To validate the accuracy and clinical value of a novel semi-supervised learning (SSL) framework for gross tumor volume (GTV) delineation in nasopharyngeal carcinoma (NPC).258 patients with MRI datasets were divided into training (n = 180), validation (n = 20), and testing (n = 58) cohorts. Ground truth contours of nasopharynx gross tumor volume (GTVnx) and node gross tumor volume (GTVnd) were manually delineated by two experienced radiation oncologists. 20% (n = 36) labeled and 80% (n = 144) unlabeled images were used to train model, producing model-generated contours for patients from testing cohort. Nine experienced experts were invited to revise model-generated GTV in randomly selected 20 patients from testing cohort. Six junior oncologists were asked to delineate GTV in randomly selected 12 patients from testing cohort without and with assistance of the model, and compared revision degrees under these two modes. The Dice similarity coefficient (DSC) was used to quantify the accuracy of the model.The model generated-contours showed a high accuracy when compared with ground truth contours, with an average DSC score of 0.83 and 0.80 for GTVnx and GTVnd, respectively. There was no significant difference in DSC score between T1-2 and T3-4 patients (0.81 vs. 0.83, p = 0.223), or between N1-2 and N3 patients (0.80 vs. 0.79, p = 0.807). The mean revision degree was lower than 10% in 19 (95%) patients for GTVnx, and in 16 (80%) patients for GTVnd. With assistance of the model, the mean revision degree for GTVnx and GTVnd by junior oncologists reduced from 25.63% to 7.75%, and from 21.38% to 14.44%, respectively. Meanwhile, the delineating efficiency was improved by over 60%.The proposed SSL based model showed a high accuracy for delineating GTV of NPC. It was clinically applicable and could assist junior oncologists improving GTV contouring accuracy and saving contouring time.Copyright © 2022. Published by Elsevier Inc.