Surrogate-free machine learning-based organ dose reconstruction for pediatric abdominal radiotherapy

Created by W.Langdon from gp-bibliography.bib Revision:1.7810

@Article{Virgolin:2020:PMB,

• author = "M Virgolin and Ziyuan Wang and B V Balgobind and I W E M {van Dijk} and J Wiersma and P S Kroon and G O Janssens and M {van Herk} and D C Hodgson and L {Zadravec Zaletel} and C R N Rasch and A Bel and P A N Bosman and T Alderliesten",
• title = "Surrogate-free machine learning-based organ dose reconstruction for pediatric abdominal radiotherapy",
• journal = "Physics in Medicine \& Biology",
• year = "2020",
• volume = "65",
• number = "24",
• pages = "245021",
• month = dec,
• keywords = "genetic algorithms, genetic programming, cancer, CT, dose reconstruction, radiotherapy dosimetry, machine learning, planemulation, childhood cancer, late adverse effects",
• publisher = "{IOP} Publishing",
• URL = "http://www.human-competitive.org/sites/default/files/humies_entry_virgolin.txt",
• URL = "http://www.human-competitive.org/sites/default/files/virgolinpaperbpreprint.pdf",
• URL = "https://doi.org/10.1088/1361-6560/ab9fcc",
• DOI = "doi:10.1088/1361-6560/ab9fcc",
• size = "16 pages",
• 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 personalisation 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 tumour plans were sampled automatically. Each artificial plan was automatically emulated on the 142 CTs, resulting in 42600 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 less than or equal 0.6 Gy for organs completely inside or outside the field. For organs positioned at the edge of the field, mean absolute errors less than or equal 1.7 Gy for, less than or equal 2.9 Gy for, and less than or equal 13 percent for and, 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.",
• notes = "Entered 2021 HUMIES with \cite{Virgolin:2020:JMI}",

}

Genetic Programming entries for Marco Virgolin Ziyuan Wang B V Balgobind I W E M van Dijk Jan Wiersma P S Kroon Geert O Janssens M van Herk David C Hodgson Lorna Zadravec Zaletel C R N Rasch Arjan Bel Peter A N Bosman Tanja Alderliesten

Citations