Search

(1) Purpose: We analysed overall survival (OS) rates following radiotherapy (RT) and chemo-RT of locally-advanced non-small cell lung cancer (LA-NSCLC) to investigate whether tumour repopulation varies with treatment-type, and to further characterise the low α / β ratio found in a previous study. (2) Materials and methods: Our dataset comprised 2-year OS rates for 4866 NSCLC patients (90.5% stage IIIA/B) belonging to 51 cohorts treated with definitive RT, sequential chemo-RT (sCRT) or concurrent chemo-RT (cCRT) given in doses-per-fraction ≤3 Gy over 16-60 days. Progressively more detailed dose-response models were fitted, beginning with a probit model, adding chemotherapy effects and survival-limiting toxicity, and allowing tumour repopulation and α / β to vary with treatment-type and stage. Models were fitted using the maximum-likelihood technique, then assessed via the Akaike information criterion and cross-validation. (3) Results: The most detailed model performed best, with repopulation offsetting 1.47 Gy/day (95% confidence interval, CI: 0.36, 2.57 Gy/day) for cCRT but only 0.30 Gy/day (95% CI: 0.18, 0.47 Gy/day) for RT/sCRT. The overall fitted tumour α / β ratio was 3.0 Gy (95% CI: 1.6, 5.6 Gy). (4) Conclusion: The fitted repopulation rates indicate that cCRT schedule durations should be shortened to the minimum in which prescribed doses can be tolerated. The low α / β ratio suggests hypofractionation should be efficacious.

Radiation-induced lung damage (RILD) is a common side effect of radiotherapy (RT). The ability to automatically segment, classify, and quantify different types of lung parenchymal change is essential to uncover underlying patterns of RILD and their evolution over time. A RILD dedicated tissue classification system was developed to describe lung parenchymal tissue changes on a voxel-wise level. The classification system was automated for segmentation of five lung tissue classes on computed tomography (CT) scans that described incrementally increasing tissue density, ranging from normal lung (Class 1) to consolidation (Class 5). For ground truth data generation, we employed a two-stage data annotation approach, akin to active learning. Manual segmentation was used to train a stage one auto-segmentation method. These results were manually refined and used to train the stage two auto-segmentation algorithm. The stage two auto-segmentation algorithm was an ensemble of six 2D Unets using different loss functions and numbers of input channels. The development dataset used in this study consisted of 40 cases, each with a pre-radiotherapy, 3-, 6-, 12-, and 24-month follow-up CT scans ( n = 200 CT scans). The method was assessed on a hold-out test dataset of 6 cases ( n = 30 CT scans). The global Dice score coefficients (DSC) achieved for each tissue class were: Class (1) 99% and 98%, Class (2) 71% and 44%, Class (3) 56% and 26%, Class (4) 79% and 47%, and Class (5) 96% and 92%, for development and test subsets, respectively. The lowest values for the test subsets were caused by imaging artefacts or reflected subgroups that occurred infrequently and with smaller overall parenchymal volumes. We performed qualitative evaluation on the test dataset presenting manual and auto-segmentation to a blinded independent radiologist to rate them as 'acceptable', 'minor disagreement' or 'major disagreement'. The auto-segmentation ratings were similar to the manual segmentation, both having approximately 90% of cases rated as acceptable. The proposed framework for auto-segmentation of different lung tissue classes produces acceptable results in the majority of cases and has the potential to facilitate future large studies of RILD.