共找到 20 条结果
We present a novel method for quantifying the microscopic structure of brain tissue. It is based on the automated recognition of interpretable features obtained by analyzing the shapes of cells. This contrasts with prevailing methods of brain anatomical analysis in two ways. First, contemporary methods use gray-scale values derived from smoothed version of the anatomical images, which dissipated valuable information from the texture of the images. Second, contemporary analysis uses the output of black-box Convolutional Neural Networks, while our system makes decisions based on interpretable features obtained by analyzing the shapes of individual cells. An important benefit of this open-box approach is that the anatomist can understand and correct the decisions made by the computer. Our proposed system can accurately localize and identify existing brain structures. This can be used to align and coregistar brains and will facilitate connectomic studies for reverse engineering of brain circuitry.
Learning functional neuroanatomy requires forming mental representations of 3D structure, but forming such representations from 2D textbook diagrams can be challenging. We address this challenge in the UW Virtual Brain Project by developing 3D narrated diagrams, which are interactive, guided tours through 3D models of perceptual systems. Lessons can be experienced in virtual realty (VR) or on a personal computer monitor (PC). We predicted participants would learn from lessons presented on both VR and PC devices (comparing pre-test/post-test scores), but that VR would be more effective for achieving both content-based learning outcomes (i.e test performance) and experience-based learning outcomes (i.e., reported enjoyment and ease of use). All participants received lessons about the visual system and auditory system, one in VR and one on a PC(order counterbalanced). We assessed content learning using a drawing/labeling task on paper (2D drawing) in Experiment 1 and a Looking Glass autostereoscopic display (3D drawing) in Experiment 2. In both experiments, we found that the UW Virtual Brain Project lessons were effective for teaching functional neuroanatomy, with no difference betwee
The Allen Atlas of the adult mouse brain is a brain-wide, genome-wide data set that has been made available online, triggering a renaissance in neuroanatomy. In particular, it has been used to define brain regions in a computational, data-driven way, and to estimate the region-specificity of cell types characterized independently by their transcriptional activity. However, these results were based on one series of co-registered (coronal) ISH image series per gene, whereas the online ABA contains several image series per genes, including sagittal ones. Since the sagittal series cover mostly the left hemisphere, we can simulate the variability of results by repeatedly drawing a random image series for each gene and restricting the computation to the left hemisphere. This gives rise to an estimate of error bars on the results of computational neuroanatomy.
The contributions of this thesis stem from technology developed to analyse large sets of volumetric images in terms of atom-like features extracted in 3D image space, following SIFT algorithm in 2D image space. New feature properties are introduced including a binary feature sign, analogous to an electrical charge, and a discrete set of symmetric feature orientation states in 3D space. These new properties are leveraged to extend feature invariance to include the sign inversion and parity (SP) transform, analogous to the charge conjugation and parity (CP) transform between a particle and its antiparticle in quantum mechanics, thereby accounting for local intensity contrast inversion between imaging modalities and axis reflections due to shape symmetry. A novel exponential kernel is proposed to quantify the similarity of a pair of features extracted in different images from their properties including location, scale, orientation, sign and appearance. A novel measure entitled the soft Jaccard is proposed to quantify the similarity of a pair of feature sets based on their overlap or intersection-over-union, where a kernel establishes non-binary or soft equivalence between a pair of fe
Multi-modal neuroimaging projects are advancing our understanding of human brain architecture, function, connectivity using high-quality non-invasive data from many subjects. However, ground truth validation of connectivity using invasive tracers is not feasible in humans. Our NonHuman Primate Neuroimaging & Neuroanatomy Project (NHP_NNP) is an international effort (6 laboratories in 5 countries) to: (i) acquire and analyze high-quality multi-modal brain imaging data of macaque and marmoset monkeys using protocols and methods adapted from the HCP; (ii) acquire quantitative invasive tract-tracing data for cortical and subcortical projections to cortical areas; and (iii) map the distributions of different brain cell types with immunocytochemical stains to better define brain areal boundaries. We are acquiring high-resolution structural, functional, and diffusion MRI data together with behavioral measures from over 100 individual macaques and marmosets in order to generate non-invasive measures of brain architecture such as myelin and cortical thickness maps, as well as functional and diffusion tractography-based connectomes. We are using classical and next-generation anatomical t
We introduce DeepNAT, a 3D Deep convolutional neural network for the automatic segmentation of NeuroAnaTomy in T1-weighted magnetic resonance images. DeepNAT is an end-to-end learning-based approach to brain segmentation that jointly learns an abstract feature representation and a multi-class classification. We propose a 3D patch-based approach, where we do not only predict the center voxel of the patch but also neighbors, which is formulated as multi-task learning. To address a class imbalance problem, we arrange two networks hierarchically, where the first one separates foreground from background, and the second one identifies 25 brain structures on the foreground. Since patches lack spatial context, we augment them with coordinates. To this end, we introduce a novel intrinsic parameterization of the brain volume, formed by eigenfunctions of the Laplace-Beltrami operator. As network architecture, we use three convolutional layers with pooling, batch normalization, and non-linearities, followed by fully connected layers with dropout. The final segmentation is inferred from the probabilistic output of the network with a 3D fully connected conditional random field, which ensures lab
Despite differences in brain sizes and cognitive niches among mammals, their cerebral cortices posses many common features and regularities. These regularities have been a subject of experimental investigation in neuroanatomy for the last 100 years. It is believed that such studies may provide clues about cortical design principles and perhaps function. However, on a theoretical side there has been little interest, until recently, in studying quantitatively these regularities. This article reviews some attempts in this direction with an emphasis on neuronal connectivity. It is suggested that the brain development is influenced by different, conflicting in outcome, functional/biochemical constraints. Because of these conflicting constraints, it is hypothesized that the architecture of the cerebral cortex is shaped by some global optimization plan.
Neuroanatomical segmentation in magnetic resonance imaging (MRI) of the brain is a prerequisite for volume, thickness and shape measurements. This work introduces a new highly accurate and versatile method based on 3D convolutional neural networks for the automatic segmentation of neuroanatomy in T1-weighted MRI. In combination with a deep 3D fully convolutional architecture, efficient linear registration-derived spatial priors are used to incorporate additional spatial context into the network. An aggressive data augmentation scheme using random elastic deformations is also used to regularize the networks, allowing for excellent performance even in cases where only limited labelled training data are available. Applied to hippocampus segmentation in an elderly population (mean Dice coefficient = 92.1%) and sub-cortical segmentation in a healthy adult population (mean Dice coefficient = 89.5%), we demonstrate new state-of-the-art accuracies and a high robustness to outliers with the same architecture. Further validation on a multi-structure segmentation task in a scan-rescan dataset demonstrates accuracy (mean Dice coefficient = 86.6%) similar to the scan-rescan reliability of exper
The three-dimensional data-driven Allen Gene Expression Atlas of the adult mouse brain consists of numerized in-situ hybridization data for thousands of genes, co-registered to the Allen Reference Atlas. We propose quantitative criteria to rank genes as markers of a brain region, based on the localization of the gene expression and on its functional fitting to the shape of the region. These criteria lead to natural generalizations to sets of genes. We find sets of genes weighted with coefficients of both signs with almost perfect localization in all major regions of the left hemisphere of the brain, except the pallidum. Generalization of the fitting criterion with positivity constraint provides a lesser improvement of the markers, but requires sparser sets of genes.
EEG-based visual neural decoding aims to align neural responses with visual stimuli for tasks such as image retrieval. However, limited paired data and a fundamental mismatch between high-fidelity digital images and biological visual perception - distorted by retinotopic mapping and subject-specific neuroanatomy - severely impede cross-modal alignment. To address this, we propose MB2L, a Multi-Level Bidirectional Biomimetic Learning framework that incorporates structured physiological inductive biases into representation learning. Specifically, we propose Adaptive Blur with Visual Priors to mitigate perceptual-structural mismatch by reweighting visual inputs according to retinotopic priors. We further propose Biomimetic Visual Feature Extraction to learn multi-level visual representations consistent with hierarchical cortical processing, enhancing subject-invariant encoding. These modules are jointly optimized via Multi-level Bidirectional Contrastive Learning, which aligns EEG and visual features in a shared semantic space through bidirectional contrastive objectives. Experiments show MB2L achieves 80.5% Top-1 and 97.6% Top-5 accuracy on zero-shot EEG-to-image retrieval, significa
Stroke remains a leading cause of mortality and disability worldwide, requiring rapid and informed clinical decision-making. A solid spatial understanding of cerebrovascular anatomy and vascular territories in relation to stroke symptoms and severity is critical for timely clinical decision and patient care. However, this knowledge is typically conveyed through static 2D diagrams and printed materials, which can hinder mastery of the complex neurovascular system and their clinical implications. Mobile augmented reality (AR) offers an accessible medium for delivering intuitive 3D anatomical education, yet applications focused on the neurovascular system and stroke remain limited despite the demand. To address this, we propose NeuroVase, a tablet-based mobile AR platform within a structured pedagogical framework that enhances stroke-related neuroanatomy learning by providing an interactive, engaging, and accessible alternative to traditional methods. NeuroVase features a dual-mode setup, using tangible cue cards as standalone study aids while also serving as interactive markers for AR content delivery. A custom learning curriculum focused on cerebrovascular anatomy and stroke support
This work introduces a new computational theory of mind grounded in set theory and hyperdimensional computing. Whereas traditional neural networks rely on continuous weights and matrix multiplication, this framework works with sparse binary data. It represents information as discrete sets, directly modeling biological neural population codes. I demonstrate that associative memory emerges naturally from network topologies featuring a combinatorially expanded hidden layer. Learning is driven by topological plasticity rather than scalar weight adjustments. This architecture unifies auto-associative and hetero-associative learning under a single core algorithm: information retrieval via subset pattern matching and exact nearest-neighbor search. Operating with constant-time complexity, these mechanisms bridge perceptual data (sparse distributed representations) and symbols (sparse holographic representations) without continuous bottlenecks. Mapping this framework to neuroanatomy, I propose that both the cerebellum and the neocortex implement variants of this algorithm, making subset pattern matching the fundamental engine of cognition. Because it relies on discrete logic rather than mat
This collection comprises the abstracts presented during poster, power pitch and oral sessions at the Inaugural Conference of the International Society for Tractography (IST Conference 2025), held in Bordeaux, France, from October 13-16, 2025. The conference was designed to foster meaningful exchange and collaboration between disparate fields. The overall focus was on advancing research, innovation, and community in the common fields of interest: neuroanatomy, tractography methods and scientific/clinical applications of tractography. The included abstracts cover the latest advancements in tractography, Diffusion MRI, and related fields including new work on; neurological and psychiatric disorders, deep brain stimulation targeting, and brain development. This landmark event brought together world-leading experts to discuss critical challenges and chart the future direction of the field.
EEG-based emotion recognition holds significant promise for objective diagnosis of mood disorders. Graph neural networks (GNNs) have emerged as the dominant paradigm for modeling inter-channel dependencies in EEG, yet existing approaches rely on symmetric adjacency matrices derived from spatial proximity or functional correlations that fundamentally capture statistical associations rather than directed causal influences, which conflicts with the inherently asymmetric, causally-driven nature of neural information flow. To bridge this gap, we propose GL-LFGNN, a Global-Local Dual-branch Causal Graph Neural Network grounded in Liang-Kleeman information flow theory. Unlike Granger causality that merely assesses temporal precedence, our approach rigorously quantifies causal strength from a dynamical systems perspective, yielding neurophysiologically interpretable directed graphs. A dual-branch architecture further integrates whole-brain connectivity with region-specific processing aligned to established functional neuroanatomy. On the MEEG dataset, GL-LFGNN achieves 86.17% (Arousal) and 86.71% (Valence) accuracy with only 37K parameters -- approximately 10% of the current state-of-the-a
We present the case for developing the tardigrade (Hypsibius exemplaris) into a model organism for systems neuroscience. These microscopic, transparent animals (~300-500 microns) are among the smallest known to possess both limbs (eight) and eyes (two), with a nervous system of only a few hundred neurons organized into a multi-lobed brain, ventral nerve cord, and a series of ganglia along the body. Despite their neuroanatomical simplicity, tardigrades exhibit complex behaviors, including multi-limbed walking gaits, individual limb grasping, phototaxis, and transitions between active and dormant states. These behaviors position tardigrades as a uniquely powerful system for addressing certain fundamental questions in systems neuroscience, such as: How do nervous systems coordinate multi-limbed behaviors? How are top-down and bottom-up motor control systems integrated? How is stereovision-guided navigation implemented? What mechanisms underlie neural resilience and recovery during environmental stress? We review current knowledge of tardigrade neuroanatomy, behavior, and genomics, and we identify opportunities and challenges for leveraging their unique biology. We propose developing e
Brain tumors induce complex structural deformations that obscure the patient' s original neuroanatomy, making it difficult to distinguish tumor-induced changes from inherent anatomical variability. Reconstructing a subject-specific pseudo-healthy brain can provide a critical reference for such analysis, but this task is inherently counterfactual, as paired pre-tumor scans and explicit healthy guidance are unavailable. We propose BrainNormalizer, a diffusion-based framework for subject-specific pseudo-healthy brain MRI reconstruction that enables anatomy-informed reconstruction without requiring paired data or explicit healthy references. The framework learns anatomical priors and edge-based structural conditioning through a two-stage training strategy consisting of inpainting-based diffusion fine-tuning and ControlNet-based edge conditioning. At inference, counterfactual pseudo-healthy reconstruction is achieved through a deliberate misalignment strategy, where tumorous inputs are paired with non-tumorous prompts and mirrored contralateral edge maps. This allows subject-specific anatomical guidance to be constructed from the patient's own anatomy, enabling anatomically consistent p
Tractography is a unique method for mapping white matter connections in the brain, but tractography algorithms suffer from an inherent trade-off between sensitivity and specificity that limits accuracy. Incorporating prior knowledge of white matter anatomy is an effective strategy for improving accuracy and has been successful for reducing false positives and false negatives in bundle-mapping protocols. However, it is challenging to scale this approach for connectomics due to the difficulty in synthesising information relating to many thousands of possible connections. In this work, we develop and evaluate a pipeline using large language models (LLMs) to generate quantitative priors for connectomics, based on their knowledge of neuroanatomy. We benchmark our approach against an evaluation set derived from a gold-standard tractography atlas, identifying prompting techniques to elicit accurate connectivity information from the LLMs. We further identify strategies for incorporating external knowledge sources into the pipeline, which can provide grounding for the LLM and improve accuracy. Finally, we demonstrate how the LLM-derived priors can augment existing tractography filtering app
To understand biological intelligence we need to map neuronal networks in vertebrate brains. Mapping mesoscale neural circuitry is done using injections of tracers that label groups of neurons whose axons project to different brain regions. Since many neurons are labeled, it is difficult to follow individual axons. Previous approaches have instead quantified the regional projections using the total label intensity within a region. However, such a quantification is not biologically meaningful. We propose a new approach better connected to the underlying neurons by skeletonizing labeled axon fragments and then estimating a volumetric length density. Our approach uses a combination of deep nets and the Discrete Morse (DM) technique from computational topology. This technique takes into account nonlocal connectivity information and therefore provides noise-robustness. We demonstrate the utility and scalability of the approach on whole-brain tracer injected data. We also define and illustrate an information theoretic measure that quantifies the additional information obtained, compared to the skeletonized tracer injection fragments, when individual axon morphologies are available. Our a
In the spirit of the historic Millennium Prize Problems that heralded a new era for mathematics, the newly formed International Society for Tractography (IST) has launched the Millennium Pathways for Tractography, a community-driven roadmap designed to shape the future of the field. Conceived during the inaugural Tract-Anat Retreat, this initiative reflects a collective vision for advancing tractography over the coming decade and beyond. The roadmap consists of 40 grand challenges, developed by international experts and organized into seven categories spanning three overarching themes: neuroanatomy, tractography methods, and clinical applications. By defining shared short-, medium-, and long-term goals, these pathways provide a structured framework to confront fundamental limitations, promote rigorous validation, and accelerate the translation of tractography into a robust tool for neuroscience and medicine. Ultimately, the Millennium Pathways aim to guide and inspire future research and collaboration, ensuring the continued scientific and clinical relevance of tractography well into the future.
Reconstructing neuron morphology from 3D light microscope imaging data is critical to aid neuroscientists in analyzing brain networks and neuroanatomy. With the boost from deep learning techniques, a variety of learning-based segmentation models have been developed to enhance the signal-to-noise ratio of raw neuron images as a pre-processing step in the reconstruction workflow. However, most existing models directly encode the latent representative features of volumetric neuron data but neglect their intrinsic morphological knowledge. To address this limitation, we design a novel framework that distills the prior knowledge from a 2D Vision Transformer pre-trained on extensive 2D natural images to facilitate neuronal morphological learning of our 3D Vision Transformer. To bridge the knowledge gap between the 2D natural image and 3D microscopic morphologic domains, we propose a deformable tubular transferring strategy that adapts the pre-trained 2D natural knowledge to the inherent tubular characteristics of neuronal structure in the latent embedding space. The experimental results on the Janelia dataset of the BigNeuron project demonstrate that our method achieves a segmentation per