# Neurovascular Segmentation in sOCT with Deep Learning and Synthetic Training Data

arXiv: https://arxiv.org/abs/2407.01419 · HTML: https://mlsanity.com/paper/2407.01419/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 38 references that are in the map.
- First posted on arXiv 1 Jul 2024.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [SynthMorph: learning contrast-invariant registration without acquired images](https://mlsanity.com/paper/2004.10282/) (2020)
- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [GANs for Medical Image Synthesis: An Empirical Study](https://mlsanity.com/paper/2105.05318/) (2021)
- [DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes](https://mlsanity.com/paper/1803.09340/) (2018)
- [Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast](https://mlsanity.com/paper/2012.13340/) (2020)
- [Topology-Aware Uncertainty for Image Segmentation](https://mlsanity.com/paper/2306.05671/) (2023)
- [Learning Probabilistic Topological Representations Using Discrete Morse Theory](https://mlsanity.com/paper/2206.01742/) (2022)
- [AnyStar: Domain randomized universal star-convex 3D instance segmentation](https://mlsanity.com/paper/2307.07044/) (2023)
- [Physiology-based simulation of the retinal vasculature enables annotation-free segmentation of OCT angiographs](https://mlsanity.com/paper/2207.11102/) (2022)

## Built on by (most cited first, 4 of 4)

- [Domain-randomized deep learning for neuroimage analysis](https://mlsanity.com/paper/2507.13458/) (2025)
- [Tractography-Driven Synthetic Data Generation for Fiber Bundle Segmentation in Tracer Histology](https://mlsanity.com/paper/2606.26898/) (2026)
- [Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It](https://mlsanity.com/paper/2604.02564/) (2026)
- [AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation in Light-Sheet Microscopy](https://mlsanity.com/paper/2609.31431/) (2026)

## Abstract (arXiv)

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 textmum 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.