Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure

About

Reconstructing visual stimuli from human brain activity (e.g., fMRI) bridges neuroscience and computer vision by decoding neural representations. However, existing methods often overlook critical brain structure-function relationships, flattening spatial information and neglecting individual anatomical variations. To address these issues, we propose (1) a novel sphere tokenizer that explicitly models fMRI signals as spatially coherent 2D spherical data on the cortical surface; (2) integration of structural MRI (sMRI) data, enabling personalized encoding of individual anatomical variations; and (3) a positive-sample mixup strategy for efficiently leveraging multiple fMRI scans associated with the same visual stimulus. Collectively, these innovations enhance reconstruction accuracy, biological interpretability, and generalizability across individuals. Experiments demonstrate superior reconstruction performance compared to SOTA methods, highlighting the effectiveness and interpretability of our biologically informed approach.

Sijin Yu, Zijiao Chen, Wenxuan Wu, Shengxian Chen, Zhongliang Liu, Jingxin Nie, Xiaofen Xing, Xiangmin Xu, Xin Zhang• 2025

Related benchmarks

TaskDatasetResultRank
fMRI DecodingNSD (Natural Scenes Dataset) shared (test)
Pixel Correlation0.165
11
Brain CaptioningNSD subj01 (test)
BLEU-149.66
3
Brain CaptioningNSD subj02 (test)
BLEU-149.37
3
Brain CaptioningNSD subj05 (test)
BLEU-149.7
3
Brain CaptioningNSD subj07 (test)
BLEU-148.61
3
Brain CaptioningNSD Average (test)
BLEU-149.33
3
Showing 6 of 6 rows

Other info

Follow for update