TY - JOUR
T1 - Surrogate-free machine learning-based organ dose reconstruction for pediatric abdominal radiotherapy
AU - Virgolin, Marco
AU - Wang, Ziyuan
AU - Balgobind, Brian
AU - van Dijk, Irma
AU - Wiersma, Jan
AU - Kroon, Petra S
AU - Janssens, Geert O
AU - van Herk, Marcel
AU - Hodgson, David C
AU - Zadravec Zaletel, Lorna
AU - Rasch, Coen
AU - Bel, Arjan
AU - Bosman, Peter A N
AU - Alderliesten, Tanja
N1 - Publisher Copyright:
© 2020 Institute of Physics and Engineering in Medicine.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/12/21
Y1 - 2020/12/21
N2 - 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.
AB - 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.
KW - childhood cancer
KW - dose reconstruction
KW - late adverse effects
KW - machine learning
KW - plan emulation
KW - radiotherapy dosimetry
UR - http://www.scopus.com/inward/record.url?scp=85098290973&partnerID=8YFLogxK
U2 - 10.1088/1361-6560/ab9fcc
DO - 10.1088/1361-6560/ab9fcc
M3 - Article
C2 - 32580177
SN - 0031-9155
VL - 65
SP - 1
EP - 16
JO - Physics in medicine and biology
JF - Physics in medicine and biology
IS - 24
M1 - 245021
ER -