需要改进对复发性鼻咽癌（NPC）在随访磁共振（MR）扫描中的检测准确性。在三个癌症中心，回顾性收集了2007年4月至2020年7月间的5035名接受治疗的NPC幸存者的5035次随访MR扫描，以开发和评估深度学习（DL）模型MODERN（基于MR的复发性鼻咽癌检测深度学习模型）。通过220次扫描的读者研究，评估了两名放射科医师在具有和不具有MODERN的扫描中检测复发的准确性。性能通过受试者工作特征曲线下面积（ROC-AUC）和具有95%的置信区间（CI）的准确性来衡量。MODERN在验证组中表现出良好的性能（内部：ROC-AUC，0.88，95% CI，0.86-0.90；外部1：ROC-AUC，0.88，95% CI，0.86-0.90；外部2：ROC-AUC，0.85，95% CI，0.82-0.88）。在读者研究中，MODERN单独实现了可靠的准确性，相比之下，放射科医生的准确性（MODERN：84.1%，95% CI，79.3%-88.9%；能干的：80.9%，95% CI，75.7%-86.1%，P < 0.001；专家的：85.9%，95% CI，81.3%-90.5%，P < 0.001）受到MODERN评分的提升（有MODERN评分的能干者：84.6%，95% CI，79.8%-89.3%，P < 0.001；有MODERN评分的专家：87.7%，95% CI，83.4%-92.1%，P < 0.001）。我们开发了一种具有可靠性表现的DL模型用于复发性检测。计算机和人类的协作有潜力改进对接受治疗的NPC患者的随访MR扫描解读工作流程。© 2023 Elsevier B.V. 保留一切权利。

Accuracy in the detection of recurrent nasopharyngeal carcinoma (NPC) on follow-up magnetic resonance (MR) scans needs to be improved.A total of 5 035 follow-up MR scans from 5 035 survivors with treated NPC between April 2007 and July 2020 were retrospectively collected from three cancer centers for developing and evaluating the deep learning (DL) model MODERN (MR-based Deep learning model for dEtecting Recurrent Nasopharyngeal carcinoma). In a reader study with 220 scans, the accuracy of two radiologists in detecting recurrence on scans with vs without MODERN was evaluated. The performance was measured using the area under the receiver operating characteristic curve (ROC-AUC) and accuracy with a 95% confidence interval (CI).MODERN exhibited sound performance in the validation cohort (internal: ROC-AUC, 0.88, 95% CI, 0.86-0.90; external 1: ROC-AUC, 0.88, 95% CI, 0.86-0.90; external 2: ROC-AUC, 0.85, 95% CI, 0.82-0.88). In a reader study, MODERN alone achieved reliable accuracy compared to that of radiologists (MODERN: 84.1%, 95% CI, 79.3%-88.9%; competent: 80.9%, 95% CI, 75.7%-86.1%, P < 0.001; expert: 85.9%, 95% CI, 81.3%-90.5%, P < 0.001). The accuracy of radiologists was boosted by the MODERN score (competent with MODERN score: 84.6%, 95% CI, 79.8%-89.3%, P < 0.001; expert with MODERN score: 87.7%, 95% CI, 83.4%-92.1%, P < 0.001).We developed a DL model for recurrence detection with reliable performance. Computer-human collaboration has the potential to refine the workflow in interpreting surveillant MR scans among patients with treated NPC.Copyright © 2023 Elsevier B.V. All rights reserved.