美国谷歌研究Viren Jain小组利用分割引导的对比学习绘制多层神经毡图。相关论文于2023年11月20日在线发表在《自然—方法学》杂志上。

研究人员提出了分割引导的对比学习表征（SegCLR），这是一种自我监督的机器学习技术，可直接从三维图像和分割中生成细胞表征。将SegCLR应用于人类和小鼠皮层体积时，它能对细胞亚区进行准确分类，并取得与监督方法相当的性能，而所需的标注示例数量却减少了400倍。SegCLR还能根据小至10 μm的片段推断细胞类型，从而提高了许多神经元在边界处被截断的体积的实用性。最后，SegCLR还能探索第5层锥体细胞亚型，并自动对小鼠视觉皮层的突触伙伴进行大规模分析。

据悉，能识别单个细胞及其类型、亚细胞成分和连接性的神经系统图有可能阐明神经回路的基本组织原理。脑组织的纳米分辨率成像提供了必要的原始数据，但推断细胞和亚细胞注释层却极具挑战性。

附：英文原文

Title: Multi-layered maps of neuropil with segmentation-guided contrastive learning

Author: Dorkenwald, Sven, Li, Peter H., Januszewski, Micha, Berger, Daniel R., Maitin-Shepard, Jeremy, Bodor, Agnes L., Collman, Forrest, Schneider-Mizell, Casey M., da Costa, Nuno Maarico, Lichtman, Jeff W., Jain, Viren

Issue&Volume: 2023-11-20

Abstract: Maps of the nervous system that identify individual cells along with their type, subcellular components and connectivity have the potential to elucidate fundamental organizational principles of neural circuits. Nanometer-resolution imaging of brain tissue provides the necessary raw data, but inferring cellular and subcellular annotation layers is challenging. We present segmentation-guided contrastive learning of representations (SegCLR), a self-supervised machine learning technique that produces representations of cells directly from 3D imagery and segmentations. When applied to volumes of human and mouse cortex, SegCLR enables accurate classification of cellular subcompartments and achieves performance equivalent to a supervised approach while requiring 400-fold fewer labeled examples. SegCLR also enables inference of cell types from fragments as small as 10μm, which enhances the utility of volumes in which many neurites are truncated at boundaries. Finally, SegCLR enables exploration of layer 5 pyramidal cell subtypes and automated large-scale analysis of synaptic partners in mouse visual cortex.

DOI: 10.1038/s41592-023-02059-8

Source: https://www.nature.com/articles/s41592-023-02059-8