Use of Overlapping Group LASSO Sparse Deep Belief Network to Discriminate Parkinson's Disease and Normal Control

摘要

18F-fluorodeoxyglucose (FDG)-positron emission tomography (PET) is an essential component in the diagnostic work-up of patients with Parkinson's Disease (PD). With the development of pattern recognition technology, analysis of brain images using deep learning are becoming more and more popular. However, existing computer-aided-diagnosis technologies often overfit and have poor generalizability. Therefore, we aimed to improve a framework based on Group Lasso Sparse Deep Belief Network (GLS-DBN) for discriminating PD and normal control (NC) subjects. In this study, 225 NC and 125 PD cohorts from Huashan and Wuxi 904 hospitals were selected. They were divided into the trainingandvalidation dataset and 2 test datasets. First, in the trainingandvalidation set, subjects were randomly partitioned 80:20, with multiple training iterations for the deep learning model. Next, Locally Linear Embedding was used as a dimension reduction algorithm. Then, GLS-DBN was used for feature learning and classification. To evaluate the effectiveness of our framework, different sparse DBN models were used to compare datasets. Accuracy, sensitivity, and specificity were examined to validate the results. Output variables of the network were also correlated with longitudinal changes of cognitive measurements (UPDRS, HandY). As a result, accuracy of prediction (90% in Test 1, 86% in Test 2) for classification of PD and NC patients outperformed conventional approaches. Output scores of the network were strongly correlated with longitudinal changes in cognitive measurements (R = 0.705, p < 0.001; R = 0.697, p < 0.001 in Test 1; R = 0.592, p = 0.0018, R = 0.528, p = 0.0067 in Test 2). These results show the feasibility of GLS-DBN as a practical tool for early diagnosis of PD.