当应用于特定中心时，中心间数据之间的固有差异可能会破坏分割模型的稳健性（数据集偏移）。我们研究了与基于多中心数据的通才模型相比，专门的中心特定模型是否更有效，以及中心特定数据如何使用微调迁移学习方法来增强特定中心内通才模型的性能。为此，我们研究了中心级别的数据集偏移，并进行了比较分析，以评估数据源对胶质母细胞瘤分割模型的影响。研究了数据集偏移的三个关键组成部分：先验概率偏移-肿瘤大小或组织分布的变化中心之间；协变量中心间 MRI 变化；和概念转变——肿瘤分割的不同标准。使用 BraTS 2021 数据集，其中包括来自 23 个中心的 1251 个病例。此后，开发并比较了 155 个深度学习模型，包括 1）使用多中心数据训练的通用模型，2）仅使用特定中心数据的专用模型，以及 3）使用特定中心数据进行微调的通用模型。描述了数据集转变的三个关键组成部分。协变量偏移量很大，表明不同中心之间的 MR 成像存在很大差异。当使用来自应用中心的数据时，胶质母细胞瘤分割模型往往表现最佳。通才模型经过 700 多个样本的训练，Dice 得分中位数为 88.98%。专业模型以 200 个案例超过了这一数字，而微调模型以 50 个案例超越了这一数字。数据集变化对模型性能的影响是显而易见的。利用来自评估中心的数据进行微调和专门的模型，其性能优于依赖于其他中心的数据的通才模型。这些方法可以鼓励医疗中心开发供本地使用的定制模型，在数据集转移不可避免的情况下提高胶质母细胞瘤分割的准确性和可靠性。版权所有 © 2024 作者。由 Elsevier B.V. 出版。保留所有权利。

Inherent variations between inter-center data can undermine the robustness of segmentation models when applied at a specific center (dataset shift). We investigated whether specialized center-specific models are more effective compared to generalist models based on multi-center data, and how center-specific data could enhance the performance of generalist models within a particular center using a fine-tuning transfer learning approach. For this purpose, we studied the dataset shift at center level and conducted a comparative analysis to assess the impact of data source on glioblastoma segmentation models.The three key components of dataset shift were studied: prior probability shift-variations in tumor size or tissue distribution among centers; covariate shift-inter-center MRI alterations; and concept shift-different criteria for tumor segmentation. BraTS 2021 dataset was used, which includes 1251 cases from 23 centers. Thereafter, 155 deep-learning models were developed and compared, including 1) generalist models trained with multi-center data, 2) specialized models using only center-specific data, and 3) fine-tuned generalist models using center-specific data.The three key components of dataset shift were characterized. The amount of covariate shift was substantial, indicating large variations in MR imaging between different centers. Glioblastoma segmentation models tend to perform best when using data from the application center. Generalist models, trained with over 700 samples, achieved a median Dice score of 88.98%. Specialized models surpassed this with 200 cases, while fine-tuned models outperformed with 50 cases.The influence of dataset shift on model performance is evident. Fine-tuned and specialized models, utilizing data from the evaluated center, outperform generalist models, which rely on data from other centers. These approaches could encourage medical centers to develop customized models for their local use, enhancing the accuracy and reliability of glioblastoma segmentation in a context where dataset shift is inevitable.Copyright © 2024 The Authors. Published by Elsevier B.V. All rights reserved.