[论文解读] Comparative Analysis of 2D and 3D ResNet Architectures for IDH and MGMT Mutation Detection in Glioma Patients

Danial Elyassirad, Benyamin Gheiji+6 more|arXiv (Cornell University)|Dec 30, 2024

Glioma Diagnosis and TreatmentMedicine被引用 3

一句话总结

本研究比较了使用T1、增强T1和FLAIR MRI序列进行胶质瘤患者IDH和MGMT突变状态非侵袭性预测的2D与3D ResNet架构。2D ResNet50在IDH状态预测中取得了最高的AUROC（0.9096），优于3D ResNet34（0.8999）；而3D模型在MGMT预测中表现失败，AUROC均低于0.5。

ABSTRACT

Gliomas are the most common cause of mortality among primary brain tumors. Molecular markers, including Isocitrate Dehydrogenase (IDH) and O[6]-methylguanine-DNA methyltransferase (MGMT) influence treatment responses and prognosis. Deep learning (DL) models may provide a non-invasive method for predicting the status of these molecular markers. To achieve non-invasive determination of gene mutations in glioma patients, we compare 2D and 3D ResNet models to predict IDH and MGMT status, using T1, post-contrast T1, and FLAIR MRI sequences. USCF glioma dataset was used, which contains 495 patients with known IDH and 410 patients with known MGMT status. The dataset was divided into training (60%), tuning (20%), and test (20%) subsets at the patient level. The 2D models take axial, coronal, and sagittal tumor slices as three separate models. To ensemble the 2D predictions the three different views were combined using logistic regression. Various ResNet architectures (ResNet10, 18, 34, 50, 101, 152) were trained. For the 3D approach, we incorporated the entire brain tumor volume in the ResNet10, 18, and 34 models. After optimizing each model, the models with the lowest tuning loss were selected for further evaluation on the separate test sets. The best-performing models in IDH prediction were the 2D ResNet50, achieving a test area under the receiver operating characteristic curve (AUROC) of 0.9096, and the 3D ResNet34, which reached a test AUROC of 0.8999. For MGMT status prediction, the 2D ResNet152 achieved a test AUROC of 0.6168; however, all 3D models yielded AUROCs less than 0.5. Overall, the study indicated that both 2D and 3D models showed high predictive value for IDH prediction, with slightly better performance in 2D models.

研究动机与目标

• 评估2D与3D ResNet架构在使用非侵袭性MRI预测胶质瘤患者IDH和MGMT突变状态方面的性能。
• 确定3D体素建模相较于2D轴向、冠状面和矢状面切片分析在分子标志物预测方面是否具有优势。
• 识别用于高精度、非侵袭性预测关键胶质瘤生物标志物的最优ResNet架构与模态组合。
• 评估深度学习模型在不同MRI序列和肿瘤表型之间的泛化能力与鲁棒性。

提出的方法

• 在T1、增强T1和FLAIR序列的轴向、冠状面和矢状面切片上训练多种2D ResNet变体（ResNet10、18、34、50、101、152）。
• 通过逻辑回归对三个正交视图的2D预测结果进行集成，以提高鲁棒性与泛化能力。
• 在相同MRI序列提取的完整3D肿瘤体积上训练3D ResNet变体（ResNet10、18、34）。
• 将USCF胶质瘤数据集（495例IDH，410例MGMT）按患者级别划分为训练集（60%）、验证集（20%）和测试集（20%），以防止数据泄露。
• 选择验证损失最低的模型在独立测试集上进行最终评估。
• 使用AUROC作为主要指标，评估IDH和MGMT状态预测的性能。

实验结果

研究问题

• RQ1 在胶质瘤患者中，2D或3D ResNet架构在IDH突变状态预测中哪一种表现更优？
• RQ2 与基于2D切片的模型相比，3D体素上下文的引入在MGMT状态预测中是提高了性能还是造成了阻碍？
• RQ3 在多平面切片（轴向、冠状面、矢状面）上训练的2D模型是否能实现优于使用完整3D体积的3D模型的泛化能力？
• RQ4 使用MRI数据进行IDH和MGMT状态预测时，最优的ResNet深度是什么？
• RQ5 3D ResNet模型在MGMT预测中是否表现出显著的性能下降？如果是，原因是什么？

主要发现

• 2D ResNet50在IDH突变状态预测中取得了最高的测试AUROC（0.9096），优于所有其他模型。
• 3D ResNet34在IDH状态预测中取得了0.8999的AUROC，表明性能强劲，但略低于表现最佳的2D模型。
• 所有用于MGMT状态预测的3D ResNet模型AUROC均低于0.5，表明其表现甚至差于随机猜测。
• 2D ResNet152在MGMT状态预测中取得了0.6168的AUROC，是所有模型中该生物标志物的最佳表现。
• 通过逻辑回归对三个2D视图的预测结果进行集成，提高了鲁棒性，并对表现最佳的2D模型有显著贡献。
• 本研究表明，2D模型在IDH状态预测中比3D模型更有效，而3D模型在MGMT预测中无法实现有效泛化。