Neurovascular Segmentation in sOCT with Deep Learning and Synthetic Training Data

TL;DR

This paper presents a novel deep learning approach for neurovascular segmentation in serial-section optical coherence tomography (sOCT) images, using synthetic training data to achieve high accuracy without manual annotations.

Contribution

The study introduces a synthesis engine for generating training labels and a label-to-image transformation, enabling effective neurovascular segmentation without manual annotations.

Findings

Achieved human-level precision in segmentation

Eliminated need for manual annotations in training

Validated on five distinct sOCT acquisitions

Abstract

Microvascular anatomy is known to be involved in various neurological disorders. However, understanding these disorders is hindered by the lack of imaging modalities capable of capturing the comprehensive three-dimensional vascular network structure at microscopic resolution. With a lateral resolution of $<=$20 {\textmu}m and ability to reconstruct large tissue blocks up to tens of cubic centimeters, serial-section optical coherence tomography (sOCT) is well suited for this task. This method uses intrinsic optical properties to visualize the vessels and therefore does not possess a specific contrast, which complicates the extraction of accurate vascular models. The performance of traditional vessel segmentation methods is heavily degraded in the presence of substantial noise and imaging artifacts and is sensitive to domain shifts, while convolutional neural networks (CNNs) require extensive labeled data and are also sensitive the precise intensity characteristics of the data that they are trained on. Building on the emerging field of synthesis-based training, this study demonstrates a synthesis engine for neurovascular segmentation in sOCT images. Characterized by minimal priors and high variance sampling, our highly generalizable method tested on five distinct sOCT acquisitions eliminates the need for manual annotations while attaining human-level precision. Our approach comprises two phases: label synthesis and label-to-image transformation. We demonstrate the efficacy of the former by comparing it to several more realistic sets of training labels, and the latter by an ablation study of synthetic noise and artifact models.