Clinical evaluation of a deep learning segmentation model including manual adjustments afterwards for locally advanced breast cancer.

Introduction: Deep learning (DL) models are increasingly developed for auto-segmentation in radiotherapy. Qualitative analysis is of great importance for clinical implementation, next to quantitative. This study evaluates a DL segmentation model for left- and right-sided locally advanced breast cancer both quantitatively and qualitatively. Methods: For each side a DL model was trained, including primary breast CTV (CTVp), lymph node levels 1-4, heart, lungs, humeral head, thyroid and esophagus. For evaluation, both automatic segmentation, including correction of contours when needed, and manual delineation was performed and both processes were timed. Quantitative scoring with dice-similarity coefficient (DSC), 95% Hausdorff Distance (95%HD) and surface DSC (sDSC) was used to compare both the automatic (not-corrected) and corrected contours with the manual contours. Qualitative scoring was performed by five radiotherapy technologists and five radiation oncologists using a 3-point Likert scale. Results: Time reduction was achieved using auto-segmentation in 95% of the cases, including correction. The time reduction (mean ± std) was 42.4% ± 26.5% and 58.5% ± 19.1% for OARs and CTVs, respectively, corresponding to an absolute mean reduction (hh:mm:ss) of 00:08:51 and 00:25:38. Good quantitative results were achieved before correction, e.g. mean DSC for the right-sided CTVp was 0.92 ± 0.06, whereas correction statistically significantly improved this contour by only 0.02 ± 0.05, respectively. In 92% of the cases, auto-contours were scored as clinically acceptable, with or without corrections. Conclusions: A DL segmentation model was trained and was shown to be a time-efficient way to generate clinically acceptable contours for locally advanced breast cancer.

Photons, protons or carbon ions for stage I non-small cell lung cancer - Results of the multicentric ROCOCO in silico study.

PURPOSE: To compare dose to organs at risk (OARs) and dose-escalation possibility for 24 stage I non-small cell lung cancer (NSCLC) patients in a ROCOCO (Radiation Oncology Collaborative Comparison) trial. METHODS: For each patient, 3 photon plans [Intensity-modulated radiotherapy (IMRT), volumetric modulated arc therapy (VMAT) and CyberKnife], a double scattered proton (DSP) and an intensity-modulated carbon-ion (IMIT) therapy plan were created. Dose prescription was 60 Gy (equivalent) in 8 fractions. RESULTS: The mean dose and dose to 2% of the clinical target volume (CTV) were lower for protons and ions compared with IMRT (p < 0.01). Doses to the lungs, heart, and mediastinal structures were lowest with IMIT (p < 0.01), doses to the spinal cord were lowest with DSP (p < 0.01). VMAT and CyberKnife allowed for reduced doses to most OARs compared with IMRT. Dose escalation was possible for 8 patients. Generally, the mediastinum was the primary dose-limiting organ. CONCLUSION: On average, the doses to the OARs were lowest using particles, with more homogenous CTV doses. Given the ability of VMAT and CyberKnife to limit doses to OARs compared with IMRT, the additional benefit of particles may only be clinically relevant in selected patients and thus should be carefully weighed for every individual patient.