BRAIN-IT: IMAGE RECONSTRUCTION FROM FMRI VIA BRAIN-INTERACTION TRANSFORMER Roman Beliy, Amit Zalcher, Jonathan Kogman, Navve Wasserman, Michal Irani Department of Computer Science and Applied Mathematics The Weizmann Institute of Science roman.beliy@weizmann.ac.il ABSTRACT Reconstructing images seen by people from their fMRI brain recordings provides a non-invasive window into the human brain. Despite recent progress enabled by diffusion models, current methods often lack faithfulness to the actual seen images. These functional-clusters are shared by all subjects, serving as building blocks for integrating information both within and across brains. All model components are shared by all clusters & subjects, allowing efficient training with a limited amount of data. To guide the image reconstruction, BIT predicts two complementary localized patch-level image features: (i) high-level semantic features which steer the diffusion model toward the correct semantic content of the image; and (ii) low-level structural features which help to initialize the diffusion process with the correct coarse layout of the image. BIT's design enables direct flow of information from brain-voxel clusters to localized image features. Through these principles, our method achieves image reconstructions from fMRI that faithfully reconstruct the seen images, and surpass current SotA approaches both visually and by standard objective metrics. Moreover, with only 1-hour of fMRI data from a new subject, we achieve results comparable to current methods trained on full 40-hour recordings. 1 INTRODUCTION Reconstructing visual experiences from brain activity (fMRI-to-image reconstruction) is a key challenge with broad implications for both neuroscience and brain-computer interfaces (Milekovic, 2018; Naci et al., 2012). Such reconstructions may provide a window into visual perception in the brain, enable the study of visual imagery (Cichy et al., 2012; Pearson et al., 2015), reveal dream content (Horikawa et al., 2013; Horikawa & Kamitani, 2017), and even assist in assessing disorders of consciousness (Monti et al., 2010; Owen et al., 2006). In a typical image decoding setting, subjects view natural images while their brain activity is being recorded using functional Magnetic Resonance Imaging (fMRI). This produces paired data of images and their corresponding fMRI scans. The task is then to reconstruct the perceived image from new (test) fMRI signals. Early work in this domain mapped fMRI signals to handcrafted image features (Kay et al., 2008; Naselaris et al., 2009; Nishimoto et al., 2011), which were then used for image reconstruction. Subsequent studies employed deep learning methods (Beliy et al., 2019; Lin et al., 2019; Shen et al., 2019).

Electromyography (EMG) signals are widely used for predicting body joint angles through machine learning (ML) and deep learni ng (DL) methods. However, these approaches often face challenges such as limited real - time applicability, non - representative test c onditions, and the need for large datasets to achieve optimal performance. This paper presents a transfer - learning framework for knee joint angle prediction that requires only a few gait cycles from new subjects. Three datasets - Georgia Tech, the Universi ty of California Irvine (UCI), and the Sharif Mechatronic Lab Exoskeleton (SMLE) - containing four EMG channels relevant to knee motion were utilized. A lightweight attention - based CNN - LSTM model was developed and pre - trained on the Georgia Tech dataset, t hen transferred to the UCI and SMLE datasets. The proposed model achieved Normalized Mean Absolute Errors (NMAE) of 6.8 percent and 13.7 percent for one - step and 50 - step predictions on abnormal subjects using EMG inputs alone. Incorporating historical knee angles reduced the NMAE to 3.1 percent and 3.5 percent for normal subjects, and to 2.8 percent and 7.5 percent for abnormal subjects. When f urther adapted to the SMLE exoskeleton with EMG, kinematic, and interaction force inputs, the model achieved 1.09 p ercent and 3.1 percent NMAE for one - and 50 - step predictions, respectively. These results demonstrate robust performance and strong generalization for both short - and long - term rehabilitation scenarios . Keywords: EMG, Transfer Learning, Knee Angle Prediction, Attention Mechanism, Rehabilitation, Exoskeleton . 1 - Introduction Electromyography (EMG) measures electrical signals generated by contracting muscle fibers, reflecting neuromuscular activity. EMG is typically measured using electrodes placed on the skin's surface (surface Electromyography (sEMG)). Alternatively, electrodes may be inserted into the muscle tissue [2] . The frequency range of EMG signals is generally reported to be from 6 to 500 Hz, with most power concentrated between 20 and 250 Hz [3] . Analyzing EMG signals provides valuable information about muscle activation patterns, coordination, and fatigue levels.

Mental and cognitive representations are believed to reside on low-dimensional, non-linear manifolds embedded within high-dimensional brain activity. Uncovering these manifolds is key to understanding individual differences in brain function, yet most existing machine learning methods either rely on population-level spatial alignment or assume data that is temporally structured, either because data is aligned among subjects or because event timings are known. We introduce a manifold learning framework that can capture subject-specific spatial variations across both structured and temporally unstructured neuroimaging data. On simulated data and two naturalistic fMRI datasets (Sherlock and Forrest Gump), our framework outperforms group-based baselines by recovering more accurate and individualized representations. We further show that the framework scales efficiently to large datasets and generalizes well to new subjects. To test this, we apply the framework to temporally unstructured resting-state fMRI data from individuals with schizophrenia and healthy controls. We further apply our method to a large resting-state fMRI dataset comprising individuals with schizophrenia and controls. In this setting, we demonstrate that the framework scales efficiently to large populations and generalizes robustly to unseen subjects. The learned subject-specific spatial maps our model finds reveal clinically relevant patterns, including increased activation in the basal ganglia, visual, auditory, and somatosensory regions, and decreased activation in the insula, inferior frontal gyrus, and angular gyrus. These findings suggest that our framework can uncover clinically relevant subject-specific brain activity patterns. Our approach thus provides a scalable and individualized framework for modeling brain activity, with applications in computational neuroscience and clinical research.

Brain decoding, a pivotal field in neuroscience, aims to reconstruct stimuli from acquired brain signals, primarily utilizing functional magnetic resonance imaging (fMRI). Currently, brain decoding is confined to a per-subject-per-model paradigm, limiting its applicability to the same individual for whom the decoding model is trained. This constraint stems from three key challenges: 1) the inherent variability in input dimensions across subjects due to differences in brain size; 2) the unique intrinsic neural patterns, influencing how different individuals perceive and process sensory information; 3) limited data availability for new subjects in real-world scenarios hampers the performance of decoding models. In this paper, we present a novel approach, MindBridge, that achieves cross-subject brain decoding by employing only one model. Our proposed framework establishes a generic paradigm capable of addressing these challenges by introducing biological-inspired aggregation function and novel cyclic fMRI reconstruction mechanism for subject-invariant representation learning. Notably, by cycle reconstruction of fMRI, MindBridge can enable novel fMRI synthesis, which also can serve as pseudo data augmentation. Within the framework, we also devise a novel reset-tuning method for adapting a pretrained model to a new subject. Experimental results demonstrate MindBridge's ability to reconstruct images for multiple subjects, which is competitive with dedicated subject-specific models. Furthermore, with limited data for a new subject, we achieve a high level of decoding accuracy, surpassing that of subject-specific models. This advancement in cross-subject brain decoding suggests promising directions for wider applications in neuroscience and indicates potential for more efficient utilization of limited fMRI data in real-world scenarios. Project page: https://littlepure2333.github.io/MindBridge

The Rapid Serial Visual Presentation (RSVP)-based Brain-Computer Interface (BCI) is an efficient technology for target retrieval using electroencephalography (EEG) signals. The performance improvement of traditional decoding methods relies on a substantial amount of training data from new test subjects, which increases preparation time for BCI systems. Several studies introduce data from existing subjects to reduce the dependence of performance improvement on data from new subjects, but their optimization strategy based on adversarial learning with extensive data increases training time during the preparation procedure. Moreover, most previous methods only focus on the single-view information of EEG signals, but ignore the information from other views which may further improve performance. To enhance decoding performance while reducing preparation time, we propose a Temporal-Spectral fusion transformer with Subject-specific Adapter (TSformer-SA). Specifically, a cross-view interaction module is proposed to facilitate information transfer and extract common representations across two-view features extracted from EEG temporal signals and spectrogram images. Then, an attention-based fusion module fuses the features of two views to obtain comprehensive discriminative features for classification. Furthermore, a multi-view consistency loss is proposed to maximize the feature similarity between two views of the same EEG signal. Finally, we propose a subject-specific adapter to rapidly transfer the knowledge of the model trained on data from existing subjects to decode data from new subjects. Experimental results show that TSformer-SA significantly outperforms comparison methods and achieves outstanding performance with limited training data from new subjects. This facilitates efficient decoding and rapid deployment of BCI systems in practical use.

Recently, commodity Wi-Fi devices have been shown to be able to construct human pose images, i.e., human skeletons, as fine-grained as cameras. Existing papers achieve good results when constructing the images of subjects who are in the prior training samples. However, the performance drops when it comes to new subjects, i.e., the subjects who are not in the training samples. This paper focuses on solving the subject-generalization problem in human pose image construction. To this end, we define the subject as the domain. Then we design a Domain-Independent Neural Network (DINN) to extract subject-independent features and convert them into fine-grained human pose images. We also propose a novel training method to train the DINN and it has no re-training overhead comparing with the domain-adversarial approach. We build a prototype system and experimental results demonstrate that our system can construct fine-grained human pose images of new subjects with commodity Wi-Fi in both the visible and through-wall scenarios, which shows the effectiveness and the subject-generalization ability of our model.

Drowsy driving is pervasive, and also a major cause of traffic accidents. Estimating a driver's drowsiness level by monitoring the electroencephalogram (EEG) signal and taking preventative actions accordingly may improve driving safety. However, individual differences among different drivers make this task very challenging. A calibration session is usually required to collect some subject-specific data and tune the model parameters before applying it to a new subject, which is very inconvenient and not user-friendly. Many approaches have been proposed to reduce the calibration effort, but few can completely eliminate it. This paper proposes a novel approach, feature weighted episodic training (FWET), to completely eliminate the calibration requirement. It integrates two techniques: feature weighting to learn the importance of different features, and episodic training for domain generalization. Experiments on EEG-based driver drowsiness estimation demonstrated that both feature weighting and episodic training are effective, and their integration can further improve the generalization performance. FWET does not need any labelled or unlabelled calibration data from the new subject, and hence could be very useful in plug-and-play brain-computer interfaces.

Aiming to make school students well-versed in technologies shaping the future, the Central Board of Secondary Education (CBSE) has decided to introduce artificial intelligence as an elective subject. "The decision to introduce artificial intelligence as a skill subject was taken at a recent meeting of the board's governing body. It has been decided that the subject would be introduced in classes 8, 9 and 10 as a skill subject," a member of the board's governing body said. Artificial intelligence is the ability of a machine to think, learn and perform tasks normally requiring human intelligence, such as visual perception, speech recognition and decision-making skills. Capabilities demonstrated by machines, including computers, from playing chess to operating cars and beyond, fall within the domain of artificial intelligence. With technologies like artificial intelligence, data analytics and big data making a huge impact globally, it is important that the board modernises its curriculum to stay abreast of the latest developments, the governing body member said.

Almost all EEG-based brain-computer interfaces (BCIs) need some labeled subject-specific data to calibrate a new subject, as neural responses are different across subjects to even the same stimulus. So, a major challenge in developing high-performance and user-friendly BCIs is to cope with such individual differences so that the calibration can be reduced or even completely eliminated. This paper focuses on the latter. More specifically, we consider an offline application scenario, in which we have unlabeled EEG trials from a new subject, and would like to accurately label them by leveraging auxiliary labeled EEG trials from other subjects in the same task. To accommodate the individual differences, we propose a novel unsupervised approach to align the EEG trials from different subjects in the Euclidean space to make them more consistent. It has three desirable properties: 1) the aligned trial lie in the Euclidean space, which can be used by any Euclidean space signal processing and machine learning approach; 2) it can be computed very efficiently; and, 3) it does not need any labeled trials from the new subject. Experiments on motor imagery and event-related potentials demonstrated the effectiveness and efficiency of our approach.

Probabilistic atlases provide essential spatial contextual information for image interpretation, Bayesian modeling, and algorithmic processing. Such atlases are typically constructed by grouping subjects with similar demographic information. Importantly, use of the same scanner minimizes inter-group variability. However, generalizability and spatial specificity of such approaches is more limited than one might like. Inspired by Commowick "Frankenstein's creature paradigm" which builds a personal specific anatomical atlas, we propose a data-driven framework to build a personal specific probabilistic atlas under the large-scale data scheme. The data-driven framework clusters regions with similar features using a point distribution model to learn different anatomical phenotypes. Regional structural atlases and corresponding regional probabilistic atlases are used as indices and targets in the dictionary. By indexing the dictionary, the whole brain probabilistic atlases adapt to each new subject quickly and can be used as spatial priors for visualization and processing. The novelties of this approach are (1) it provides a new perspective of generating personal specific whole brain probabilistic atlases (132 regions) under data-driven scheme across sites. (2) The framework employs the large amount of heterogeneous data (2349 images). (3) The proposed framework achieves low computational cost since only one affine registration and Pearson correlation operation are required for a new subject. Our method matches individual regions better with higher Dice similarity value when testing the probabilistic atlases. Importantly, the advantage the large-scale scheme is demonstrated by the better performance of using large-scale training data (1888 images) than smaller training set (720 images).