基于影像的放射学搜索:利用MRI放射组学特征识别数据库中的脑肿瘤亚型
本研究纳入295例2000至2021年间接受手术和/或放疗的原发性脑肿瘤患者,回顾性提取MRI放射组学特征,将数据集分为参考集和查询集,通过降维聚类参考病例并检索最近邻。t-SNE(6个成分)表现最佳,按肿瘤类型的平均精度均值(k=5)为78%-100%;前5个检索参考病例与查询病例视觉相似性高(76%评为「相似」或「非常相似」)。
要点
- 基于MRI放射组学特征的影像搜索可检索与查询病例视觉相似的历史参考病例。
- t-SNE(6个成分)是表现最佳的降维技术,按肿瘤类型的平均精度均值(k=5)为78%-100%。
- 前5个检索参考病例中76%被专家评为与查询病例「相似」或「非常相似」。
核心结论
- 作者提出一种基于影像的搜索方法,用于探索原发性脑肿瘤的历史MR图像并获取与查询病例高度相似的参考病例;专家神经放射科医生的肿瘤类型比较和视觉相似性Likert评分验证了该方法的有效性。
研究设计与样本
- 回顾性研究,纳入295例2000至2021年间接受手术和/或放疗的原发性脑肿瘤患者(平均年龄±标准差,51±20岁),采用半自动卷积神经网络肿瘤分割并提取放射组学特征,数据集分为参考集和查询集,对参考病例进行降维聚类,将查询病例的放射组学特征投影到聚类参考病例上并检索最近邻。
诊断标准与关键数值
- 检索性能采用平均精度均值(k)评估;t-SNE(6个成分)为表现最佳的降维技术,按肿瘤类型的平均精度均值(k=5)为78%-100%;专家读者采用5点Likert量表独立评定视觉相似性,前5个检索参考病例与相应查询病例的视觉相似性高(76%评为「相似」或「非常相似」)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND AND PURPOSE: Existing neuroradiology reference materials do not cover the full range of primary brain tumor presentations, and text-based medical image search engines are limited by the lack of consistent structure in radiology reports. To address this, an image-based search approach is introduced here, leveraging an institutional database to find reference MRIs visually similar to presented query cases.
MATERIALS AND METHODS: Two hundred ninety-five patients (mean age and standard deviation, 51 ± 20 years) with primary brain tumors who underwent surgical and/or radiotherapeutic treatment between 2000 and 2021 were included in this retrospective study. Semiautomated convolutional neural network-based tumor segmentation was performed, and radiomic features were extracted. The data set was split into reference and query subsets, and dimensionality reduction was applied to cluster reference cases. Radiomic features extracted from each query case were projected onto the clustered reference cases, and nearest neighbors were retrieved. Retrieval performance was evaluated by using mean average precision at k, and the best-performing dimensionality reduction technique was identified. Expert readers independently rated visual similarity by using a 5-point Likert scale.
RESULTS: t-Distributed stochastic neighbor embedding with 6 components was the highest-performing dimensionality reduction technique, with mean average precision at 5 ranging from 78%-100% by tumor type. The top 5 retrieved reference cases showed high visual similarity Likert scores with corresponding query cases (76% 'similar' or 'very similar').
CONCLUSIONS: We introduce an image-based search method for exploring historical MR images of primary brain tumors and fetching reference cases closely resembling queried ones. Assessment involving comparison of tumor types and visual similarity Likert scoring by expert neuroradiologists validates the effectiveness of this method.
引用
- von Reppert M, Chadha S, Willms K, et al. Image-Based Search in Radiology: Identification of Brain Tumor Subtypes within Databases Using MRI-Based Radiomic Features. AJNR Am J Neuroradiol. 2025. PMID: 40250848. doi:10.3174/ajnr.A8805
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。