The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, China; Henan Key Laboratory of Biological Psychiatry, Xinxiang, China; School of Medical Engineering, Xinxiang Medical University, Xinxiang, China; Engineering Technology Research Center of Neurosense and Control of Henan Province, Xinxiang, China; Xinxiang Engineering Technology Research Center of Intelligent Medical Imaging Diagnosis, Xinxiang, China.
The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, China; Henan Key Laboratory of Biological Psychiatry, Xinxiang, China; School of Medical Engineering, Xinxiang Medical University, Xinxiang, China; Engineering Technology Research Center of Neurosense and Control of Henan Province, Xinxiang, China.
Brain Res Bull. 2024 Jan;206:110848. doi: 10.1016/j.brainresbull.2023.110848. Epub 2023 Dec 15.
Schizophrenia classification and abnormal brain network recognition have an important research significance. Researchers have proposed many classification methods based on machine learning and deep learning. However, fewer studies utilized the advantages of complementary information from multi feature to learn the best representation of schizophrenia. In this study, we proposed a multi-feature fusion network (MFFN) using functional network connectivity (FNC) and time courses (TC) to distinguish schizophrenia patients from healthy controls. DNN backbone was adopted to learn the feature map of functional network connectivity, C-RNN backbone was designed to learn the feature map of time courses, and Deep SHAP was applied to obtain the most discriminative brain networks. We proved the effectiveness of this proposed model using the combining two public datasets and evaluated this model quantitatively using the evaluation indexes. The results showed that the functional network connectivity generated by independent component analysis has advantage in schizophrenia classification by comparing static and dynamic functional connections. This method obtained the best classification accuracy (ACC=87.30%, SPE=89.28%, SEN=85.71%, F1 =88.23%, and AUC=0.9081), and it demonstrated the superiority of this proposed model by comparing state-of-the-art methods. Ablation experiment also demonstrated that multi feature fusion and attention module can improve classification accuracy. The most discriminative brain networks showed that default mode network and visual network of schizophrenia patients have aberrant connections in brain networks. In conclusion, this method can identify schizophrenia effectively and visualize the abnormal brain network, and it has important clinical application value.
精神分裂症的分类和异常脑网络识别具有重要的研究意义。研究人员已经提出了许多基于机器学习和深度学习的分类方法。然而，利用多特征互补信息的研究较少，这些信息可以帮助学习精神分裂症的最佳表示。在这项研究中，我们提出了一种使用功能网络连接（FNC）和时间序列（TC）的多特征融合网络（MFFN），以区分精神分裂症患者和健康对照组。采用 DNN 主干来学习功能网络连接的特征图，设计 C-RNN 主干来学习时间序列的特征图，并应用 Deep SHAP 来获得最具判别力的脑网络。我们使用两个公共数据集来验证该模型的有效性，并使用评估指标对该模型进行定量评估。结果表明，通过比较静态和动态功能连接，独立成分分析生成的功能网络连接在精神分裂症分类中具有优势。该方法获得了最佳的分类准确率（ACC=87.30%，SPE=89.28%，SEN=85.71%，F1=88.23%，AUC=0.9081），并通过与最先进的方法进行比较，证明了该模型的优越性。消融实验还证明了多特征融合和注意力模块可以提高分类准确率。最具判别力的脑网络显示，精神分裂症患者的默认模式网络和视觉网络在脑网络中存在异常连接。总之，该方法可以有效地识别精神分裂症，并可视化异常脑网络，具有重要的临床应用价值。
