“刚刚接受”的论文已经过全面的同行评审，并已被《放射学：人工智能》接受发表。本文在最终版本发布之前将经过文案编辑、布局和校样审查。请注意，在最终编辑文章的过程中，可能会发现可能影响内容的错误。目的 使用逐步迁移学习开发、外部测试和评估深度学习 (DL) 儿科脑肿瘤分割模型的临床可接受性。材料和方法 在这项回顾性研究中，作者利用了来自国家脑肿瘤联盟的两个 T2 加权 MRI 数据集（2001 年 5 月至 2015 年 12 月）（n = 184；中位年龄，7 岁（范围：1-23 岁）；94男性）和儿科癌症中心（n = 100；中位年龄，8 岁（范围：1-19 岁）；47 名男性）使用新型逐步迁移学习方法开发和评估用于儿科低级别神经胶质瘤分割的 DL 神经网络在有限的数据场景下最大化性能。最佳模型在独立测试集上进行了外部测试，并由三名临床医生进行了随机、盲法评估，其中他们通过 10 点李克特量表和图灵测试评估了专家和人工智能 (AI) 生成的分割的临床可接受性。结果 最佳 AI 模型使用域内逐步迁移学习（中位 DSC：0.88 [IQR 0.72-0.91]，而基线模型为 0.812 [0.56-0.89]；P = .049）。在外部测试中，AI 模型使用三位临床专家的参考标准产生了出色的准确性（Expert-1：0.83 [0.75-0.90]；Expert-2：0.81 [0.70-0.89]；Expert-3：0.81 [0.68-0.88]；平均准确度：0.82))。在临床基准测试（n = 100 次扫描）中，与其他专家相比，专家对基于 AI 的分割的平均评分较高（中位 Likert 评分：中位数 9 [IQR 7-9]）与 7 [IQR 7-9]），并且对 AI 的评价更高临床上可接受的分割（80.2% 对比 65.4%）。专家平均在 26.0% 的案例中正确预测了 AI 分割的起源。结论 逐步迁移学习实现了专家级、自动化的儿科脑肿瘤自动分割和体积测量，具有较高的临床可接受性。 ©RSNA，2024。

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop, externally test, and evaluate clinical acceptability of a deep learning (DL) pediatric brain tumor segmentation model using stepwise transfer learning. Materials and Methods In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001-December 2015) from a national brain tumor consortium (n = 184; median age, 7 years (range: 1-23 years); 94 male) and a pediatric cancer center (n = 100; median age, 8 years (range: 1-19 years); 47 male) to develop and evaluate DL neural networks for pediatric low-grade glioma segmentation using a novel stepwise transfer learning approach to maximize performance in a limited data scenario. The best model was externally-tested on an independent test set and subjected to randomized, blinded evaluation by three clinicians, wherein they assessed clinical acceptability of expert- and artificial intelligence (AI)-generated segmentations via 10-point Likert scales and Turing tests. Results The best AI model used in-domain, stepwise transfer learning (median DSC: 0.88 [IQR 0.72-0.91] versus 0.812 [0.56-0.89] for baseline model; P = .049). On external testing, AI model yielded excellent accuracy using reference standards from three clinical experts (Expert-1: 0.83 [0.75-0.90]; Expert-2: 0.81 [0.70-0.89]; Expert-3: 0.81 [0.68-0.88]; mean accuracy: 0.82)). On clinical benchmarking (n = 100 scans), experts rated AI-based segmentations higher on average compared with other experts (median Likert score: median 9 [IQR 7-9]) versus 7 [IQR 7-9]) and rated more AI segmentations as clinically acceptable (80.2% versus 65.4%). Experts correctly predicted the origin of AI segmentations in an average of 26.0% of cases. Conclusion Stepwise transfer learning enabled expert-level, automated pediatric brain tumor auto-segmentation and volumetric measurement with a high level of clinical acceptability. ©RSNA, 2024.