深度学习联合弥散加权成像提升胶质瘤基因亚型无创分类
本研究纳入384例新诊断胶质瘤患者的术前MRI(含解剖与弥散加权成像)及147例外部队列(仅解剖成像),评估训练策略与生物学相关图像对深度学习预测IDH突变和1p19q共缺失状态的影响。最佳三分类CNN模型包含弥散加权成像,测试总体准确率达85.7%(95% CI: [77.1, 100]),三分类模型优于分层方法13.5%-17.5%。
要点
- 三分类CNN同时预测IDH突变和1p19q状态,优于先IDH后1p19q的分层策略。
- 纳入弥散加权成像(ADC)使模型准确率较仅解剖成像提高5%-8.8%。
- 最佳模型对IDHwt、IDHmut-intact、IDHmut-codel的分别正确分类95.2%、88.9%、60.0%。
核心结论
- 同时预测IDH突变和1p19q共缺失状态的三分类深度学习模型优于分层结构。
- 纳入表观弥散系数(ADC)作为细胞密度替代标志物能更准确捕捉亚组差异。
研究设计与样本
- 回顾性研究,内部数据集384例新诊断胶质瘤患者术前MRI含标准解剖和弥散加权成像。
- 外部队列147例仅含解剖成像,用于评估解剖成像模型的泛化能力。
- 以手术组织样本分类为IDH野生型、IDH突变/1p19q非共缺失、IDH突变/1p19q共缺失三个亚组。
主要发现
- 最佳模型为三分类CNN含弥散加权成像输入,测试总体准确率85.7%(95% CI: [77.1, 100])。
- 该模型正确分类95.2%的IDHwt、88.9%的IDHmut-intact、60.0%的IDHmut-codel肿瘤。
- 三分类模型总体优于分层方法13.5%-17.5%。
- 包含弥散加权成像的模型比仅用解剖成像的模型准确率高5%-8.8%。
临床怎么用
- 对于未行切除或需无创评估的胶质瘤患者,可考虑深度学习联合弥散加权成像预测基因亚型。
- 建模时应优先采用同时预测IDH和1p19q的三分类策略而非分层策略。
- 弥散加权成像(ADC)应纳入模型输入以提升亚型分类准确性。
局限性
- 外部队列仅含解剖成像,未评估含弥散加权成像模型的外部泛化能力。
- IDHmut-codel亚组的正确分类率仅60.0%,相对较低。
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)。
原文
BACKGROUND: Diagnostic classification of diffuse gliomas now requires an assessment of molecular features, often including IDH-mutation and 1p19q-codeletion status. Because genetic testing requires an invasive process, an alternative noninvasive approach is attractive, particularly if resection is not recommended. The goal of this study was to evaluate the effects of training strategy and incorporation of biologically relevant images on predicting genetic subtypes with deep learning. METHODS: Our dataset consisted of 384 patients with newly diagnosed gliomas who underwent preoperative MRI with standard anatomical and diffusion-weighted imaging, and 147 patients from an external cohort with anatomical imaging. Using tissue samples acquired during surgery, each glioma was classified into IDH-wildtype (IDHwt), IDH-mutant/1p19q-noncodeleted (IDHmut-intact), and IDH-mutant/1p19q-codeleted (IDHmut-codel) subgroups. After optimizing training parameters, top performing convolutional neural network (CNN) classifiers were trained, validated, and tested using combinations of anatomical and diffusion MRI with either a 3-class or tiered structure. Generalization to an external cohort was assessed using anatomical imaging models. RESULTS: The best model used a 3-class CNN containing diffusion-weighted imaging as an input, achieving 85.7% (95% CI: [77.1, 100]) overall test accuracy and correctly classifying 95.2%, 88.9%, 60.0% of the IDHwt, IDHmut-intact, and IDHmut-codel tumors. In general, 3-class models outperformed tiered approaches by 13.5%-17.5%, and models that included diffusion-weighted imaging were 5%-8.8% more accurate than those that used only anatomical imaging. CONCLUSION: Training a classifier to predict both IDH-mutation and 1p19q-codeletion status outperformed a tiered structure that first predicted IDH-mutation, then 1p19q-codeletion. Including apparent diffusion coefficient (ADC), a surrogate marker of cellularity, more accurately captured differences between subgroups.
引用
- Cluceru J, Interian Y, Phillips JJ, et al. Improving the noninvasive classification of glioma genetic subtype with deep learning and diffusion-weighted imaging. Neuro Oncol. 2022. PMID: 34653254. doi:10.1093/neuonc/noab238
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。