A Classification Method for Depression Based on MRI

Depression is a serious threat to human health, and the difficulty of diagnosis and stigmatized by society make it difficult to theat. More than 350 million people worldwide suffer from depression. Therefore, earlier and more accurate diagnosis can save patients' lives. Most depression detection methods such as deep learning methods and manual questionnaires, perform poor interpretability or need long detection time. Therefore, our designed a depression diagnosis method based on Magnetic resonance imaging data. Firstly, we preprocessed the image to obtain data with high signal-to-noise ratio. Secondly, we extracted structural brain networks and functional brain networks from the data as input features. Finally, we used a classification method base on support vector machines and light gradient boosting machine algorithm to obtain classification results.