A label-free and data-free training strategy for vasculature segmentation in serial sectioning OCT data

TL;DR

This paper introduces a novel label-free, data-free training approach for segmenting vasculature in serial sectioning OCT images, utilizing synthetic vessel datasets to overcome the scarcity of labeled data and improve segmentation accuracy.

Contribution

It presents a synthetic dataset-based training strategy for vasculature segmentation in OCT images, eliminating the need for labeled data and addressing OCT image complexity.

Findings

Synthetic vessel datasets achieve similar segmentation accuracy to real labels.

The method reduces reliance on time-consuming manual labeling.

It effectively handles OCT image noise and artifacts.

Abstract

Serial sectioning Optical Coherence Tomography (sOCT) is a high-throughput, label free microscopic imaging technique that is becoming increasingly popular to study post-mortem neurovasculature. Quantitative analysis of the vasculature requires highly accurate segmentation; however, sOCT has low signal-to-noise-ratio and displays a wide range of contrasts and artifacts that depend on acquisition parameters. Furthermore, labeled data is scarce and extremely time consuming to generate. Here, we leverage synthetic datasets of vessels to train a deep learning segmentation model. We construct the vessels with semi-realistic splines that simulate the vascular geometry and compare our model with realistic vascular labels generated by constrained constructive optimization. Both approaches yield similar Dice scores, although with very different false positive and false negative rates. This method addresses the complexity inherent in OCT images and paves the way for more accurate and efficient analysis of neurovascular structures.