Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China.
School of Computer Science and Engineering, Chongqing Normal University, Chongqing, 401331, China.
Eur Radiol. 2024 Jan;34(1):391-399. doi: 10.1007/s00330-023-09944-y. Epub 2023 Aug 8.
To develop a high-accuracy MRI-based deep learning method for predicting cyclin-dependent kinase inhibitor 2A/B (CDKN2A/B) homozygous deletion status in isocitrate dehydrogenase (IDH)-mutant astrocytoma.
Multiparametric brain MRI data and corresponding genomic information of 234 subjects (111 positives for CDKN2A/B homozygous deletion and 123 negatives for CDKN2A/B homozygous deletion) were obtained from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA) respectively. Two independent multi-sequence networks (ResFN-Net and FN-Net) are built on the basis of ResNet and ConvNeXt network combined with attention mechanism to classify CDKN2A/B homozygous deletion status using MR images including contrast-enhanced T1-weighted imaging (CE-T1WI) and T2-weighted imaging (T2WI). The performance of the network is summarized by three-way cross-validation; ROC analysis is also performed.
The average cross-validation accuracy (ACC) of ResFN-Net is 0.813. The average cross-validation area under curve (AUC) of ResFN-Net is 0.8804. The average cross-validation ACC and AUC of FN-Net is 0.9236 and 0.9704, respectively. Comparing all sequence combinations of the two networks (ResFN-Net and FN-Net), the sequence combination of CE-T1WI and T2WI performed the best, and the ACC and AUC were 0.8244, 0.8975 and 0.8971, 0.9574, respectively.
The FN-Net deep learning networks based on ConvNeXt network achieved promising performance for predicting CDKN2A/B homozygous deletion status of IDH-mutant astrocytoma.
A novel deep learning network (FN-Net) based on preoperative MRI was developed to predict the CDKN2A/B homozygous deletion status. This network has the potential to be a practical tool for the noninvasive characterization of CDKN2A/B in glioma to support personalized classification and treatment planning.
• CDKN2A/B homozygous deletion status is an important marker for glioma grading and prognosis. • An MRI-based deep learning approach was developed to predict CDKN2A/B homozygous deletion status. • The predictive performance based on ConvNeXt network was better than that of ResNet network.
开发一种基于磁共振成像（MRI）的深度学习方法，用于预测异柠檬酸脱氢酶（IDH）突变型星形细胞瘤中环细胞周期蛋白依赖性激酶抑制剂 2A/B（CDKN2A/B）纯合缺失状态。
从癌症影像档案（TCIA）和癌症基因组图谱（TCGA）中分别获得 234 名患者的多参数脑 MRI 数据和相应的基因组信息（111 名 CDKN2A/B 纯合缺失阳性，123 名 CDKN2A/B 纯合缺失阴性）。在 ResNet 和 ConvNeXt 网络的基础上分别构建两个独立的多序列网络（ResFN-Net 和 FN-Net），并结合注意力机制，利用包括增强对比 T1 加权成像（CE-T1WI）和 T2 加权成像（T2WI）在内的 MRI 图像对 CDKN2A/B 纯合缺失状态进行分类。通过三向交叉验证总结网络性能；同时进行 ROC 分析。
ResFN-Net 的平均交叉验证准确率（ACC）为 0.813。ResFN-Net 的平均交叉验证曲线下面积（AUC）为 0.8804。FN-Net 的平均交叉验证 ACC 和 AUC 分别为 0.9236 和 0.9704。比较两个网络（ResFN-Net 和 FN-Net）的所有序列组合，CE-T1WI 和 T2WI 的序列组合表现最佳，ACC 和 AUC 分别为 0.8244、0.8975 和 0.8971、0.9574。
基于 ConvNeXt 网络的 FN-Net 深度学习网络在预测 IDH 突变型星形细胞瘤 CDKN2A/B 纯合缺失状态方面取得了有前景的性能。
开发了一种基于术前 MRI 的新的深度学习网络（FN-Net），用于预测 CDKN2A/B 纯合缺失状态。该网络有可能成为胶质瘤中 CDKN2A/B 无创特征的实用工具，以支持个性化分类和治疗计划。
• CDKN2A/B 纯合缺失状态是胶质瘤分级和预后的重要标志物。• 开发了一种基于磁共振成像的深度学习方法来预测 CDKN2A/B 纯合缺失状态。• 基于 ConvNeXt 网络的预测性能优于 ResNet 网络。
