# Spec2VolCAMU-Net: A Spectrogram-to-Volume Model for EEG-to-fMRI Reconstruction based on Multi-directional Time-Frequency Convolutional Attention Encoder and Vision-Mamba U-Net

arXiv: https://arxiv.org/abs/2505.09521 · HTML: https://mlsanity.com/paper/2505.09521/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Physiological signal modeling, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 14 May 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Physiological signal modeling](https://mlsanity.com/ssm/physiological-signal-modeling/)

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [VM-UNet: Vision Mamba UNet for Medical Image Segmentation](https://mlsanity.com/paper/2402.02491/) (2024)
- [EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers](https://mlsanity.com/paper/2205.03436/) (2022)
- [NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping](https://mlsanity.com/paper/2410.05341/) (2024)
- [EEG to fMRI Synthesis Benefits from Attentional Graphs of Electrode Relationships](https://mlsanity.com/paper/2203.03481/) (2022)
- [Leveraging sinusoidal representation networks to predict fMRI signals from EEG](https://mlsanity.com/paper/2311.04234/) (2023)
- [NT-ViT: Neural Transcoding Vision Transformers for EEG-to-fMRI Synthesis](https://mlsanity.com/paper/2409.11836/) (2024)
- [From Brainwaves to Brain Scans: A Robust Neural Network for EEG-to-fMRI Synthesis](https://mlsanity.com/paper/2502.08025/) (2025)

## Built on by (most cited first, 2 of 2)

- [Non-Invasive Reconstruction of Intracranial EEG Across the Deep Temporal Lobe from Scalp EEG based on Conditional Normalizing Flow](https://mlsanity.com/paper/2603.03354/) (2026)
- [MEL: Coordinate-Preserving EEG Tokenization for fMRI Translation](https://mlsanity.com/paper/2608.29304/) (2026)

## Abstract (arXiv)

High-resolution functional magnetic resonance imaging (fMRI) is essential for mapping human brain activity; however, it remains costly and logistically challenging. If comparable volumes could be generated directly from widely available scalp electroencephalography (EEG), advanced neuroimaging would become significantly more accessible. Existing EEG-to-fMRI generators rely on plain Convolutional Neural Networks (CNNs) that fail to capture cross-channel time-frequency cues or on heavy transformer/Generative Adversarial Network (GAN) decoders that strain memory and stability. To address these limitations, we propose Spec2VolCAMU-Net, a lightweight architecture featuring a Multi-directional Time-Frequency Convolutional Attention Encoder for rich feature extraction and a Vision-Mamba U-Net decoder that uses linear-time state-space blocks for efficient long-range spatial modelling. We frame the goal of this work as establishing a new state of the art in the spatial fidelity of single-volume reconstruction, a foundational prerequisite for the ultimate aim of generating temporally coherent fMRI time series. Trained end-to-end with a hybrid SSI-MSE loss, Spec2VolCAMU-Net achieves state-of-the-art fidelity on three public benchmarks, recording Structural Similarity Index (SSIM) of 0.693 on NODDI, 0.725 on Oddball and 0.788 on CN-EPFL, representing improvements of 14.5%, 14.9%, and 16.9% respectively over previous best SSIM scores. Furthermore, it achieves competitive Signal-to-Noise Ratio (PSNR) scores, particularly excelling on the CN-EPFL dataset with a 4.6% improvement over the previous best PSNR, thus striking a better balance in reconstruction quality. The proposed model is lightweight and efficient, making it suitable for real-time applications in clinical and research settings. The code is available at https://github.com/hdy6438/Spec2VolCAMU-Net.