Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916770859712512 |
|---|---|
| author | Chalcroft, Liam Crinion, Jenny Price, Cathy J. Ashburner, John |
| author_facet | Chalcroft, Liam Crinion, Jenny Price, Cathy J. Ashburner, John |
| contents | Segmenting stroke lesions in MRI is challenging due to diverse acquisition protocols that limit model generalisability. In this work, we introduce two physics-constrained approaches to generate synthetic quantitative MRI (qMRI) images that improve segmentation robustness across heterogeneous domains. Our first method, $\texttt{qATLAS}$, trains a neural network to estimate qMRI maps from standard MPRAGE images, enabling the simulation of varied MRI sequences with realistic tissue contrasts. The second method, $\texttt{qSynth}$, synthesises qMRI maps directly from tissue labels using label-conditioned Gaussian mixture models, ensuring physical plausibility. Extensive experiments on multiple out-of-domain datasets show that both methods outperform a baseline UNet, with $\texttt{qSynth}$ notably surpassing previous synthetic data approaches. These results highlight the promise of integrating MRI physics into synthetic data generation for robust, generalisable stroke lesion segmentation. Code is available at https://github.com/liamchalcroft/qsynth |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03318 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data Chalcroft, Liam Crinion, Jenny Price, Cathy J. Ashburner, John Image and Video Processing Computer Vision and Pattern Recognition Medical Physics Segmenting stroke lesions in MRI is challenging due to diverse acquisition protocols that limit model generalisability. In this work, we introduce two physics-constrained approaches to generate synthetic quantitative MRI (qMRI) images that improve segmentation robustness across heterogeneous domains. Our first method, $\texttt{qATLAS}$, trains a neural network to estimate qMRI maps from standard MPRAGE images, enabling the simulation of varied MRI sequences with realistic tissue contrasts. The second method, $\texttt{qSynth}$, synthesises qMRI maps directly from tissue labels using label-conditioned Gaussian mixture models, ensuring physical plausibility. Extensive experiments on multiple out-of-domain datasets show that both methods outperform a baseline UNet, with $\texttt{qSynth}$ notably surpassing previous synthetic data approaches. These results highlight the promise of integrating MRI physics into synthetic data generation for robust, generalisable stroke lesion segmentation. Code is available at https://github.com/liamchalcroft/qsynth |
| title | Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Medical Physics |
| url | https://arxiv.org/abs/2412.03318 |