Dendritic and axonal morphology reflects the input and output of neurons and is a defining feature of neuronal types1,2, yet our knowledge of its diversity remains limited. Here, to systematically examine complete single-neuron morphologies on a brain-wide scale, we established a pipeline encompassing sparse labelling, whole-brain imaging, reconstruction, registration and analysis. We fully reconstructed 1,741 neurons from cortex, claustrum, thalamus, striatum and other brain regions in mice. We identified 11 major projection neuron types with distinct morphological features and corresponding transcriptomic identities. Extensive projectional diversity was found within each of these major types, on the basis of which some types were clustered into more refined subtypes. This diversity follows a set of generalizable principles that govern long-range axonal projections at different levels, including molecular correspondence, divergent or convergent projection, axon termination pattern, regional specificity, topography, and individual cell variability. Although clear concordance with transcriptomic profiles is evident at the level of major projection type, fine-grained morphological diversity often does not readily correlate with transcriptomic subtypes derived from unsupervised clustering, highlighting the need for single-cell cross-modality studies. Overall, our study demonstrates the crucial need for quantitative description of complete single-cell anatomy in cell-type classification, as single-cell morphological diversity reveals a plethora of ways in which different cell types and their individual members may contribute to the configuration and function of their respective circuits.
Convolutional neural networks have been highly successful in hyperspectral image classification owing to their unique feature expression ability. However, the traditional data partitioning strategy in tandem with patch-wise classification may lead to information leakage and result in overoptimistic experimental insights. In this paper, we propose a novel data partitioning scheme and a triple-attention parallel network (TAP-Net) to enhance the performance of HSI classification without information leakage. The dataset partitioning strategy is simple yet effective to avoid overfitting, and allows fair comparison of various algorithms, particularly in the case of limited annotated data. In contrast to classical encoder–decoder models, the proposed TAP-Net utilizes parallel subnetworks with the same spatial resolution and repeatedly reuses high-level feature maps of preceding subnetworks to refine the segmentation map. In addition, a channel–spectral–spatial-attention module is proposed to optimize the information transmission between different subnetworks. Experiments were conducted on three benchmark hyperspectral datasets, and the results demonstrate that the proposed method outperforms state-of-the-art methods with the overall accuracy of 90.31%, 91.64%, and 81.35% and the average accuracy of 93.18%, 87.45%, and 78.85% over Salinas Valley, Pavia University and Indian Pines dataset, respectively. It illustrates that the proposed TAP-Net is able to effectively exploit the spatial–spectral information to ensure high performance.
We conducted a large-scale whole-brain morphometry study by analyzing 3.7 peta-voxels of mouse brain images at the single-cell resolution, producing one of the largest multi-morphometry databases of mammalian brains to date. We registered 204 mouse brains of three major imaging modalities to the Allen Common Coordinate Framework (CCF) atlas, annotated 182,497 neuronal cell bodies, modeled 15,441 dendritic microenvironments, characterized the full morphology of 1876 neurons along with their axonal motifs, and detected 2.63 million axonal varicosities that indicate potential synaptic sites. Our analyzed six levels of information related to neuronal populations, dendritic microenvironments, single-cell full morphology, dendritic and axonal arborization, axonal varicosities, and sub-neuronal structural motifs, along with a quantification of the diversity and stereotypy of patterns at each level. This integrative study provides key anatomical descriptions of neurons and their types across a multiple scales and features, contributing a substantial resource for understanding neuronal diversity in mammalian brains.
With the thriving of deep learning, 3D convolutional neural networks have become a popular choice in volumetric image analysis due to their impressive 3D context mining ability. However, the 3D convolutional kernels will introduce a significant increase in the amount of trainable parameters. Considering the training data are often limited in biomedical tasks, a trade-off has to be made between model size and its representational power. To address this concern, in this paper, we propose a novel 3D Dense Separated Convolution (3D-DSC) module to replace the original 3D convolutional kernels. The 3D-DSC module is constructed by a series of densely connected 1D filters. The decomposition of 3D kernel into 1D filters reduces the risk of overfitting by removing the redundancy of 3D kernels in a topologically constrained manner, while providing the infrastructure for deepening the network. By further introducing nonlinear layers and dense connections between 1D filters, the network’s representational power can be significantly improved while maintaining a compact architecture. We demonstrate the superiority of 3D-DSC on volumetric medical image classification and segmentation, which are two challenging tasks often encountered in biomedical image computing.