Pixel Embedding Method for Tubular Neurite Segmentation

TL;DR

This paper introduces a novel deep learning framework that produces pixel embeddings for improved neuronal segmentation, enabling more accurate reconstruction of neuron structures and proposing a new topological evaluation metric.

Contribution

It presents a new deep network with a specialized loss for distinguishing neuronal connections, an end-to-end pipeline for neuron structure extraction, and a topological metric for better segmentation assessment.

Findings

Significantly reduces error in neuronal topology reconstruction.

Outperforms classical methods on fMOST imaging data.

Introduces a topological metric for segmentation quality evaluation.

Abstract

Automatic segmentation of neuronal topology is critical for handling large scale neuroimaging data, as it can greatly accelerate neuron annotation and analysis. However, the intricate morphology of neuronal branches and the occlusions among fibers pose significant challenges for deep learning based segmentation. To address these issues, we propose an improved framework: First, we introduce a deep network that outputs pixel level embedding vectors and design a corresponding loss function, enabling the learned features to effectively distinguish different neuronal connections within occluded regions. Second, building on this model, we develop an end to end pipeline that directly maps raw neuronal images to SWC formatted neuron structure trees. Finally, recognizing that existing evaluation metrics fail to fully capture segmentation accuracy, we propose a novel topological assessment metric to more appropriately quantify the quality of neuron segmentation and reconstruction. Experiments on our fMOST imaging dataset demonstrate that, compared to several classical methods, our approach significantly reduces the error rate in neuronal topology reconstruction.