# DINeuro: Distilling Knowledge from 2D Natural Images via Deformable Tubular Transferring Strategy for 3D Neuron Reconstruction

arXiv: https://arxiv.org/abs/2410.22078 · HTML: https://mlsanity.com/paper/2410.22078/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 29 Oct 2024.

## Builds on (most cited first, 6 of 6)

- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation](https://mlsanity.com/paper/2307.08388/) (2023)
- [Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images](https://mlsanity.com/paper/2101.08910/) (2021)
- [PointNeuron: 3D Neuron Reconstruction via Geometry and Topology Learning of Point Clouds](https://mlsanity.com/paper/2210.08305/) (2022)
- [Voxel-wise Cross-Volume Representation Learning for 3D Neuron Reconstruction](https://mlsanity.com/paper/2108.06522/) (2021)
- [Boosting 3D Neuron Segmentation with 2D Vision Transformer Pre-trained on Natural Images](https://mlsanity.com/paper/2405.02686/) (2024)

## Built on by (most cited first, 1 of 1)

- [NeuroSeg Meets DINOv3: Transferring 2D Self-Supervised Visual Priors to 3D Neuron Segmentation via DINOv3 Initialization](https://mlsanity.com/paper/2603.23104/) (2026)

## Abstract (arXiv)

Reconstructing neuron morphology from 3D light microscope imaging data is critical to aid neuroscientists in analyzing brain networks and neuroanatomy. With the boost from deep learning techniques, a variety of learning-based segmentation models have been developed to enhance the signal-to-noise ratio of raw neuron images as a pre-processing step in the reconstruction workflow. However, most existing models directly encode the latent representative features of volumetric neuron data but neglect their intrinsic morphological knowledge. To address this limitation, we design a novel framework that distills the prior knowledge from a 2D Vision Transformer pre-trained on extensive 2D natural images to facilitate neuronal morphological learning of our 3D Vision Transformer. To bridge the knowledge gap between the 2D natural image and 3D microscopic morphologic domains, we propose a deformable tubular transferring strategy that adapts the pre-trained 2D natural knowledge to the inherent tubular characteristics of neuronal structure in the latent embedding space. The experimental results on the Janelia dataset of the BigNeuron project demonstrate that our method achieves a segmentation performance improvement of 4.53% in mean Dice and 3.56% in mean 95% Hausdorff distance.