skip to main content

Title: Mind Reader: Reconstructing complex images from brain activities
Understanding how the brain encodes external stimuli and how these stimuli can be decoded from the measured brain activities are long-standing and challenging questions in neuroscience. In this paper, we focus on reconstructing the complex image stimuli from fMRI (functional magnetic resonance imaging) signals. Unlike previous works that reconstruct images with single objects or simple shapes, our work aims to reconstruct image stimuli that are rich in semantics, closer to everyday scenes, and can reveal more perspectives. However, data scarcity of fMRI datasets is the main obstacle to applying state-of-the-art deep learning models to this problem. We find that incorporating an additional text modality is beneficial for the reconstruction problem compared to directly translating brain signals to images. Therefore, the modalities involved in our method are: (i) voxel-level fMRI signals, (ii) observed images that trigger the brain signals, and (iii) textual description of the images. To further address data scarcity, we leverage an aligned vision-language latent space pre-trained on massive datasets. Instead of training models from scratch to find a latent space shared by the three modalities, we encode fMRI signals into this pre-aligned latent space. Then, conditioned on embeddings in this space, we reconstruct images with a generative model. The reconstructed images from our pipeline balance both naturalness and fidelity: they are photo-realistic and capture the ground truth image contents well.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ;
Publisher / Repository:
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
Date Published:
Journal Name:
Advances in neural information processing systems
Page Range / eLocation ID:
Medium: X
New Orleans, LA
Sponsoring Org:
National Science Foundation
More Like this
  1. Andreas Krause, Barbara Engelhardt (Ed.)
    Reconstructing natural images from fMRI recordings is a challenging task of great importance in neuroscience. The current architectures are bottlenecked because they fail to effectively capture the hierarchical processing of visual stimuli that takes place in the human brain. Motivated by that fact, we introduce a novel neural network architecture for the problem of neural decoding. Our architecture uses Hierarchical Variational Autoencoders (HVAEs) to learn meaningful representations of natural images and leverages their latent space hierarchy to learn voxel-to-image mappings. By mapping the early stages of the visual pathway to the first set of latent variables and the higher visual cortex areas to the deeper layers in the latent hierarchy, we are able to construct a latent variable neural decoding model that replicates the hierarchical visual information processing. Our model achieves better reconstructions compared to the state of the art and our ablation study indicates that the hierarchical structure of the latent space is responsible for that performance. 
    more » « less
  2. Neuroimaging studies of human memory have consistently found that univariate responses in parietal cortex track episodic experience with stimuli (whether stimuli are 'old' or 'new'). More recently, pattern-based fMRI studies have shown that parietal cortex also carries information about the semantic content of remembered experiences. However, it is not well understood how memory-based and content-based signals are integrated within parietal cortex. Here, in humans (males and females), we used voxel-wise encoding models and a recognition memory task to predict the fMRI activity patterns evoked by complex natural scene images based on (1) the episodic history and (2) the semantic content of each image. Models were generated and compared across distinct subregions of parietal cortex and for occipitotemporal cortex. We show that parietal and occipitotemporal regions each encode memory and content information, but they differ in how they combine this information. Among parietal subregions, angular gyrus was characterized by robust and overlapping effects of memory and content. Moreover, subject-specific semantic tuning functions revealed that successful recognition shifted the amplitude of tuning functions in angular gyrus but did not change the selectivity of tuning. In other words, effects of memory and content were additive in angular gyrus. This pattern of data contrasted with occipitotemporal cortex where memory and content effects were interactive: memory effects were preferentially expressed by voxels tuned to the content of a remembered image. Collectively, these findings provide unique insight into how parietal cortex combines information about episodic memory and semantic content.

    SIGNIFICANCE STATEMENTNeuroimaging studies of human memory have identified multiple brain regions that not only carry information about “whether” a visual stimulus is successfully recognized but also “what” the content of that stimulus includes. However, a fundamental and open question concerns how the brain integrates these two types of information (memory and content). Here, using a powerful combination of fMRI analysis methods, we show that parietal cortex, particularly the angular gyrus, robustly combines memory- and content-related information, but these two forms of information are represented via additive, independent signals. In contrast, memory effects in high-level visual cortex critically depend on (and interact with) content representations. Together, these findings reveal multiple and distinct ways in which the brain combines memory- and content-related information.

    more » « less
  3. We present a tomographic imaging technique, termed Deep Prior Diffraction Tomography (DP-DT), to reconstruct the 3D refractive index (RI) of thick biological samples at high resolution from a sequence of low-resolution images collected under angularly varying illumination. DP-DT processes the multi-angle data using a phase retrieval algorithm that is extended by a deep image prior (DIP), which reparameterizes the 3D sample reconstruction with an untrained, deep generative 3D convolutional neural network (CNN). We show that DP-DT effectively addresses the missing cone problem, which otherwise degrades the resolution and quality of standard 3D reconstruction algorithms. As DP-DT does not require pre-captured data or pre-training, it is not biased towards any particular dataset. Hence, it is a general technique that can be applied to a wide variety of 3D samples, including scenarios in which large datasets for supervised training would be infeasible or expensive. We applied DP-DT to obtain 3D RI maps of bead phantoms and complex biological specimens, both in simulation and experiment, and show that DP-DT produces higher-quality results than standard regularization techniques. We further demonstrate the generality of DP-DT, using two different scattering models, the first Born and multi-slice models. Our results point to the potential benefits of DP-DT for other 3D imaging modalities, including X-ray computed tomography, magnetic resonance imaging, and electron microscopy.

    more » « less
  4. null (Ed.)
    Abstract Background Cryo-EM data generated by electron tomography (ET) contains images for individual protein particles in different orientations and tilted angles. Individual cryo-EM particles can be aligned to reconstruct a 3D density map of a protein structure. However, low contrast and high noise in particle images make it challenging to build 3D density maps at intermediate to high resolution (1–3 Å). To overcome this problem, we propose a fully automated cryo-EM 3D density map reconstruction approach based on deep learning particle picking. Results A perfect 2D particle mask is fully automatically generated for every single particle. Then, it uses a computer vision image alignment algorithm (image registration) to fully automatically align the particle masks. It calculates the difference of the particle image orientation angles to align the original particle image. Finally, it reconstructs a localized 3D density map between every two single-particle images that have the largest number of corresponding features. The localized 3D density maps are then averaged to reconstruct a final 3D density map. The constructed 3D density map results illustrate the potential to determine the structures of the molecules using a few samples of good particles. Also, using the localized particle samples (with no background) to generate the localized 3D density maps can improve the process of the resolution evaluation in experimental maps of cryo-EM. Tested on two widely used datasets, Auto3DCryoMap is able to reconstruct good 3D density maps using only a few thousand protein particle images, which is much smaller than hundreds of thousands of particles required by the existing methods. Conclusions We design a fully automated approach for cryo-EM 3D density maps reconstruction (Auto3DCryoMap). Instead of increasing the signal-to-noise ratio by using 2D class averaging, our approach uses 2D particle masks to produce locally aligned particle images. Auto3DCryoMap is able to accurately align structural particle shapes. Also, it is able to construct a decent 3D density map from only a few thousand aligned particle images while the existing tools require hundreds of thousands of particle images. Finally, by using the pre-processed particle images,Auto3DCryoMap reconstructs a better 3D density map than using the original particle images. 
    more » « less
  5. Decoding auditory stimulus from neural activity can enable neuroprosthetics and direct communication with the brain. Some recent studies have shown successful speech decoding from intracranial recording using deep learning models. However, scarcity of training data leads to low quality speech reconstruction which prevents a complete brain-computer-interface (BCI) application. In this work, we propose a transfer learning approach with a pre-trained GAN to disentangle representation and generation layers for decoding. We first pre-train a generator to produce spectrograms from a representation space using a large corpus of natural speech data. With a small amount of paired data containing the stimulus speech and corresponding ECoG signals, we then transfer it to a bigger network with an encoder attached before, which maps the neural signal to the representation space. To further improve the network generalization ability, we introduce a Gaussian prior distribution regularizer on the latent representation during the transfer phase. With at most 150 training samples for each tested subject, we achieve a state-of-the-art decoding performance. By visualizing the attention mask embedded in the encoder, we observe brain dynamics that are consistent with findings from previous studies investigating dynamics in the superior temporal gyrus (STG), pre-central gyrus (motor) and inferior frontal gyrus (IFG). Our findings demonstrate a high reconstruction accuracy using deep learning networks together with the potential to elucidate interactions across different brain regions during a cognitive task. 
    more » « less