Brain-aligning of semantic vectors improves neural decoding of visual stimuli

📅 2024-03-22
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Existing neural decoding methods rely on pre-trained image or text feature vectors, yet their semantic structures fundamentally mismatch the brain’s intrinsic neural representations, limiting decoding accuracy. To address this, we propose Brain Alignment—a novel framework that explicitly aligns semantic vector spaces with cortical functional organization via fMRI-supervised fine-tuning. This approach bridges the modality gap by learning brain-grounded semantic embeddings. Crucially, Brain Alignment enables zero-shot transfer to MEG and ECoG modalities, significantly improving stimulus reconstruction correlation (p < 0.001) and fine-grained semantic category classification accuracy across modalities. The gains are robust, generalizable, and reproducible. Furthermore, our analysis reveals that the choice of source semantic space critically determines alignment efficacy—highlighting the importance of architectural compatibility between pretrained features and neural dynamics. This work establishes a principled, brain-informed paradigm for cross-modal neural decoding.

Technology Category

Application Category

📝 Abstract
The development of algorithms to accurately decode neural information has long been a research focus in the field of neuroscience. Brain decoding typically involves training machine learning models to map neural data onto a preestablished vector representation of stimulus features. These vectors are usually derived from image- and/or text-based feature spaces. Nonetheless, the intrinsic characteristics of these vectors might fundamentally differ from those that are encoded by the brain, limiting the ability of decoders to accurately learn this mapping. To address this issue, we propose a framework, called brain-aligning of semantic vectors, that fine-tunes pretrained feature vectors to better align with the structure of neural representations of visual stimuli in the brain. We trained this model with functional magnetic resonance imaging (fMRI) and then performed zero-shot brain decoding on fMRI, magnetoencephalography (MEG), and electrocorticography (ECoG) data. fMRI-based brain-aligned vectors improved decoding performance across all three neuroimaging datasets when accuracy was determined by calculating the correlation coefficients between true and predicted vectors. Additionally, when decoding accuracy was determined via stimulus identification, this accuracy increased in specific category types; improvements varied depending on the original vector space that was used for brain-alignment, and consistent improvements were observed across all neuroimaging modalities.
Problem

Research questions and friction points this paper is trying to address.

Improves neural decoding by aligning semantic vectors with brain representations
Addresses mismatch between preestablished feature vectors and brain-encoded characteristics
Enhances decoding accuracy across fMRI, MEG, and ECoG neuroimaging datasets
Innovation

Methods, ideas, or system contributions that make the work stand out.

Fine-tuning pretrained semantic vectors for brain alignment
Training with fMRI data for cross-modality decoding
Improving neural decoding accuracy across multiple imaging techniques
S
Shirin Vafaei
Department of Neurosurgery, Graduate School of Medicine, University of Osaka, Suita, Japan
R
R. Fukuma
Department of Neurosurgery, Graduate School of Medicine, University of Osaka, Suita, Japan
T
T. Yanagisawa
Department of Neurosurgery, Graduate School of Medicine, University of Osaka, Suita, Japan
H
Huixiang Yang
Department of Neuroinformatics, University of Osaka Graduate School of Medicine, Suita, Japan
S
S. Oshino
Department of Neurosurgery, Graduate School of Medicine, University of Osaka, Suita, Japan
N
N. Tani
Department of Neurosurgery, Graduate School of Medicine, University of Osaka, Suita, Japan
H
H. M. Khoo
Department of Neurosurgery, Graduate School of Medicine, University of Osaka, Suita, Japan
H
H. Sugano
Department of Neurosurgery, Juntendo University, Tokyo, Japan
Y
Y. Iimura
Department of Neurosurgery, Juntendo University, Tokyo, Japan
H
Hiroharu Suzuki
Department of Neurosurgery, Juntendo University, Tokyo, Japan
M
Madoka Nakajima
Department of Neurosurgery, Juntendo University, Tokyo, Japan
K
Kentaro Tamura
Department of Neurosurgery, Nara Medical University, Kashihara, Japan
H
H. Kishima
Department of Neurosurgery, Graduate School of Medicine, University of Osaka, Suita, Japan