomies. These can however lack personalization and lead to coarse reconstructions. We present and validate a surrogate-free dose reconstruction method based on Machine Learning (ML). Abdominal planning CTs (n = 142) of recently-treated childhood cancer patients were gathered, their organs at risk were segmented, and 300 artificial Wilms' tumor plans were sampled automatically. Each artificial plan was automatically emulated on the 142 CTs, resulting in 42,600 3D dose distributions from which dose-volume metrics were derived. Anatomical features were extracted from digitally reconstructed radiographs simulated from the CTs to resemble historical radiographs. Further, patient and radiotherapy plan features typically available from historical treatment records were collected. An evolutionary ML algorithm was then used to link features to dose-volume metrics. Besides 5-fold cross validation, a further evaluation was done on an independent dataset of five CTs each associated with two clinical plans. Cross-validation resulted in mean absolute errors ≤ 0.6 Gy for organs completely inside or outside the field. For organs positioned at the edge of the field, mean absolute errors ≤ 1.7 Gy for [Formula: see text], ≤ 2.9 Gy for [Formula: see text], and ≤ 13% for [Formula: see text] and [Formula: see text], were obtained, without systematic bias. Similar results were found for the independent dataset. To conclude, we proposed a novel organ dose reconstruction method that uses ML models to predict dose-volume metric values given patient and plan features. Our approach is not only accurate, but also efficient, as the setup of a surrogate is no longer needed.
Authors 14
-
Centrum Wiskunde & Informatica
Affiliation as printed
Life Sciences and Health Group, Centrum Wiskunde & Informatica, The Netherlands
shared first authorship, the two authors contributed equally to this work
Life Sciences and Health Group, Centrum Wiskunde & Informatica, the Netherlands
-
Amsterdam University Medical Centers · University of Amsterdam
Affiliation as printed
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, The Netherlands
shared first authorship, the two authors contributed equally to this work
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, the Netherlands
-
Amsterdam University Medical Centers · University of Amsterdam
Affiliation as printed
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, The Netherlands
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, the Netherlands
-
Amsterdam University Medical Centers · University of Amsterdam
Affiliation as printed
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, The Netherlands
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, the Netherlands
-
Amsterdam University Medical Centers · University of Amsterdam
Affiliation as printed
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, The Netherlands
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, the Netherlands
-
University Medical Center Utrecht
Affiliation as printed
Department of Radiotherapy, University Medical Center Utrecht, The Netherlands
Department of Radiotherapy, University Medical Center Utrecht, the Netherlands
-
University Medical Center Utrecht · Princess Máxima Center
Affiliation as printed
Department of Radiotherapy, University Medical Center Utrecht, The Netherlands
Princess Màxima Center for Pediatric Oncology, The Netherlands
Department of Radiotherapy, University Medical Center Utrecht, the Netherlands
Princess Màxima Center for Pediatric Oncology, the Netherlands
-
University of Manchester · Cancer Research UK Manchester Centre
Affiliation as printed
Manchester Cancer Research Centre, Division of Cancer Sciences, University of Manchester, United Kingdom
-
Princess Margaret Cancer Centre
Affiliation as printed
Department of Radiation Oncology, Princess Margaret Cancer Centre, Canada
-
Institute of Oncology Ljubljana
Affiliation as printed
Department of Radiation Oncology, Institute of Oncology Ljubljana, Slovenia
-
Leiden University Medical Center · Amsterdam University Medical Centers · University of Amsterdam
Affiliation as printed
Department of Radiation Oncology, Leiden University Medical Center, The Netherlands
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, the Netherlands
Department of Radiation Oncology, Leiden University Medical Center, the Netherlands
-
Amsterdam University Medical Centers · University of Amsterdam
Affiliation as printed
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, The Netherlands
-
Centrum Wiskunde & Informatica · Delft University of Technology
Affiliation as printed
Department of Software Technology, Algorithmics Group, Delft University of Technology, The Netherlands
Life Sciences and Health Group, Centrum Wiskunde & Informatica, The Netherlands
Department of Software Technology, Algorithmics Group, Delft University of Technology, the Netherlands
Life Sciences and Health Group, Centrum Wiskunde & Informatica, the Netherlands
-
Leiden University Medical Center · Amsterdam University Medical Centers · University of Amsterdam
Affiliation as printed
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, The Netherlands
Department of Radiation Oncology, Leiden University Medical Center, The Netherlands
Department of Radiation Oncology, Amsterdam UMC, University of Amsterdam, the Netherlands
Department of Radiation Oncology, Leiden University Medical Center, the Netherlands
Cited by 3 stored of 3
3 results
No patents citing this paper on Lens.org (checked 2026-10-11).