Dynamic casual modeling of functional magnetic resonance imaging（fMRI） signals is employed to explore critical emotional neurocircuitry under sad stimuli. The intrinsic model of emotional loops is built on the basis of Papez＇s circuit and related prior knowledge, and then three modulatory connection models are established. In these models, stimuli are placed at different points, which represents they affect the neural activities between brain regions, and these activities are modulated in different ways. Then, the optimal model is selected by Bayesian model comparison. From group analysis, patients＇ intrinsic and modulatory connections from the anterior cingulate cortex （ACC） to the right inferior frontal gyrus （rlFG） are significantly higher than those of the control group. Then the functional connection parameters of the model are selected as classifier features. The classification accuracy rate from the support vector machine（SVM） classifier is 80.73%, which, to some extent, validates the effectiveness of the regional connectivity parameters for depression recognition and provides a new approach for the clinical diagnosis of depression.
Both functional magnetic resonance imaging （fMRI） and diffusion tensor imaging （DTI） can provide different information of the human brain, so using the wavelet transform method can achieve a fusion of these two types of image data and can effectively improve the depression recognition accuracy. Multi-resolution wavelet decomposition is used to transform each type of images to the frequency domain in order to obtain the frequency components of the images. To each subject, decomposition components of two images are then added up separately according to their frequencies. The inverse discrete wavelet transform is used to reconstruct the fused images. After that, principal component analysis （PCA） is applied to reduce the dimension and obtain the features of the fusion data before classification. Based on the features of the fused images, an accuracy rate of 80. 95 % for depression recognition is achieved using a leave-one-out cross-validation test. It can be concluded that this wavelet fusion scheme has the ability to improve the current diagnosis of depression.
