Diffusion Model-Based Data Augmentation for Enhanced Neuron Segmentation

TL;DR

This paper introduces a diffusion model-based data augmentation framework that generates diverse, structurally realistic neuron images and labels, significantly improving segmentation accuracy in electron microscopy datasets with limited annotations.

Contribution

The proposed method is the first to use a diffusion model for biologically plausible data augmentation in neuron segmentation, incorporating multi-scale conditioning and mask remodeling.

Findings

Improves ARAND metric by over 30% on AC3 and AC4 datasets.

Enhances segmentation performance under low-annotation regimes.

Generates structurally diverse and realistic training samples.

Abstract

Neuron segmentation in electron microscopy (EM) aims to reconstruct the complete neuronal connectome; however, current deep learning-based methods are limited by their reliance on large-scale training data and extensive, time-consuming manual annotations. Traditional methods augment the training set through geometric and photometric transformations; however, the generated samples remain highly correlated with the original images and lack structural diversity. To address this limitation, we propose a diffusion-based data augmentation framework capable of generating diverse and structurally plausible image-label pairs for neuron segmentation. Specifically, the framework employs a resolution-aware conditional diffusion model with multi-scale conditioning and EM resolution priors to enable voxel-level image synthesis from 3D masks. It further incorporates a biology-guided mask remodeling module that produces augmented masks with enhanced structural realism. Together, these components effectively enrich the training set and improve segmentation performance. On the AC3 and AC4 datasets under low-annotation regimes, our method improves the ARAND metric by 32.1% and 30.7%, respectively, when combined with two different post-processing methods. Our code is available at https://github.com/HeadLiuYun/NeuroDiff.