越来越多的研究表明，利用从成像数据中提取的放射组学特征来预测各种恶性肿瘤的组织学或遗传信息的能力。本研究旨在研究基于 MRI 的放射组学通过内部和外部验证预测脑转移的原发肿瘤，使用过采样技术来解决类别不平衡问题。这项 IRB 批准的回顾性多中心研究包括肺癌、黑色素瘤、乳腺癌的脑转移、结直肠癌和其他主要实体的组合异质组（5 级分类）。本地数据是在 2003 年至 2021 年间从 231 名患者（545 个转移灶）获得的。分别对来自公开的斯坦福 BrainMetShare 和加州大学旧金山脑转移立体定向放射外科数据集的 82 名患者（280 个转移瘤）和 258 名患者（809 个转移瘤）进行了外部验证。预处理包括大脑提取、偏差校正、配准、强度标准化和半手动二元肿瘤分割。从每个序列的 T1w（± 对比度）、流体衰减反演恢复 (FLAIR) 和小波变换（8 次分解）中提取了 2528 个放射组学特征。使用原始数据和过采样数据（5 倍交叉验证）上的选定特征对随机森林分类器进行训练，并使用准确度、精确度、召回率、F1 分数和接收者操作特征曲线下面积对内部/外部保留测试集进行评估（ AUC）。过采样并没有改善内部和外部测试集上总体不令人满意的性能。不正确的数据划分（训练/验证/测试分割之前的过采样）会导致模型性能的大幅高估。应严格评估放射组学模型从成像中预测组织学或基因组数据的能力；外部验证至关重要。© 作者 2024。由牛津大学出版社、神经肿瘤学会和欧洲神经肿瘤学会出版。

Growing research demonstrates the ability to predict histology or genetic information of various malignancies using radiomic features extracted from imaging data. This study aimed to investigate MRI-based radiomics in predicting the primary tumor of brain metastases through internal and external validation, using oversampling techniques to address the class imbalance.This IRB-approved retrospective multicenter study included brain metastases from lung cancer, melanoma, breast cancer, colorectal cancer, and a combined heterogenous group of other primary entities (5-class classification). Local data were acquired between 2003 and 2021 from 231 patients (545 metastases). External validation was performed with 82 patients (280 metastases) and 258 patients (809 metastases) from the publicly available Stanford BrainMetShare and the University of California San Francisco Brain Metastases Stereotactic Radiosurgery datasets, respectively. Preprocessing included brain extraction, bias correction, coregistration, intensity normalization, and semi-manual binary tumor segmentation. Two-thousand five hundred and twenty-eight radiomic features were extracted from T1w (± contrast), fluid-attenuated inversion recovery (FLAIR), and wavelet transforms for each sequence (8 decompositions). Random forest classifiers were trained with selected features on original and oversampled data (5-fold cross-validation) and evaluated on internal/external holdout test sets using accuracy, precision, recall, F1 score, and area under the receiver-operating characteristic curve (AUC).Oversampling did not improve the overall unsatisfactory performance on the internal and external test sets. Incorrect data partitioning (oversampling before train/validation/test split) leads to a massive overestimation of model performance.Radiomics models' capability to predict histologic or genomic data from imaging should be critically assessed; external validation is essential.© The Author(s) 2024. Published by Oxford University Press, the Society for Neuro-Oncology and the European Association of Neuro-Oncology.