Effective representation of Regions of Interest (ROI) and independent alignment of these ROIs can significantly enhance the performance of deformable medical image registration (DMIR). However, current learning-based DMIR methods have limitations. Unsupervised techniques disregard ROI representation and proceed directly with aligning pairs of images, while weakly-supervised methods heavily depend on label constraints to facilitate registration. To address these issues, we introduce a novel ROI-based registration approach named EASR-DCN. Our method represents medical images through effective ROIs and achieves independent alignment of these ROIs without requiring labels. Specifically, we first used a Gaussian mixture model for intensity analysis to represent images using multiple effective ROIs with distinct intensities. Furthermore, we propose a novel Divide-and-Conquer Network (DCN) to process these ROIs through separate channels to learn feature alignments for each ROI. The resultant correspondences are seamlessly integrated to generate a comprehensive displacement vector field. Extensive experiments were performed on three MRI and one CT datasets to showcase the superior accuracy and deformation reduction efficacy of our EASR-DCN. Compared to VoxelMorph, our EASR-DCN achieved improvements of 10.31\% in the Dice score for brain MRI, 13.01\% for cardiac MRI, and 5.75\% for hippocampus MRI, highlighting its promising potential for clinical applications. The code for this work will be released upon acceptance of the paper.
The hippocampus encodes space through a striking gradient of place field sizes along its dorsal-ventral axis, yet the principles generating this continuous gradient from discrete grid cell inputs remain debated. We propose a unified theoretical framework establishing that hippocampal place fields arise naturally as linear projections of grid cell population activity, interpretable as eigenmodes. Critically, we demonstrate that a frequency-dependent decay of these grid-to-place connection weights naturally transforms inputs from discrete grid modules into a continuous spectrum of place field sizes. This multiscale organization is functionally significant: we reveal it shapes the inductive bias of the population code, balancing a fundamental trade-off between precision and generalization. Mathematical analysis and simulations demonstrate an optimal place field size for few-shot learning, which scales with environment structure. Our results offer a principled explanation for the place field gradient and generate testable predictions, bridging anatomical connectivity with adaptive learning in both biological and artificial intelligence.
The hippocampus enables spatial navigation through place cell populations forming cognitive maps. We propose proximity-preserving neural embeddings to encode multi-scale random walk transitions, where the inner product $\langle h(x, t), h(y, t) \rangle = q(y|x, t)$ represents normalized transition probabilities, with $h(x, t)$ as the embedding at location $x$ and $q(y|x, t)$ as the transition probability at scale $\sqrt{t}$. This scale hierarchy mirrors hippocampal dorsoventral organization. The embeddings $h(x, t)$ reduce pairwise spatial proximity into an environmental map, with Euclidean distances preserving proximity information. We use gradient ascent on $q(y|x, t)$ for straight-forward path planning, employing adaptive scale selection for trap-free, smooth trajectories, equivalent to minimizing embedding space distances. Matrix squaring ($P_{2t} = P_t^2$) efficiently builds global transitions from local ones ($P_1$), enabling preplay-like shortcut prediction. Experiments demonstrate localized place fields, multi-scale tuning, adaptability, and remapping, achieving robust navigation in complex environments. Our biologically plausible framework, extensible to theta-phase precession, unifies spatial and temporal coding for scalable navigation.
The hippocampus, a critical brain structure involved in memory processing and various neurodegenerative and psychiatric disorders, comprises three key subregions: the dentate gyrus (DG), Cornu Ammonis 1 (CA1), and Cornu Ammonis 3 (CA3). Accurate segmentation of these subregions from histological tissue images is essential for advancing our understanding of disease mechanisms, developmental dynamics, and therapeutic interventions. However, no existing methods address the automated segmentation of hippocampal subregions from tissue images, particularly from immunohistochemistry (IHC) images. To bridge this gap, we introduce a novel set of four comprehensive murine hippocampal IHC datasets featuring distinct staining modalities: cFos, NeuN, and multiplexed stains combining cFos, NeuN, and either {\Delta}FosB or GAD67, capturing structural, neuronal activity, and plasticity associated information. Additionally, we propose ROIsGAN, a region-guided U-Net-based generative adversarial network tailored for hippocampal subregion segmentation. By leveraging adversarial learning, ROIsGAN enhances boundary delineation and structural detail refinement through a novel region-guided discriminator loss combining Dice and binary cross-entropy loss. Evaluated across DG, CA1, and CA3 subregions, ROIsGAN consistently outperforms conventional segmentation models, achieving performance gains ranging from 1-10% in Dice score and up to 11% in Intersection over Union (IoU), particularly under challenging staining conditions. Our work establishes foundational datasets and methods for automated hippocampal segmentation, enabling scalable, high-precision analysis of tissue images in neuroscience research. Our generated datasets, proposed model as a standalone tool, and its corresponding source code are publicly available at: https://github.com/MehediAzim/ROIsGAN
Modeling episodic memory (EM) remains a significant challenge in both neuroscience and AI, with existing models either lacking interpretability or struggling with practical applications. This paper proposes the Vision-Language Episodic Memory (VLEM) framework to address these challenges by integrating large-scale pretrained models with hippocampal attractor dynamics. VLEM leverages the strong semantic understanding of pretrained models to transform sensory input into semantic embeddings as the neocortex, while the hippocampus supports stable memory storage and retrieval through attractor dynamics. In addition, VLEM incorporates prefrontal working memory and the entorhinal gateway, allowing interaction between the neocortex and the hippocampus. To facilitate real-world applications, we introduce EpiGibson, a 3D simulation platform for generating episodic memory data. Experimental results demonstrate the VLEM framework's ability to efficiently learn high-level temporal representations from sensory input, showcasing its robustness, interpretability, and applicability in real-world scenarios.
Our study presents PNN-UNet as a method for constructing deep neural networks that replicate the planarian neural network (PNN) structure in the context of 3D medical image data. Planarians typically have a cerebral structure comprising two neural cords, where the cerebrum acts as a coordinator, and the neural cords serve slightly different purposes within the organism's neurological system. Accordingly, PNN-UNet comprises a Deep-UNet and a Wide-UNet as the nerve cords, with a densely connected autoencoder performing the role of the brain. This distinct architecture offers advantages over both monolithic (UNet) and modular networks (Ensemble-UNet). Our outcomes on a 3D MRI hippocampus dataset, with and without data augmentation, demonstrate that PNN-UNet outperforms the baseline UNet and several other UNet variants in image segmentation.
Morphometry of medial temporal lobe (MTL) subregions in brain MRI is sensitive biomarker to Alzheimers Disease and other related conditions. While T2-weighted (T2w) MRI with high in-plane resolution is widely used to segment hippocampal subfields due to its higher contrast in hippocampus, its lower out-of-plane resolution reduces the accuracy of subregion thickness measurements. To address this issue, we developed a nearly isotropic segmentation pipeline that incorporates image and label upsampling and high-resolution segmentation in T2w MRI. First, a high-resolution atlas was created based on an existing anisotropic atlas derived from 29 individuals. Both T1-weighted and T2w images in the atlas were upsampled from their original resolution to a nearly isotropic resolution 0.4x0.4x0.52mm3 using a non-local means approach. Manual segmentations within the atlas were also upsampled to match this resolution using a UNet-based neural network, which was trained on a cohort consisting of both high-resolution ex vivo and low-resolution anisotropic in vivo MRI with manual segmentations. Second, a multi-modality deep learning-based segmentation model was trained within this nearly isotropic atlas. Finally, experiments showed the nearly isotropic subregion segmentation improved the accuracy of cortical thickness as an imaging biomarker for neurodegeneration in T2w MRI.
The human brain functions very differently from artificial neural networks (ANN) and possesses unique features that are absent in ANN. An important one among them is "adaptive synaptogenesis" that modifies synaptic weights when needed to avoid catastrophic forgetting and promote lifelong learning. The key aspect of this algorithm is supervised Hebbian learning, where weight modifications in the neocortex driven by temporal coincidence are further accepted or vetoed by an added control mechanism from the hippocampus during the training cycle, to make distant synaptic connections highly sparse and strategic. In this work, we discuss various algorithmic aspects of adaptive synaptogenesis tailored to edge computing, demonstrate its function using simulations, and design nanomagnetic hardware accelerators for specific functions of synaptogenesis.
Drug-resistant focal epilepsy is associated with abnormalities in the brain in both grey matter (GM) and superficial white matter (SWM). However, it is unknown if both types of abnormalities are important in supporting seizures. Here, we test if surgical removal of GM and/or SWM abnormalities relates to post-surgical seizure outcome in people with temporal lobe epilepsy (TLE). We analyzed structural imaging data from 143 TLE patients (pre-op dMRI and pre-op T1-weighted MRI) and 97 healthy controls. We calculated GM volume abnormalities and SWM mean diffusivity abnormalities and evaluated if their surgical removal distinguished seizure outcome groups post-surgically. At a group level, GM and SWM abnormalities were most common in the ipsilateral temporal lobe and hippocampus in people with TLE. Analyzing both modalities together, compared to in isolation, improved surgical outcome discrimination (GM AUC = 0.68, p < 0.01, WM AUC = 0.65, p < 0.01; Union AUC = 0.72, p < 0.01, Concordance AUC = 0.64, p = 0.04). Additionally, 100% of people who had all concordant abnormal regions resected had ILAE$_{1,2}$ outcomes. These findings suggest that regions identified as abnormal from both diffusion-weighted and T1-weighted MRIs are involved in the epileptogenic network and that resection of both types of abnormalities may enhance the chances of living without disabling seizures.
Few-shot image classification has become a popular research topic for its wide application in real-world scenarios, however the problem of supervision collapse induced by single image-level annotation remains a major challenge. Existing methods aim to tackle this problem by locating and aligning relevant local features. However, the high intra-class variability in real-world images poses significant challenges in locating semantically relevant local regions under few-shot settings. Drawing inspiration from the human's complementary learning system, which excels at rapidly capturing and integrating semantic features from limited examples, we propose the generalization-optimized Systems Consolidation Adaptive Memory Dual-Network, SCAM-Net. This approach simulates the systems consolidation of complementary learning system with an adaptive memory module, which successfully addresses the difficulty of identifying meaningful features in few-shot scenarios. Specifically, we construct a Hippocampus-Neocortex dual-network that consolidates structured representation of each category, the structured representation is then stored and adaptively regulated following the generalization optimization principle in a long-term memory inside Neocortex. Extensive experiments on benchmark datasets show that the proposed model has achieved state-of-the-art performance.
Many tasks require flexibly modifying perception and behavior based on current goals. Humans can retrieve episodic memories from days to years ago, using them to contextualize and generalize behaviors across novel but structurally related situations. The brain's ability to control episodic memories based on task demands is often attributed to interactions between the prefrontal cortex (PFC) and hippocampus (HPC). We propose a reinforcement learning model that incorporates a PFC-HPC interaction mechanism for goal-directed generalization. In our model, the PFC learns to generate query-key representations to encode and retrieve goal-relevant episodic memories, modulating HPC memories top-down based on current task demands. Moreover, the PFC adapts its encoding and retrieval strategies dynamically when faced with multiple goals presented in a blocked, rather than interleaved, manner. Our results show that: (1) combining working memory with selectively retrieved episodic memory allows transfer of decisions among similar environments or situations, (2) top-down control from PFC over HPC improves learning of arbitrary structural associations between events for generalization to novel environments compared to a bottom-up sensory-driven approach, and (3) the PFC encodes generalizable representations during both encoding and retrieval of goal-relevant memories, whereas the HPC exhibits event-specific representations. Together, these findings highlight the importance of goal-directed prefrontal control over hippocampal episodic memory for decision-making in novel situations and suggest a computational mechanism by which PFC-HPC interactions enable flexible behavior.
Accurate prediction of neural dynamics in the brain's reward circuitry is crucial for elucidating how natural and pharmacological rewards influence neural activity and connectivity. Traditional linear models, such as autoregressive (AR) and vector autoregressive (VAR), often inadequately capture the inherent nonlinear interactions in neural data. This study develops and benchmarks both linear and advanced deep learning models for predicting local field potentials (LFPs) in the rat hippocampus (HIP) and nucleus accumbens (NAc) across morphine, food, and saline conditions. We compared AR, VAR, long short-term memory (LSTM), and wavelet-based deep learning model (WCLSA). Additionally, a novel wavelet coherence-enhanced model (WCOH CLSA) was introduced to capture cross-region connectivity. Results indicate that WCLSA achieves superior predictive accuracy (up to 0.97 for HIP in food, 0.96 for NAc in morphine), while VAR performs competitively in the food group due to significant HIP-NAc correlation. Wavelet coherence analysis reveals robust connectivity in natural reward contexts and disrupted or nonlinear relationships under pharmacological influence. These findings highlight the differential engagement of HIP and NAc in reward processing and underscore the importance of advanced nonlinear models for capturing complex neural dynamics. The study provides a robust framework for predictive neuroscience and elucidates functional interactions within the reward circuitry.
This study investigates the multi-label classification of Local Field Potential (LFP) data from the hippocampus (HIP) and nucleus accumbens (NAc) in the rat brain, focusing on reward responses using the Conditioned Place Preference (CPP) paradigm. Rats were conditioned with saline, morphine, and food rewards, and LFP recordings were conducted from both HIP and NAc during pre- and post-tests. The LFP data were classified into four categories: treatment types, test phases, recording channels, and chamber positions within the CPP setup. Features were extracted using Continuous Wavelet Transform (CWT), Wavelet Coherence, and Wavelet Scattering. Classification was performed via Decision Trees, Multilayer Perceptrons, and Support Vector Machines. Notably, in the Food group, HIP and combined HIP-NAc features yielded the highest classification accuracy for CPP chambers, whereas NAc features excelled in the Morphine group. Employing wavelet scattering, an 80% classification accuracy was achieved across treatment groups, test phases, and channels. Exceptionally high classification accuracies were observed for Food-post-test-HIP (99.75%) and Morphine-post-test-NAc (99.58%). The study reveals that NAc activity is pivotal for morphine-induced CPP, whereas HIP and HIP-NAc connectivity are crucial for food-induced CPP. The proposed methodology provides a novel avenue for precisely classifying LFP data, shedding light on neural circuit activities underlying behavioral responses.
Purpose: Several brain complications of SARS-CoV-2 infection have been reported. It has been moreover speculated that this neurotropism could potentially cause a delayed outbreak of neuropsychiatric and neurodegenerative diseases of neuroinflammatory origin. A propagation mechanism has been proposed across the cribriform plate of the ethmoid bone, from the nose to the olfactory epithelium, and possibly afterward to other limbic structures, and deeper parts of the brain including the brainstem. Methods: Review of clinical examination, and whole-brain voxel-based analysis of $^{18}$F-FDG PET metabolism in comparison with healthy subjects (p voxel<0.001, p-cluster<0.05, uncorrected), of two patients with confirmed diagnosis of SARS-CoV-2 explored at the post-viral stage of the disease. Results: Hypometabolism of the olfactory/rectus gyrus was found on the two patients, especially one with 4-week prolonged anosmia. Additional hypometabolisms were found within amygdala, hippocampus, parahippocampus, cingulate cortex, pre-/post-central gyrus, thalamus/hypothalamus, cerebellum, pons, and medulla in the other patient who complained of delayed onset of a painful syndrome. Conclusion: These preliminary findings reinforce the hypotheses of SARS-CoV-2 neurotropism through the olfactory bulb and the possible extension of this impairment to other brain structures. $^{18}$F-FDG PET hypometabolism could constitute a cerebral quantitative biomarker of this involvement. Post-viral cohort studies are required to specify the exact relationship between such hypometabolisms and the possible persistent disorders, especially involving cognitive or emotion disturbances, residual respiratory symptoms, or painful complaints.
Topological techniques have become a popular tool for studying information flows in neural networks. In particular, simplicial homology theory is used to analyze how cognitive representations of space emerge from large conglomerates of independent neuronal contributions. Meanwhile, a growing number of studies suggest that many cognitive functions are sustained by serial patterns of activity. Here, we investigate stashes of such patterns using path homology theory--an impartial, universal approach that does not require a priori assumptions about the sequences' nature, functionality, underlying mechanisms, or other contexts. We focus on the hippocampus -- a key enabler of learning and memory in mammalian brains -- and quantify the ordinal arrangement of its activity similarly to how its topology has previously been studied in terms of simplicial homologies. The results reveal that the vast majority of sequences produced during spatial navigation are structurally equivalent to one another. Only a few classes of distinct sequences form an ordinal schema of serial activity that remains stable as the pool of sequences consolidates. Importantly, the structure of both maps is upheld by combinations of short sequences, suggesting that brief activity motifs dominate physiological computations. This ordinal organization emerges and stabilizes on timescales characteristic of spatial learning, displaying similar dynamics. Yet, the ordinal maps generally do not reflect topological affinities -- spatial and sequential analyses address qualitatively different aspects of spike flows, representing two complementary formats of information processing.
Diffusion models have been used extensively for high quality image and video generation tasks. In this paper, we propose a novel conditional diffusion model with spatial attention and latent embedding (cDAL) for medical image segmentation. In cDAL, a convolutional neural network (CNN) based discriminator is used at every time-step of the diffusion process to distinguish between the generated labels and the real ones. A spatial attention map is computed based on the features learned by the discriminator to help cDAL generate more accurate segmentation of discriminative regions in an input image. Additionally, we incorporated a random latent embedding into each layer of our model to significantly reduce the number of training and sampling time-steps, thereby making it much faster than other diffusion models for image segmentation. We applied cDAL on 3 publicly available medical image segmentation datasets (MoNuSeg, Chest X-ray and Hippocampus) and observed significant qualitative and quantitative improvements with higher Dice scores and mIoU over the state-of-the-art algorithms. The source code is publicly available at https://github.com/Hejrati/cDAL/.
Large language models based Multi Agent Systems (MAS) have demonstrated promising performance for enhancing the efficiency and accuracy of code generation tasks. However,most existing methods follow a conventional sequence of planning, coding, and debugging,which contradicts the growth-driven nature of human learning process. Additionally,the frequent information interaction between multiple agents inevitably involves high computational costs. In this paper,we propose Cogito,a neurobiologically inspired multi-agent framework to enhance the problem-solving capabilities in code generation tasks with lower cost. Specifically,Cogito adopts a reverse sequence: it first undergoes debugging, then coding,and finally planning. This approach mimics human learning and development,where knowledge is acquired progressively. Accordingly,a hippocampus-like memory module with different functions is designed to work with the pipeline to provide quick retrieval in similar tasks. Through this growth-based learning model,Cogito accumulates knowledge and cognitive skills at each stage,ultimately forming a Super Role an all capable agent to perform the code generation task. Extensive experiments against representative baselines demonstrate the superior performance and efficiency of Cogito. The code is publicly available at https://anonymous.4open.science/r/Cogito-0083.
Alzheimer's disease (AD) progresses through distinct stages, from early mild cognitive impairment (EMCI) to late mild cognitive impairment (LMCI) and eventually to AD. Accurate identification of these stages, especially distinguishing LMCI from EMCI, is crucial for developing pre-dementia treatments but remains challenging due to subtle and overlapping imaging features. This study proposes a minimal-feature machine learning framework that leverages structural MRI data, focusing on the hippocampus and amygdala as regions of interest. The framework addresses the curse of dimensionality through feature selection, utilizes region-specific voxel information, and implements innovative data organization to enhance classification performance by reducing noise. The methodology integrates dimensionality reduction techniques such as PCA and t-SNE with state-of-the-art classifiers, achieving the highest accuracy of 88.46%. This framework demonstrates the potential for efficient and accurate staging of AD progression while providing valuable insights for clinical applications.
Integrating multiple functionalities into a system poses a fascinating challenge to the field of deep learning. While the precise mechanisms by which the brain encodes and decodes information, and learns diverse skills, remain elusive, memorization undoubtedly plays a pivotal role in this process. In this article, we delve into the implementation and application of an autoencoder-inspired hippocampus network in a multi-functional system. We propose an autoencoder-based memorization method for policy function's parameters. Specifically, the encoder of the autoencoder maps policy function's parameters to a skill vector, while the decoder retrieves the parameters via this skill vector. The policy function is dynamically adjusted tailored to corresponding tasks. Henceforth, a skill vectors graph neural network is employed to represent the homeomorphic topological structure of subtasks and manage subtasks execution.
The influence of the epileptiform neuronal activity on the response of a CMOS-integrated ZrO2-based memristive crossbar and its conductivity was studied. Epileptiform neuronal activity was obtained in vitro in the hippocampus slices of laboratory mice using 4-aminopyridine experimental model. Synaptic plasticity of the memristive crossbar induced by epileptiform neuronal activity pulses was detected. Qualitatively, the results obtained in the case of normal (without pathologies) and epileptiform neuronal activity with and without noise coincide. For quantitative analysis, the value of the relative change in synaptic weight has been calculated for such important biological mechanisms of synapses as paired-pulse facilitation/depression, post-tetanic potentiation/depression, and long-term potentiation/depression. It has been shown that average value of the relative change in synaptic weight and its are smaller mainly in the case of epileptiform neuronal activity pulses. An effect of the influence of noise included in the neuronal activity was found, which consists in the fact that the current response of the memristive crossbar is smaller in the presence of noise. The results of this study can be used in the development of new generation hardware-implemented computing devices with high performance and energy efficiency for the tasks of restorative medicine and robotics. In particular, using these results, neurohybrid devices can be developed for processing epileptiform activity in real time and for its suppression.