Abstract
PurposeWe developed a deep learning model to achieve automatic multitarget delineation on planning CT (pCT) and synthetic CT (sCT) images generated from cone-beam CT (CBCT) images. The geometric and dosimetric impact of the model was evaluated for breast cancer adaptive radiation therapy.MethodsWe retrospectively analyzed 1,127 patients treated with radiotherapy after breast-conserving surgery from two medical institutions. The CBCT images for patient setup acquired utilizing breath-hold guided by optical surface monitoring system were used to generate sCT with a generative adversarial network. Organs at risk (OARs), clinical target volume (CTV), and tumor bed (TB) were delineated automatically with a 3D U-Net model on pCT and sCT images. The geometric accuracy of the model was evaluated with metrics, including Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95). Dosimetric evaluation was performed by quick dose recalculation on sCT images relying on gamma analysis and dose-volume histogram (DVH) parameters. The relationship between ΔD95, ΔV95 and DSC-CTV was assessed to quantify the clinical impact of the geometric changes of CTV.ResultsThe ranges of DSC and HD95 were 0.73–0.97 and 2.22–9.36 mm for pCT, 0.63–0.95 and 2.30–19.57 mm for sCT from institution A, 0.70–0.97 and 2.10–11.43 mm for pCT from institution B, respectively. The quality of sCT was excellent with an average mean absolute error (MAE) of 71.58 ± 8.78 HU. The mean gamma pass rate (3%/3 mm criterion) was 91.46 ± 4.63%. DSC-CTV down to 0.65 accounted for a variation of more than 6% of V95 and 3 Gy of D95. DSC-CTV up to 0.80 accounted for a variation of less than 4% of V95 and 2 Gy of D95. The mean ΔD90/ΔD95 of CTV and TB were less than 2Gy/4Gy, 4Gy/5Gy for all the patients. The cardiac dose difference in left breast cancer cases was larger than that in right breast cancer cases.ConclusionsThe accurate multitarget delineation is achievable on pCT and sCT via deep learning. The results show that dose distribution needs to be considered to evaluate the clinical impact of geometric variations during breast cancer radiotherapy.
Highlights
Intensity-modulated radiotherapy (IMRT) after breastconserving surgery significantly improves the survival of breast cancer patients [1]
We developed a deep learning model to achieve automatic multitarget delineation on planning computed tomography (CT) and synthetic CT images generated from conebeam CT (CBCT) images
We investigated the relationship between the Dice similarity coefficient (DSC) and the dose difference to evaluate the effect of anatomical changes on dose during radiotherapy. synthetic CT (sCT) images were rigidly registered to planning CT (pCT) by reference to the bony landmarks
Summary
Intensity-modulated radiotherapy (IMRT) after breastconserving surgery significantly improves the survival of breast cancer patients [1]. Large interfraction variation is observed, motivating the need for adaptive radiotherapy. Adaptive radiotherapy can automatically adjust the plan according to changes in the target volume [6, 7]. When the patient is lying on the couch waiting for treatment, plan evaluation and adaptation need to be completed as quickly as possible. Online adaptation, which requires real-time delineation of the contours of the target volumes and organs at risk (OARs) for re-planning, is a promising technique [8]. Conebeam CT (CBCT) is a common tool for location verification in radiotherapy and can be used for plan adaptation [14, 15]. Imaging artifacts caused by respiratory movement make CBCT-based adaptive radiotherapy for breast cancer infeasible. CBCT images cannot be directly used for dose calculation due to inaccurate HU values and needs to be converted into synthetic CT for dosimetric evaluation [16,17,18,19]
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
