Deep wavelet scattering orthogonal fusion network for glioma IDH mutation status prediction

• Published in: Computers in biology and medicine 2023-11, Vol.166, p.107493, Article 107493
• Main Authors: Chen, Qijian, Wang, Lihui, Xing, Zhiyang, Wang, Li, Hu, Xubin, Wang, Rongpin, Zhu, Yue-Min
• Format: Article
• Language: English
• Subjects: Ablation; Brain Neoplasms - diagnostic imaging; Brain Neoplasms - genetics; Cancer; Computer Science; Datasets; Feature extraction; Glioma; Glioma - diagnostic imaging; Glioma - genetics; Gliomas; Humans; IDH mutation status; Isocitrate dehydrogenase; Isocitrate Dehydrogenase - genetics; Life Sciences; Machine learning; Magnetic Resonance Imaging; Medical Imaging; Modules; Multi-center; Multimodal information fusion; Mutation; Neurons and Cognition; Orthogonal projection; Predictions; Scattering; Wavelet Analysis; Wavelet scattering
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107493

Accurately predicting the isocitrate dehydrogenase (IDH) mutation status of gliomas is greatly significant for formulating appropriate treatment plans and evaluating the prognoses of gliomas. Although existing studies can accurately predict the IDH mutation status of gliomas based on multimodal magnetic resonance (MR) images and machine learning methods, most of these methods cannot fully explore multimodal information and effectively predict IDH status for datasets acquired from multiple centers. To address this issue, a novel wavelet scattering (WS)-based orthogonal fusion network (WSOFNet) was proposed in this work to predict the IDH mutation status of gliomas from multiple centers. First, transformation-invariant features were extracted from multimodal MR images with a WS network, and then the multimodal WS features were used instead of the original images as the inputs of WSOFNet and were fully fused through an adaptive multimodal feature fusion module (AMF2M) and an orthogonal projection module (OPM). Finally, the fused features were input into a fully connected classifier to predict IDH mutation status. In addition, to achieve improved prediction accuracy, four auxiliary losses were also used in the feature extraction modules. The comparison results showed that the prediction area under the curve (AUC) of WSOFNet on a single-center dataset was 0.9966 and that on a multicenter dataset was approximately 0.9655, which was at least 3.9% higher than that of state-of-the-art methods. Moreover, the ablation experimental results also proved that the adaptive multimodal feature fusion strategy based on orthogonal projection could effectively improve the prediction performance of the model, especially for an external validation dataset. •Proposed WSOFNet to predict IDH mutation in multicenter gliomas via multimodal MR images (AUC > 0.96).•Achieved robust performance using invariant wavelet scattering features.•Used adaptive spatial, channel attentions and orthogonal projections to fuse multimodal MR information.