Chen Zhining, Coste Gabrielle I, Li Evan, Huganir Richard L, Graves Austin R, Charles Adam S
Department of Biomedical Engineering, Johns Hopkins University.
Department of Neuroscience, Johns Hopkins University.
bioRxiv. 2025 Jan 23:2025.01.22.634278. doi: 10.1101/2025.01.22.634278.
Synapses are submicron structures that connect and enable communication between neurons. Many forms of learning are thought to be encoded by synaptic plasticity, wherein the strength of specific synapses is regulated by modulating expression of neurotransmitter receptors. For instance, regulation of AMPA-type glutamate receptors is a central mechanism controlling the formation and recollection of long-term memories. A critical step in understanding how synaptic plasticity drives behavior is thus to directly observe, i.e., image, fluorescently labeled synapses in living tissue. However, due to their small size and incredible density - with one ~0.5 μm diameter synapse every cubic micron - accurately detecting individual synapses and segmenting each from its closely abutting neighbors is challenging. To overcome this, we trained a convolutional neural network to simultaneously detect and separate densely labeled synapses. These tools significantly increased the accuracy and scale of synapse detection, enabling segmentation of hundreds of thousands of individual synapses imaged in living mice.
突触是连接神经元并使其能够进行通信的亚微米结构。许多形式的学习被认为是由突触可塑性编码的，其中特定突触的强度通过调节神经递质受体的表达来调节。例如，AMPA型谷氨酸受体的调节是控制长期记忆形成和回忆的核心机制。因此，理解突触可塑性如何驱动行为的关键一步是直接观察，即成像活组织中荧光标记的突触。然而，由于它们的尺寸小且密度惊人——每立方微米有一个直径约0.5μm的突触——准确检测单个突触并将其与紧密相邻的突触区分开来具有挑战性。为了克服这一问题，我们训练了一个卷积神经网络来同时检测和分离密集标记的突触。这些工具显著提高了突触检测的准确性和规模，能够对在活小鼠中成像的数十万单个突触进行分割。
