Task sub-type states decoding via group deep bidirectional recurrent neural network

Shijie Zhao, Long Fang, Yang Yang, Guochang Tang, Guoxin Luo, Junwei Han, Tianming Liu, Xintao Hu

Abstract: Highlights•The proposed Group-DBRNN exhibits exceptional capability in decoding fine-grained task sub-type states with an average accuracy of 94.7 % across 23 diverse cognitive processes. For coarse-grained decoding tasks, encompassing seven cognitive domains, an average accuracy of 96.72 % was achieved, indicating the model's remarkable performance.•We also propose a training sample collection strategy, namely, multiple-scale random fragment strategy (MRFS), to introduce task-relevant brain activity contrast in training samples, as well as a multi-task interaction (MTIL) module to effectively encode task-relevant brain activity contrast. The experimental results on HCP task fMRI dataset demonstrate the superiority of the proposed Group-DBRNN model in differentiating 23 task sub-type states in the seven independent tasks compared to existing methods.•Moreover, our extensive interpretations of the intermediate features via visual inspections based on feature visualizations and quantitative assessments of their discriminability and inter-subject alignment show that the proposed Group-DBRNN model can effectively capture the temporal dependency and task-relevant contrast.