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 , ≤ 2.9 Gy for , and ≤ 13% 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.
Highlights
Patients undergoing radiotherapy (RT) are prone to develop radiation-related Adverse Effects (AEs) (Birgisson et al 2005, van Dijk et al 2010, Cheung et al 2017)
Among the 300 artificial plans, plan side and Organs At Risk (OARs) type was found to influence the distribution of a dose-volume metric considerably
For the contralateral kidney and for the spinal cord the distributions are similar for both plan sides, as the contralateral kidney should be outside the field and the spinal cord should be included within the field
Summary
Patients undergoing radiotherapy (RT) are prone to develop radiation-related Adverse Effects (AEs) (Birgisson et al 2005, van Dijk et al 2010, Cheung et al 2017). To improve the design of future multi-modality treatments, clinicians are interested in better understanding the relationship between radiation dose and onset of AEs. Modern research efforts in this direction delve into dosimetric details, employing dose distribution metrics to a specific organ (or sub-volume) as explanatory variables. Modern research efforts in this direction delve into dosimetric details, employing dose distribution metrics to a specific organ (or sub-volume) as explanatory variables Such rich information is obtained by simulating the RT plan on 3D imaging of the patient (i.e., CT scans) with organ segmentations in a Treatment Planning System (TPS) (Donovan et al 2007, Feng et al 2007, Bolling et al 2011). 2D radiographs can be available, from which information can be gathered on the internal anatomy (mainly bony anatomy, as internal organs are normally not clearly distinguishable), and on the plan configuration with respect to the patient’s anatomy (Leisenring et al 2009, van Dijk et al 2010)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
