Purpose To study radiation-induced esophageal expansion as an objective measure of radiation esophagitis in patients with non-small-cell lung cancer (NSCLC) treated with IMRT. Methods and Materials Eighty-five patients had weekly intra-treatment CT imaging and esophagitis scoring according to Common Toxicity Criteria for Adverse Events 4.0, (24 Grade0, 45 Grade2, and 16 Grade3). Nineteen esophageal expansion metrics based on mean, maximum, spatial length, and volume of expansion were calculated as voxel-based relative volume change, using the Jacobian determinant from deformable image registration between the planning and weekly CTs. An anatomic variability correction method was validated and applied to these metrics to reduce uncertainty. An analysis of expansion metrics and radiation esophagitis grade was conducted using normal tissue complication probability (NTCP) from univariate logistic regression and Spearman rank for grade 2 and grade 3 esophagitis endpoints, as well as the timing of expansion and esophagitis grade. Metrics’ performance in classifying esophagitis was tested with Receiver Operating Characteristic (ROC) analysis. Results Expansion increased with esophagitis grade. Thirteen of nineteen expansion metrics had ROC area under the curve (AUC) values >0.80 for both grade 2 and grade 3 esophagitis endpoints, with the highest performance from maximum axial expansion (MaxExp1) and esophageal length with axial expansion ≥30% (LenExp30%) with AUCs of 0.93 and 0.91 for grade2, 0.90 and 0.90 for grade3 esophagitis, respectively. Conclusions Esophageal expansion may be a suitable objective measure of esophagitis, particularly maximum axial esophageal expansion and esophageal length with axial expansion ≥30%, with 2.1 Jacobian Value and 98.6mm as the metric value for 50% probability of grade3 esophagitis. The uncertainty in esophageal Jacobian calculations can be reduced with anatomic correction methods.

No abstract

Background: Typically, cardiac substructures are neither delineated nor analyzed during radiation treatment planning. Therefore, we developed a novel machine learning model to evaluate the impact of cardiac substructure dose for predicting radiation-induced pericardial effusion (PCE). Materials and methods: One-hundred and forty-one stage III NSCLC patients, who received radiation therapy in a prospective clinical trial, were included in this analysis. The impact of dose-volume histogram (DVH) metrics (mean and max dose, V5Gy[%]-V70Gy[%]) for the whole heart, left and right atrium, and left and right ventricle, on pericardial effusion toxicity (!grade 2, CTCAE v4.0 grading) were examined. Elastic net logistic regression, using repeat cross-validation (n ¼ 100 iterations, 75%/ 25% training/test set data split), was conducted with cardiac-based DVH metrics as covariates. The following model types were constructed and analyzed: (i) standard model type, which only included whole-heart DVH metrics; and (ii) a model type trained with both whole-heart and substructure DVH metrics. Model performance was analyzed on the test set using area under the curve (AUC), accuracy, calibration slope and calibration intercept. A final fitted model, based on the optimal model type, was developed from the entire study population for future comparisons. Results: Grade 2 PCE incidence was 49.6% (n ¼ 70). Models using whole heart and substructure dose had the highest performance (median values: AUC ¼ 0.820; calibration slope/intercept ¼ 1.356/ À0.235; accuracy ¼ 0.743) and outperformed the standard whole-heart only model type (median values: AUC ¼ 0.799; calibration slope/intercept ¼ 2.456/À0.729; accuracy ¼ 0.713). The final fitted elastic net model showed high performance in predicting PCE (median values: AUC ¼ 0.879; calibration slope/intercept ¼ 1.352/À0.174; accuracy ¼ 0.801). Conclusions: We developed and evaluated elastic net regression toxicity models of radiation-induced PCE. We found the model type that included cardiac substructure dose had superior predictive performance. A final toxicity model that included cardiac substructure dose metrics was developed and reported for comparison with external datasets.

Manually delineating upper abdominal organs at risk (OARs) is a time-consuming task. To develop a deep-learning-based tool for accurate and robust auto-segmentation of these OARs, forty pancreatic cancer patients with contrast-enhanced breath-hold computed tomographic (CT) images were selected. We trained a three-dimensional (3D) U-Net ensemble that automatically segments all organ contours concurrently with the self-configuring nnU-Net framework. Our tool’s performance was assessed on a held-out test set of 30 patients quantitatively. Five radiation oncologists from three different institutions assessed the performance of the tool using a 5-point Likert scale on an additional 75 randomly selected test patients. The mean (± std. dev.) Dice similarity coefficient values between the automatic segmentation and the ground truth on contrast-enhanced CT images were 0.80 ± 0.08, 0.89 ± 0.05, 0.90 ± 0.06, 0.92 ± 0.03, 0.96 ± 0.01, 0.97 ± 0.01, 0.96 ± 0.01, and 0.96 ± 0.01 for the duodenum, small bowel, large bowel, stomach, liver, spleen, right kidney, and left kidney, respectively. 89.3% (contrast-enhanced) and 85.3% (non-contrast-enhanced) of duodenum contours were scored as a 3 or above, which required only minor edits. More than 90% of the other organs’ contours were scored as a 3 or above. Our tool achieved a high level of clinical acceptability with a small training dataset and provides accurate contours for treatment planning.