Evaluation of deep learning-based auto-segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients.

OBJECTIVE: To evaluate the accuracy of a deep learning-based auto-segmentation mode to that of manual contouring by one medical resident, where both entities tried to mimic the delineation "habits" of the same clinical senior physician. METHODS: This study included 125 cervical cancer patients whose clinical target volumes (CTVs) and organs at risk (OARs) were delineated by the same senior physician. Of these 125 cases, 100 were used for model training and the remaining 25 for model testing. In addition, the medical resident instructed by the senior physician for approximately 8 months delineated the CTVs and OARs for the testing cases. The dice similarity coefficient (DSC) and the Hausdorff Distance (HD) were used to evaluate the delineation accuracy for CTV, bladder, rectum, small intestine, femoral-head-left, and femoral-head-right. RESULTS: The DSC values of the auto-segmentation model and manual contouring by the resident were, respectively, 0.86 and 0.83 for the CTV (P < 0.05), 0.91 and 0.91 for the bladder (P > 0.05), 0.88 and 0.84 for the femoral-head-right (P < 0.05), 0.88 and 0.84 for the femoral-head-left (P < 0.05), 0.86 and 0.81 for the small intestine (P < 0.05), and 0.81 and 0.84 for the rectum (P > 0.05). The HD (mm) values were, respectively, 14.84 and 18.37 for the CTV (P < 0.05), 7.82 and 7.63 for the bladder (P > 0.05), 6.18 and 6.75 for the femoral-head-right (P > 0.05), 6.17 and 6.31 for the femoral-head-left (P > 0.05), 22.21 and 26.70 for the small intestine (P > 0.05), and 7.04 and 6.13 for the rectum (P > 0.05). The auto-segmentation model took approximately 2 min to delineate the CTV and OARs while the resident took approximately 90 min to complete the same task. CONCLUSION: The auto-segmentation model was as accurate as the medical resident but with much better efficiency in this study. Furthermore, the auto-segmentation approach offers additional perceivable advantages of being consistent and ever improving when compared with manual approaches.

A Nomogram for Predicting the Risk of Radiotherapy-Related Esophageal Fistula in Esophageal Cancer Patients.

BACKGROUND: To construct and validate a nomogram for predicting the risk of esophageal fistula in esophageal cancer patients receiving radiotherapy. METHODS: A retrospective nested case-control study was performed, in which a total of 81 esophageal fistula patients and 243 controls from 2014 to 2020 in the First Affiliated Hospital of Anhui Medical University were enrolled. Factors included in the nomogram were determined by univariate and multiple logistic regression analysis. The following methods including ROC curve, C-index, calibration curves, Brier score, and decision curve analysis (DCA) were adopted to evaluate this nomogram. RESULTS: Multivariate logistic regression analysis showed that T4 stage, level 4 stenosis, ulcerative esophageal cancer, prealbumin, and maximum diameters of GTV and NLR were the independent risk factors of esophageal fistula. Accordingly, a nomogram incorporating the aforementioned six parameters was constructed. The AUC was 0.848 (95% CI 0.901-0.895), indicating a high prediction accuracy of this nomogram. Further evaluation of this model showed that the C-index was 0.847, while the bias-corrected C-index after internal validation was 0.833. The Brier score was 0.127. The calibration curves presented good concordance, and the DCA revealed promising clinical application. CONCLUSIONS: The nomogram presents accurate and applicable prediction for the esophageal fistula risk in esophageal cancer patients receiving radiotherapy.