Towards Generalized Synapse Detection Across Invertebrate Species

2025-09-21

AI Summary

To address the high-throughput, cross-species demand for synaptic structure analysis in invertebrate connectomics, we propose SimpSyn—a lightweight, single-stage model based on a Residual U-Net architecture that directly predicts dual-channel spherical masks. Efficient post-processing—including local peak detection and distance-based filtering—enables precise synapse localization. Evaluated on a novel benchmark comprising four volumetric electron microscopy datasets from *Drosophila* and parasitoid wasps, SimpSyn consistently outperforms the state-of-the-art multi-task model Synful in F1 score, demonstrating superior generalization—especially under joint training across species. SimpSyn achieves an optimal balance among detection accuracy, training/inference efficiency, and deployment scalability. Its design enables robust, general-purpose synaptic detection at scale, thereby facilitating large-scale structure–behavior correlation studies in neural circuit analysis.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Behavioural differences across organisms, whether healthy or pathological, are closely tied to the structure of their neural circuits. Yet, the fine-scale synaptic changes that give rise to these variations remain poorly understood, in part due to persistent challenges in detecting synapses reliably and at scale. Volume electron microscopy (EM) offers the resolution required to capture synaptic architecture, but automated detection remains difficult due to sparse annotations, morphological variability, and cross-dataset domain shifts. To address this, we make three key contributions. First, we curate a diverse EM benchmark spanning four datasets across two invertebrate species: adult and larval Drosophila melanogaster, and Megaphragma viggianii (micro-WASP). Second, we propose SimpSyn, a single-stage Residual U-Net trained to predict dual-channel spherical masks around pre- and post-synaptic sites, designed to prioritize training and inference speeds and annotation efficiency over architectural complexity. Third, we benchmark SimpSyn against Buhmann et al.'s Synful [1], a state-of-the-art multi-task model that jointly infers synaptic pairs. Despite its simplicity, SimpSyn consistently outperforms Synful in F1-score across all volumes for synaptic site detection. While generalization across datasets remains limited, SimpSyn achieves competitive performance when trained on the combined cohort. Finally, ablations reveal that simple post-processing strategies - such as local peak detection and distance-based filtering - yield strong performance without complex test-time heuristics. Taken together, our results suggest that lightweight models, when aligned with task structure, offer a practical and scalable solution for synapse detection in large-scale connectomic pipelines.

Problem

• Detecting synapses reliably across species using electron microscopy data
• Addressing morphological variability and domain shifts in synapse detection
• Developing scalable automated methods for neural circuit analysis

Innovation

• Residual U-Net predicts dual-channel spherical masks
• Prioritizes training speed and annotation efficiency
• Uses simple post-processing for strong performance