Hong Jialin, Huang Yueqi, Ye Jianming, Wang Jianqing, Xu Xiaomei, Wu Yan, Li Yi, Zhao Jialu, Li Ruipeng, Kang Junlong, Lai Xiaobo
School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, China.
Department of Psychiatry, Hangzhou Seventh People's Hospital, Hangzhou, China.
Front Aging Neurosci. 2022 May 13;14:912283. doi: 10.3389/fnagi.2022.912283. eCollection 2022.
Major Depressive Disorder (MDD) is the most prevalent psychiatric disorder, seriously affecting people's quality of life. Manually identifying MDD from structural magnetic resonance imaging (sMRI) images is laborious and time-consuming due to the lack of clear physiological indicators. With the development of deep learning, many automated identification methods have been developed, but most of them stay in 2D images, resulting in poor performance. In addition, the heterogeneity of MDD also results in slightly different changes reflected in patients' brain imaging, which constitutes a barrier to the study of MDD identification based on brain sMRI images. We propose an automated MDD identification framework in sMRI data (3D FRN-ResNet) to comprehensively address these challenges, which uses 3D-ResNet to extract features and reconstruct them based on feature maps. Notably, the 3D FRN-ResNet fully exploits the interlayer structure information in 3D sMRI data and preserves most of the spatial details as well as the location information when converting the extracted features into vectors. Furthermore, our model solves the feature map reconstruction problem in closed form to produce a straightforward and efficient classifier and dramatically improves model performance. We evaluate our framework on a private brain sMRI dataset of MDD patients. Experimental results show that the proposed model exhibits promising performance and outperforms the typical other methods, achieving the accuracy, recall, precision, and 1 values of 0.86776, 0.84237, 0.85333, and 0.84781, respectively.
重度抑郁症（MDD）是最常见的精神疾病，严重影响人们的生活质量。由于缺乏明确的生理指标，从结构磁共振成像（sMRI）图像中手动识别MDD既费力又耗时。随着深度学习的发展，已经开发了许多自动识别方法，但其中大多数停留在二维图像上，导致性能不佳。此外，MDD的异质性也导致患者脑成像中反映出的变化略有不同，这构成了基于脑sMRI图像进行MDD识别研究的障碍。我们提出了一种用于sMRI数据的自动MDD识别框架（3D FRN-ResNet）来全面应对这些挑战，该框架使用3D-ResNet提取特征并基于特征图对其进行重构。值得注意的是，3D FRN-ResNet充分利用了3D sMRI数据中的层间结构信息，并在将提取的特征转换为向量时保留了大部分空间细节以及位置信息。此外，我们的模型以封闭形式解决了特征图重构问题，以产生一个直接且高效的分类器，并显著提高了模型性能。我们在一个MDD患者的私有脑sMRI数据集上评估了我们的框架。实验结果表明，所提出的模型表现出良好的性能，优于其他典型方法，分别实现了0.86776、0.84237、0.85333和0.84781的准确率、召回率、精确率和F1值。
