# Synthetic Data for Robust Stroke Segmentation

arXiv: https://arxiv.org/abs/2404.01946 · HTML: https://mlsanity.com/paper/2404.01946/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 58 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Builds on (most cited first, 24 of 24)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [Deep Structural Causal Models for Tractable Counterfactual Inference](https://mlsanity.com/paper/2006.06485/) (2020)
- [SynthMorph: learning contrast-invariant registration without acquired images](https://mlsanity.com/paper/2004.10282/) (2020)
- [ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset](https://mlsanity.com/paper/2206.06694/) (2022)
- [Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation](https://mlsanity.com/paper/2004.04668/) (2020)
- [Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling](https://mlsanity.com/paper/2109.09735/) (2021)
- [High Fidelity Image Counterfactuals with Probabilistic Causal Models](https://mlsanity.com/paper/2306.15764/) (2023)
- [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)
- [Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation](https://mlsanity.com/paper/2101.02323/) (2021)
- [Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation](https://mlsanity.com/paper/1903.03148/) (2019)
- [MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images](https://mlsanity.com/paper/2203.12362/) (2022)
- [Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models](https://mlsanity.com/paper/2111.14923/) (2021)
- [CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation](https://mlsanity.com/paper/2108.06883/) (2021)
- [Anatomy-aware and acquisition-agnostic joint registration with SynthMorph](https://mlsanity.com/paper/2301.11329/) (2023)
- [A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis](https://mlsanity.com/paper/2005.05135/) (2020)
- [LesionMix: A Lesion-Level Data Augmentation Method for Medical Image Segmentation](https://mlsanity.com/paper/2308.09026/) (2023)
- [Cortical analysis of heterogeneous clinical brain MRI scans for large-scale neuroimaging studies](https://mlsanity.com/paper/2305.01827/) (2023)
- [Harmonization and the Worst Scanner Syndrome](https://mlsanity.com/paper/2101.06255/) (2021)
- [Local Gamma Augmentation for Ischemic Stroke Lesion Segmentation on MRI](https://mlsanity.com/paper/2401.06893/) (2024)

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

- [SIAM: Head and Brain MRI Segmentation from Few High-Quality Templates via Synthetic Training](https://mlsanity.com/paper/2605.02737/) (2026)
- [Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data](https://mlsanity.com/paper/2412.03318/) (2024)
- [Automated Lesion Segmentation of Stroke MRI Using nnU-Net: A Comprehensive External Validation Across Acute and Chronic Lesions](https://mlsanity.com/paper/2601.08701/) (2026)
- [Synthetic training for long-tail haemorrhagic lesion segmentation in data-scarce settings](https://mlsanity.com/paper/2610.01542/) (2026)

## Abstract (arXiv)

Current deep learning-based approaches to lesion segmentation in neuroimaging often depend on high-resolution images and extensive annotated data, limiting clinical applicability. This paper introduces a novel synthetic data framework tailored for stroke lesion segmentation, expanding the SynthSeg methodology to incorporate lesion-specific augmentations that simulate diverse pathological features. Using a modified nnUNet architecture, our approach trains models with label maps from healthy and stroke datasets, facilitating segmentation across both normal and pathological tissue without reliance on specific sequence-based training. Evaluation across in-domain and out-of-domain (OOD) datasets reveals that our method matches state-of-the-art performance within the training domain and significantly outperforms existing methods on OOD data. By minimizing dependence on large annotated datasets and allowing for cross-sequence applicability, our framework holds potential to improve clinical neuroimaging workflows, particularly in stroke pathology. PyTorch training code and weights are publicly available at https://github.com/liamchalcroft/SynthStroke, along with an SPM toolbox featuring a plug-and-play model at https://github.com/liamchalcroft/SynthStrokeSPM.