RESUMEN
Purpose: As a discipline in its infancy, online adaptive RT (ART) needs new ontologies and ad hoc criteria to evaluate the appropriateness of its use in clinical practice. In this experience, we propose a predictive model able to quantify the dosimetric impact due to daily inter-fraction variability in a standard RT breast treatment, to identify in advance the treatment fractions where patients might benefit from an online ART approach. Methods: The study was focused on right breast cancer patients treated using standard adjuvant RT on an artificial intelligence (AI)-based linear accelerator. Patients were treated with daily CBCT images and without online adaptation, prescribing 40.05 Gy in 15 fractions, with four IMRT tangential beams. ESTRO guidelines were followed for the delineation on planning CT (pCT) of organs at risk and targets. For each patient, all the CBCT images were rigidly aligned to pCT: CTV and PTV were manually re-contoured and the original treatment plan was recalculated. Various radiological parameters were measured on CBCT images, to quantify inter-fraction variability present in each RT fraction after the couch shifts compensation. The variation of these parameters was correlated with the variation of V95% of PTV (ΔV95%) using the Wilcoxon Mann-Whitney test. Fractions where ΔV95% > 2% were considered as adverse events. A logistic regression model was calculated considering the most significant parameter, and its performance was quantified with a receiver operating characteristic (ROC) curve. Results: A total of 75 fractions on 5 patients were analyzed. The body variation between daily CBCT and pCT along the beam axis with the highest MU was identified as the best predictor (p = 0.002). The predictive model showed an area under ROC curve of 0.86 (95% CI, 0.82-0.99) with a sensitivity of 85.7% and a specificity of 83.8% at the best threshold, which was equal to 3 mm. Conclusion: A novel strategy to identify treatment fractions that may benefit online ART was proposed. After image alignment, the measure of body difference between daily CBCT and pCT can be considered as an indirect estimator of V95% PTV variation: a difference larger than 3 mm will result in a V95% decrease larger than 2%. A larger number of observations is needed to confirm the results of this hypothesis-generating study.
RESUMEN
BACKGROUND: Organs at risk (OARs) delineation is a crucial step of radiotherapy (RT) treatment planning workflow. Time-consuming and inter-observer variability are main issues in manual OAR delineation, mainly in the head and neck (H & N) district. Deep-learning based auto-segmentation is a promising strategy to improve OARs contouring in radiotherapy departments. A comparison of deep-learning-generated auto-contours (AC) with manual contours (MC) was performed by three expert radiation oncologists from a single center. METHODS: Planning computed tomography (CT) scans of patients undergoing RT treatments for H&N cancers were considered. CT scans were processed by Limbus Contour auto-segmentation software, a commercial deep-learning auto-segmentation based software to generate AC. H&N protocol was used to perform AC, with the structure set consisting of bilateral brachial plexus, brain, brainstem, bilateral cochlea, pharyngeal constrictors, eye globes, bilateral lens, mandible, optic chiasm, bilateral optic nerves, oral cavity, bilateral parotids, spinal cord, bilateral submandibular glands, lips and thyroid. Manual revision of OARs was performed according to international consensus guidelines. The AC and MC were compared using the Dice similarity coefficient (DSC) and 95% Hausdorff distance transform (DT). RESULTS: A total of 274 contours obtained by processing CT scans were included in the analysis. The highest values of DSC were obtained for the brain (DSC 1.00), left and right eye globes and the mandible (DSC 0.98). The structures with greater MC editing were optic chiasm, optic nerves and cochleae. CONCLUSIONS: In this preliminary analysis, deep-learning auto-segmentation seems to provide acceptable H&N OAR delineations. For less accurate organs, AC could be considered a starting point for review and manual adjustment. Our results suggest that AC could become a useful time-saving tool to optimize workload and resources in RT departments.