TumorSynth:适用于任意分辨率和对比度脑MRI扫描的脑肿瘤与组织集成分割
研究开发并验证了一种深度神经网络TumorSynth,结合贝叶斯生成模型与深度学习分割模型,可在任意对比度和分辨率的MRI上同时分割脑肿瘤与解剖结构。共纳入1971例患者(训练集351例,测试集1620例),未受累脑体积和肿瘤区域的中位DSC均为0.89,跨模态验证DSC为0.79-0.88,无肿瘤MR图像假阳性率为4%。
要点
- TumorSynth在任意对比度和分辨率MRI上同时分割脑肿瘤与解剖结构,未受累脑体积和肿瘤区域中位DSC均为0.89。
- 跨模态验证中ADC图像DSC为0.88、DWI为0.85、SWI为0.80、FA为0.79。
- 处理无肿瘤MR图像时假阳性率为4%,缺失一个MRI序列时分割性能无差异(P = .07)。
核心结论
- 作者开发了一种用于脑肿瘤和组织分割的深度神经网络,在标准结构MRI序列上验证了其性能,并确定了其对未见数据的泛化能力。
研究设计与样本
- 研究纳入来自四个不同数据集的伴或不伴脑肿瘤患者的多种MRI扫描,分为训练集351例和测试集1620例;方法TumorSynth结合贝叶斯生成模型与深度学习分割模型,生成模型创建带模拟肿瘤和脑组织的配对合成标签与图像用于训练分割模型,通过计算Dice相似系数(DSC)与其他广泛使用的方法进行定量比较。
诊断标准与关键数值
- 未受累脑体积分割中位DSC为0.89(IQR 0.83-0.95,P < .001)。
- 肿瘤区域分割中位DSC为0.89(IQR 0.84-0.94,P < .001)。
- 跨模态验证DSC:表观扩散系数图像0.88,扩散加权成像0.85,磁敏感加权成像0.80,各向异性分数图像0.79。
- 处理无肿瘤MR图像时假阳性率为4%。
- 缺失一个MRI序列时分割性能无差异(P = .07)。
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
Purpose To develop and validate a deep neural network that simultaneously segments brain tumors and anatomic structures, regardless of the contrast and resolution of the input scans, and can effortlessly adapt to unseen modalities. Materials and Methods The authors included various MRI scans from patients with and without brain tumors from four different datasets. Patient data were divided into a training set and a test set. The authors' method, TumorSynth, combines a Bayesian generative model and a deep learning segmentation model. The generative model creates paired synthetic labels and images with simulated tumors and brain tissues, providing a rich dataset for training the segmentation model. The authors quantitatively compared its performance with that of other widely used methods by calculating Dice similarity coefficients (DSCs). Results A total of 1971 patients with and without tumors were included in the study (training set, n = 351 patients; test set, n = 1620 patients). The median DSCs for segmentation (authors' method vs reference standard) were 0.89 (IQR, 0.83-0.95; P < .001) for the unaffected brain volume and 0.89 (IQR, 0.84-0.94; P < .001) for the tumor region. There were no differences in parcellation performance when an MRI sequence was missing (P = .07). In cross-modality validation, the authors' method achieved DSC values of 0.88 for apparent diffusion coefficient, 0.85 for diffusion-weighted imaging, 0.80 for susceptibility-weighted imaging, and 0.79 for fractional anisotropy images. The authors observed a 4% false-positive rate when processing tumor-free MR images. Conclusion The authors developed a deep neural network for brain tumor and tissue segmentation, validated its performance across standard structural MRI sequences, and determined its generalizability to unseen data. Keywords: Segmentation, Neuro-Oncology, CNS, Deep Learning, Neurosurgery Supplemental material is available online for this article. © RSNA, 2026.
引用
- Wu J, Billot B, Zhao F, et al. TumorSynth: Integrated Brain Tumor and Tissue Segmentation on Brain MRI Scans of Any Resolution and Contrast. Radiol Imaging Cancer. 2026. PMID: 41891822. doi:10.1148/rycan.250222
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。