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

• Main Authors: Virgolin, M, Wang, Z, Balgobind, B. V, van Dijk, I. W. E. M, Wiersma, J, Kroon, P. S, Janssens, G. O, van Herk, M, Hodgson, D. C, Zaletel, L. Zadravec, Rasch, C. R. N, Bel, A, Bosman, P. A. N, Alderliesten, T
• Format: Journal Article
• Language: English
• Published: 10-02-2021
• Subjects: Computer Science - Learning; Physics - Medical Physics; Statistics - Machine Learning
• DOI: 10.48550/arxiv.2002.07161

Physics in Medicine & Biology. 2020 Dec 8;65(24):245021 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.