A novel fully automated MRI-based deep-learning method for classification of IDH mutation status in brain gliomas.
A novel fully automated MRI-based deep-learning method for classification of IDH mutation status in brain gliomas.
复制标题
一种新颖的基于 MRI 的全自动深度学习方法，用于对脑胶质瘤 IDH 突变状态进行分类。
DOI：
10.1093/neuonc/noz199
复制
发表时间：
2020
期刊：
影响因子：
15.9
通讯作者：
Maldjian,Joseph
中科院分区：
文献类型：
--
作者：
BangaloreYogananda,ChandanGanesh;Shah,BhavyaR;Vejdani-Jahromi,Maryam;Nalawade,SahilS;Murugesan,GowthamK;Yu,FrankF;Pinho,MarcoC;Wagner,BenjaminC;Mickey,Bruce;Patel,ToralR;Fei,Baowei;Madhuranthakam,AnanthJ;Maldjian,Joseph
背景。异柠檬酸脱氢酶（IDH）突变状态已成为胶质瘤预后的重要标志。目前，可靠的IDH突变测定需要侵入性外科手术。本研究的目的是使用t2加权（T2w） MR图像开发一个高度准确的、基于mri的、体素深度学习的IDH分类网络，并将其性能与多对比网络进行比较。方法。从癌症影像档案和癌症基因组图谱中获得214名受试者（94名IDH突变型，120名IDH野生型）的多参数脑MRI数据和相应的基因组信息。开发了两个独立的网络，包括T2w图像网络（T2-net）和多重对比（T2w，流体衰减反转恢复和T1对比后）网络（TS-net），用于进行IDH分类和同时进行单标签肿瘤分割。这些网络使用3D Dense-UNets进行训练。进行了三重交叉验证，以推广网络的性能。并进行了接收机工作特性分析。计算骰子分数以确定肿瘤分割的准确性。结果。T2-net预测IDH突变状态的平均交叉验证准确率为97.14% ~ 0.04，敏感性为0.97 ~ 0.03，特异性为0.98 ~ 0.01，曲线下面积（AUC）为0.98 ~ 0.01。TS-net交叉验证的平均准确率为97.12% ~ 0.09，灵敏度为0.98 ~ 0.02，特异性为0.97 ~ 0.001，AUC为0.99 ~ 0.01。T2-net和ts -net的全肿瘤分割Dice平均评分分别为0.85 ~ 0.009和0.89 ~ 0.006。我们仅使用t2加权MR图像证明了高IDH分类精度。这是临床翻译的一个重要里程碑。
Background. Isocitrate dehydrogenase (IDH) mutation status has emerged as an important prognostic marker in gliomas. Currently, reliable IDH mutation determination requires invasive surgical procedures. The purpose of this study was to develop a highly accurate, MRI-based, voxelwise deep-learning IDH classification network using T2-weighted (T2w) MR images and compare its performance to a multicontrast network. Methods. Multiparametric brain MRI data and corresponding genomic information were obtained for 214 subjects (94 IDH-mutated, 120 IDH wild-type) from The Cancer Imaging Archive and The Cancer Genome Atlas. Two separate networks were developed, including a T2w image-only network (T2-net) and a multicontrast (T2w, fluid attenuated inversion recovery, and T1 postcontrast) network (TS-net) to perform IDH classification and simultaneous single label tumor segmentation. The networks were trained using 3D Dense-UNets. Three-fold cross-validation was performed to generalize the networks’ performance. Receiver operating characteristic analysis was also performed. Dice scores were computed to determine tumor segmentation accuracy. Results. T2-net demonstrated a mean cross-validation accuracy of 97.14% ą 0.04 in predicting IDH mutation status, with a sensitivity of 0.97 ą 0.03, specificity of 0.98 ą 0.01, and an area under the curve (AUC) of 0.98 ą 0.01. TS-net achieved a mean cross-validation accuracy of 97.12% ą 0.09, with a sensitivity of 0.98 ą 0.02, specificity of 0.97 ą 0.001, and an AUC of 0.99 ą 0.01. The mean whole tumor segmentation Dice scores were 0.85 ą 0.009 for T2-net and 0.89 ą 0.006 for TS-net.Conclusion. We demonstrate high IDH classification accuracy using only T2-weighted MR images. This represents an important milestone toward clinical translation.