DoGNet: A deep architecture for synapse detection in multiplexed fluorescence images

Neuronal synapses transmit electrochemical signals between cells through the coordinated action of presynaptic vesicles, ion channels, scaffolding and adapter proteins, and membrane receptors. In situ structural characterization of numerous synaptic proteins simultaneously through multiplexed imaging facilitates a bottom-up approach to synapse classification and phenotypic description. Objective automation of efficient and reliable synapse detection within these datasets is essential for the high-throughput investigation of synaptic features. Convolutional neural networks can solve this generalized problem of synapse detection, however, these architectures require large numbers of training examples to optimize their thousands of parameters. We propose DoGNet, a neural network architecture that closes the gap between classical computer vision blob detectors, such as Difference of Gaussians (DoG) filters, and modern convolutional networks. DoGNet is optimized to analyze highly multiplexed microscopy data. Its small number of training parameters allows DoGNet to be trained with few examples, which facilitates its application to new datasets without overfitting. We evaluate the method on multiplexed fluorescence imaging data from both primary mouse neuronal cultures and mouse cortex tissue slices. We show that DoGNet outperforms convolutional networks with a low-to-moderate number of training examples, and DoGNet is efficiently transferred between datasets collected from separate research groups. DoGNet synapse localizations can then be used to guide the segmentation of individual synaptic protein locations and spatial extents, revealing their spatial organization and relative abundances within individual synapses. The source code is publicly available: https://github.com/kulikovv/dognet.Author summary: Multiplexed fluorescence imaging of synaptic proteins facilitates high throughput investigations in neuroscience and drug discovery. Currently, there are several approaches to synapse detection using computational image processing. Unsupervised techniques rely on the a priori knowledge of synapse properties, such as size, intensity, and co-localization of synapse markers in each channel. For each experimental replicate, these parameters are typically tuned manually in order to obtain appropriate results. In contrast, supervised methods like modern convolutional networks require massive amounts of manually labeled data, and are sensitive to signal/noise ratios. As an alternative, here we propose DoGNet, a neural architecture that closes the gap between classical computer vision blob detectors, such as Difference of Gaussians (DoG) filters, and modern convolutional networks. This approach leverages the strengths of each approach, including automatic tuning of detection parameters, prior knowledge of the synaptic signal shape, and requiring only several training examples. Overall, DoGNet is a new tool for blob detection from multiplexed fluorescence images consisting of several up to dozens of fluorescence channels that requires minimal supervision due to its few input parameters. It offers the ability to capture complex dependencies between synaptic signals in distinct imaging planes, acting as a trainable frequency filter.