信息工程大学学报2025，Vol.26Issue(6)：646-651,6.DOI:10.3969/j.issn.1671-0673.2025.06.003
融合多区域信息的fMRI低级视觉区编码模型
Encoding Model of fMRI Low-Level Visual Areas with Multi-Region Information Fusion
摘要
Abstract
A cross-regional visual encoding method based on multi-gate mixture-of-experts(MMoE)is proposed to address the problem that functional magnetic resonance imaging(fMRI)signals of various visual regions in the human brain are heterogeneous,and existing single-region modeling methods ig-nore the influence of other brain regions and fail to effectively predict fMRI signals.First,the encoding of adjacent visual cortices is converted into a multi-task learning problem to simulate cross-regional in-teractions.Second,a parallel expert network is constructed to capture cross-regional shared features and region-specific information.Finally,an adaptive gating function is designed to dynamically fuse the outputs of experts,further to simulate the cross-regional interaction mechanism of the biological vi-sual system.Experimental results demonstrate that the prediction accuracy of the model in each subre-gion of V1～V3 is significantly higher than that of the single-region baseline model,with the proportion of dominant voxels in V1v and V1d reaching 81.96%and 92.38%,respectively,validating the effec-tiveness of the visual encoding method integrating multi-region information.关键词
功能磁共振成像/低级视觉区/视觉编码模型/多门混合专家网络/跨区域信息融合Key words
functional Magnetic Resonance Imaging/low-level visual area/visual encoding model/multi-gate mixture-of-experts network/cross-regional information fusion分类
信息技术与安全科学引用本文复制引用
ZHAO Weichen,LIU Tianyuan,YAN Bin..融合多区域信息的fMRI低级视觉区编码模型[J].信息工程大学学报,2025,26(6):646-651,6.基金项目
国家自然科学基金(62106285) （62106285）
