Bangalore Yogananda Chandan Ganesh, Wagner Benjamin C, Truong Nghi C D, Holcomb James M, Reddy Divya D, Saadat Niloufar, Hatanpaa Kimmo J, Patel Toral R, Fei Baowei, Lee Matthew D, Jain Rajan, Bruce Richard J, Pinho Marco C, Madhuranthakam Ananth J, Maldjian Joseph A
Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
Department of Pathology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
Bioengineering (Basel). 2023 Sep 5;10(9):1045. doi: 10.3390/bioengineering10091045.
Isocitrate dehydrogenase (IDH) mutation status has emerged as an important prognostic marker in gliomas. This study sought to develop deep learning networks for non-invasive IDH classification using T2w MR images while comparing their performance to a multi-contrast network. Methods: Multi-contrast brain tumor MRI and genomic data were obtained from The Cancer Imaging Archive (TCIA) and The Erasmus Glioma Database (EGD). Two separate 2D networks were developed using , a T2w-image-only network (T2-net) and a multi-contrast network (MC-net). Each network was separately trained using TCIA (227 subjects) or TCIA + EGD data (683 subjects combined). The networks were trained to classify IDH mutation status and implement single-label tumor segmentation simultaneously. The trained networks were tested on over 1100 held-out datasets including 360 cases from UT Southwestern Medical Center, 136 cases from New York University, 175 cases from the University of Wisconsin-Madison, 456 cases from EGD (for the TCIA-trained network), and 495 cases from the University of California, San Francisco public database. A receiver operating characteristic curve (ROC) was drawn to calculate the AUC value to determine classifier performance. Results: T2-net trained on TCIA and TCIA + EGD datasets achieved an overall accuracy of 85.4% and 87.6% with AUCs of 0.86 and 0.89, respectively. MC-net trained on TCIA and TCIA + EGD datasets achieved an overall accuracy of 91.0% and 92.8% with AUCs of 0.94 and 0.96, respectively. We developed reliable, high-performing deep learning algorithms for IDH classification using both a T2-image-only and a multi-contrast approach. The networks were tested on more than 1100 subjects from diverse databases, making this the largest study on image-based IDH classification to date.
异柠檬酸脱氢酶（IDH）突变状态已成为神经胶质瘤重要的预后标志物。本研究旨在利用T2加权磁共振（MR）图像开发用于非侵入性IDH分类的深度学习网络，并将其性能与多对比度网络进行比较。方法：多对比度脑肿瘤MRI和基因组数据来自癌症影像存档库（TCIA）和伊拉斯谟神经胶质瘤数据库（EGD）。使用仅T2加权图像网络（T2网络）和多对比度网络（MC网络）开发了两个独立的二维网络。每个网络分别使用TCIA（227名受试者）或TCIA + EGD数据（共683名受试者）进行训练。训练网络对IDH突变状态进行分类，并同时实施单标签肿瘤分割。在超过1100个保留数据集上对训练好的网络进行测试，这些数据集包括来自德克萨斯大学西南医学中心的360例、来自纽约大学的136例、来自威斯康星大学麦迪逊分校的175例、来自EGD的456例（用于TCIA训练的网络）以及来自加利福尼亚大学旧金山分校公共数据库的495例。绘制受试者工作特征曲线（ROC）以计算AUC值来确定分类器性能。结果：在TCIA和TCIA + EGD数据集上训练的T2网络总体准确率分别为85.4%和87.6%，AUC分别为0.86和0.89。在TCIA和TCIA + EGD数据集上训练的MC网络总体准确率分别为91.0%和92.8%，AUC分别为0.94和0.96。我们使用仅T2图像和多对比度方法开发了用于IDH分类的可靠、高性能深度学习算法。这些网络在来自不同数据库的1100多名受试者上进行了测试，使其成为迄今为止基于图像的IDH分类的最大规模研究。
