AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation in Light-Sheet Microscopy

2026-09-25

AI Summary

This study addresses the prohibitive cost of ground-truth annotation and limited cross-domain generalization in 3D axon segmentation by proposing an unsupervised transfer framework that integrates synthetic labels with domain randomization. Specifically, the method leverages rendering techniques to generate large-scale synthetic 3D axon data for training a three-class 3D U-Net model, thereby eliminating reliance on manual annotations in the target domain and enabling zero-shot cross-domain segmentation. Experimental results demonstrate that this framework significantly improves Dice coefficients while substantially reducing component counting errors on both macaque and human brain samples. By achieving robust performance without target-domain supervision, this work provides an efficient and scalable solution for cross-species neuroanatomical analysis.

Abstract

Accurate segmentation of axons in 3D microscopy data is important for analyzing white-matter organization, but dense ground truth labels are expensive to obtain. Existing supervised axon segmentation methods rely on target-domain annotations and can be brittle when tissue type, species, modality, or acquisition conditions change. We present AxonSynth, a domain-randomized synthetic-data framework for training 3D axon segmentation models without manually annotated real training volumes. AxonSynth generates dense synthetic axon labels with orientation priors that reflect realistic fiber configurations and renders them with randomized density, contrast, bias fields, blur, and noise. A three-class 3D U-Net is trained to predict background, axon sheath and intra-axonal space. We evaluate zero-shot transfer on 10 held-out light-sheet microscopy (LSM) patches from macaque and human brain samples labeled with one of three axonal markers, comparing against calibrated thresholding and Frangi filtering using overlap, corrected detection, false-positive, and topology metrics. On macaque samples, AxonSynth achieved the best corrected Dice and corrected precision (0.826 and 0.851), compared with 0.765 and 0.754 for thresholding and 0.685 and 0.762 for Frangi. On human samples, corrected Dice was comparable to thresholding (0.857 vs. 0.868), while component-count error decreased from 22,504 to 3,377. Across all held-out patches, AxonSynth reduced component-count error in 10/10 patches and Euler-characteristic error in 8/10. These results show that synthetic-label domain randomization can reduce dependence on manual axon annotation while supporting synthetic-to-real 3D segmentation.

Problem

• 3D axon segmentation
• light-sheet microscopy
• zero-shot transfer
• synthetic data
• domain randomization

Innovation

• Domain Randomization
• Zero-Shot Segmentation
• Synthetic Data
• 3D Axon Segmentation
• Light-Sheet Microscopy