Surrogate-free machine learning-based organ dose reconstruction for pediatric abdominal radiotherapy
| Autor: | Tanja Alderliesten, Marco Virgolin, L. Zadravec Zaletel, Petra S. Kroon, Jan Wiersma, D.C. Hodgson, Peter A. N. Bosman, C. R. N. Rasch, M. van Herk, I. W. E. M. van Dijk, Ziyuan Wang, Arjan Bel, Geert O. Janssens, Brian V. Balgobind |
|---|---|
| Přispěvatelé: | Graduate School, Radiotherapy, CCA - Cancer Treatment and Quality of Life |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Male
FOS: Computer and information sciences Computer Science - Machine Learning Radiography medicine.medical_treatment Childhood cancer FOS: Physical sciences Machine Learning (stat.ML) Dose distribution dose reconstruction Radiation Dosage Machine learning computer.software_genre Cross-validation Machine Learning (cs.LG) Statistics - Machine Learning radiotherapy dosimetry Neoplasms Humans Medicine childhood cancer Radiology Nuclear Medicine and imaging Abdominal radiotherapy late adverse effects Child Radiological and Ultrasound Technology business.industry Radiotherapy Planning Computer-Assisted Radiotherapy Dosage Physics - Medical Physics Reconstruction method Radiation therapy machine learning Female Artificial intelligence Metric (unit) Medical Physics (physics.med-ph) Tomography X-Ray Computed business computer plan emulation |
| Zdroj: | Physics in Medicine and Biology, 65(24) Physics in Medicine & Biology, 65(24). IOP PUBLISHING LTD Virgolin, M, Wang, Z, Balgobind, B, Dijk, I V, Wiersma, J, Kroon, P S, Janssens, G O, Van Herk, M, Hodgson, D C, Zaletel, L Z, Rasch, C, Bel, A, Bosman, P A N & Alderliesten, T 2020, ' Surrogate-free machine learning-based organ dose reconstruction for pediatric abdominal radiotherapy ', Physics in Medicine and Biology . https://doi.org/10.1088/1361-6560/ab9fcc Physics in medicine and biology, 65(24):245021. IOP Publishing Ltd. |
| ISSN: | 1361-6560 0031-9155 |
| DOI: | 10.1088/1361-6560/ab9fcc |
| Popis: | 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 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 (MAEs) $\leq$0.6 Gy for organs completely inside or outside the field. For organs positioned at the edge of the field, MAEs $\leq$1.7 Gy for D$_{mean}$, $\leq$2.9 Gy for D$_{2cc}$, and $\leq$13% for V$_{5Gy}$ and V$_{10Gy}$, were obtained, without systematic bias. Similar results were found for the independent dataset. Our novel, ML-based organ dose reconstruction method is not only accurate but also efficient, as the setup of a surrogate is no longer needed. Comment: M. Virgolin and Z. Wang share first authorship |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|