arrow
Return

Learnable Diffusion Framework for Mouse V1 Neural Decoding

delete2026-03-05
delete0
delete
OA
AI
K
Kaiwen Deng *
P
Peter S. Schwendeman
Y
Yuanfang Guan *
DOI:10.1002/advs.202520220delete
deleteOriginal
deleteShare
deleteSave
View PDF
Abstract

Abstract

En 中文
Decoding visual stimuli from neural signals is an essential step toward understanding how sensory information is represented in the brain. While most existing approaches reconstruct visual stimuli from human functional magnetic resonance imaging (fMRI), utilizing calcium imaging in mice opens the door to single-neuron-level insights into non-primate visual systems with distinct spectral sensitivities. Here, we present Sensorium-Viz, a diffusion-based framework specifically designed for decoding activity in the mouse primary visual cortex. The model is among the first to reliably reconstruct complex, high-resolution images from previously unseen single-neuron responses. At its core, Sensorium-Viz introduces two key advances for neuron-to-image decoding: a synthetic-response augmentation strategy that improves reconstruction performance by more than 30% while enabling cross-mouse generalization through fine-tuning, and an architectural design that integrates a Diffusion Transformer (DiT) with a spatial neuron-embedding module, thereby achieving up to a 10.65% performance gain over leading fMRI-based reconstruction methods across pixel- and content-level benchmarks. Analysis of the neural responses and corresponding reconstructions reveals that neurons sensitive to low-level visual features form the primary basis of V1's representation of external stimuli. These findings establish Sensorium-Viz as a biologically grounded and technically robust tool for vision decoding.
Keywords:
diffusion model
mouse
neural decoding
primary visual cortex

Journal

Advanced Science cover
Advanced Science
IF:
14.1
Papers:
1.9W
Citations:
16.2W

Organization

U
university of michigan
Scholars:
5.1K
Papers: 2.0K
Citations: 4.3W
Cited Papers

Cited Papers

scikit-image: image processing in Python
err2014-06-19
err0
errOAAI
errStéfan van der Walt; Johannes L. Schönberger; Juan Nunez-Iglesias; François Boulogne; Joshua D. Warner; Neil Yager; Emmanuelle Gouillart; Tony Yu
errShare
errSave
Mind Reading and Writing: The Future of Neurotechnology
err2018-07-01
err56
errOAAI
errRoelfsema, Pieter R.; Denys, Damiaan; Klink, P. Christiaan
errShare
errSave
Learnable latent embeddings for joint behavioural and neural analysis
errNature
IF48.5
err2023-05-03
err0
errOAAI
errSteffen Schneider; Jin Hwa Lee; Mackenzie Weygandt Mathis
errShare
errSave
Natural Whisker-Guided Behavior by Head-Fixed Mice in Tactile Virtual Reality
err2014-07-16
err0
errOAAI
errNicholas J. Sofroniew; Jeremy D. Cohen; Albert K. Lee; Karel Svoboda
errShare
errSave
Inverse retinotopy: Inferring the visual content of images from brain activation patterns
err2006-12-01
err0
PREAI
errBertrand Thirion; Edouard Duchesnay; Edward Hubbard; Jessica Dubois; Jean-Baptiste Poline; Denis Lebihan; Stanislas Dehaene
errShare
errSave
State-dependent pupil dilation rapidly shifts visual feature selectivity
err2022-09-28
err0
errOAAI
errKatrin Franke; Konstantin F. Willeke; Kayla Ponder; Mario Galdamez; Na Zhou; Taliah Muhammad; Saumil Patel; Emmanouil Froudarakis; Jacob Reimer; Fabian H. Sinz; Andreas S. Tolias
errShare
errSave
The brain-inspired decoder for natural visual image reconstruction
err2023-05-02
err1
errOAAI
errLi, Wenyi; Zheng, Shengjie; Liao, Yufan; Hong, Rongqi; He, Chenggang; Chen, Weiliang; Deng, Chunshan; Li, Xiaojian
errShare
errSave
researcher View more