Improving cross-domain brain tissue segmentation in fetal MRI with synthetic data
- URL: http://arxiv.org/abs/2403.15103v1
- Date: Fri, 22 Mar 2024 10:42:25 GMT
- Title: Improving cross-domain brain tissue segmentation in fetal MRI with synthetic data
- Authors: Vladyslav Zalevskyi, Thomas Sanchez, Margaux Roulet, Jordina Aviles Verddera, Jana Hutter, Hamza Kebiri, Meritxell Bach Cuadra,
- Abstract summary: We introduce Fetal SynthSeg, a domain randomization method to segment fetal brain MRI.
Our results show that models trained solely on synthetic data outperform models trained on real data.
We extend our evaluation to 40 subjects acquired using lowfield (0.55T) MRI and reconstructed with novel SR models.
- Score: 1.1936126505067601
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Segmentation of fetal brain tissue from magnetic resonance imaging (MRI) plays a crucial role in the study of in utero neurodevelopment. However, automated tools face substantial domain shift challenges as they must be robust to highly heterogeneous clinical data, often limited in numbers and lacking annotations. Indeed, high variability of the fetal brain morphology, MRI acquisition parameters, and superresolution reconstruction (SR) algorithms adversely affect the model's performance when evaluated out-of-domain. In this work, we introduce FetalSynthSeg, a domain randomization method to segment fetal brain MRI, inspired by SynthSeg. Our results show that models trained solely on synthetic data outperform models trained on real data in out-ofdomain settings, validated on a 120-subject cross-domain dataset. Furthermore, we extend our evaluation to 40 subjects acquired using lowfield (0.55T) MRI and reconstructed with novel SR models, showcasing robustness across different magnetic field strengths and SR algorithms. Leveraging a generative synthetic approach, we tackle the domain shift problem in fetal brain MRI and offer compelling prospects for applications in fields with limited and highly heterogeneous data.
Related papers
- A Demographic-Conditioned Variational Autoencoder for fMRI Distribution Sampling and Removal of Confounds [49.34500499203579]
We create a variational autoencoder (VAE)-based model, DemoVAE, to decorrelate fMRI features from demographics.
We generate high-quality synthetic fMRI data based on user-supplied demographics.
arXiv Detail & Related papers (2024-05-13T17:49:20Z) - Anatomically Constrained Tractography of the Fetal Brain [6.112565873653592]
We advocate for anatomically constrained tractography based on an accurate segmentation of the fetal brain tissue directly in the dMRI space.
Experiments on independent test data show that this method can accurately segment the fetal brain tissue and drastically improve tractography results.
arXiv Detail & Related papers (2024-03-04T19:56:19Z) - Artificial Intelligence in Fetal Resting-State Functional MRI Brain
Segmentation: A Comparative Analysis of 3D UNet, VNet, and HighRes-Net Models [1.2382905694337476]
This study introduced a novel application of artificial intelligence (AI) for automated brain segmentation in fetal brain fMRI, magnetic resonance imaging (fMRI)
Three AI models were employed: 3D UNet, VNet, and HighResNet.
Our findings shed light on the performance of different AI models for fetal resting-state fMRI brain segmentation.
arXiv Detail & Related papers (2023-11-17T19:57:05Z) - fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for
Multi-Subject Brain Activity Decoding [54.17776744076334]
We propose fMRI-PTE, an innovative auto-encoder approach for fMRI pre-training.
Our approach involves transforming fMRI signals into unified 2D representations, ensuring consistency in dimensions and preserving brain activity patterns.
Our contributions encompass introducing fMRI-PTE, innovative data transformation, efficient training, a novel learning strategy, and the universal applicability of our approach.
arXiv Detail & Related papers (2023-11-01T07:24:22Z) - Metadata-Conditioned Generative Models to Synthesize
Anatomically-Plausible 3D Brain MRIs [12.492451825171408]
We propose a new generative model, Brain Synth, to synthesize metadata-conditioned (e.g., age- and sex-specific) MRIs.
Results indicate that more than half of the brain regions in our synthetic MRIs are anatomically accurate, with a small effect size between real and synthetic MRIs.
Our synthetic MRIs can significantly improve the training of a Convolutional Neural Network to identify accelerated aging effects.
arXiv Detail & Related papers (2023-10-07T00:05:47Z) - Source-Free Collaborative Domain Adaptation via Multi-Perspective
Feature Enrichment for Functional MRI Analysis [55.03872260158717]
Resting-state MRI functional (rs-fMRI) is increasingly employed in multi-site research to aid neurological disorder analysis.
Many methods have been proposed to reduce fMRI heterogeneity between source and target domains.
But acquiring source data is challenging due to concerns and/or data storage burdens in multi-site studies.
We design a source-free collaborative domain adaptation framework for fMRI analysis, where only a pretrained source model and unlabeled target data are accessible.
arXiv Detail & Related papers (2023-08-24T01:30:18Z) - Domain generalization in fetal brain MRI segmentation \\with
multi-reconstruction augmentation [0.348097307252416]
We propose to leverage the power of fetal brain MRI super-resolution (SR) reconstruction methods to generate multiple reconstructions of a single subject.
Overall, the latter significantly improves the generalization of segmentation methods over SR pipelines.
arXiv Detail & Related papers (2022-11-25T18:29:53Z) - Data and Physics Driven Learning Models for Fast MRI -- Fundamentals and
Methodologies from CNN, GAN to Attention and Transformers [72.047680167969]
This article aims to introduce the deep learning based data driven techniques for fast MRI including convolutional neural network and generative adversarial network based methods.
We will detail the research in coupling physics and data driven models for MRI acceleration.
Finally, we will demonstrate through a few clinical applications, explain the importance of data harmonisation and explainable models for such fast MRI techniques in multicentre and multi-scanner studies.
arXiv Detail & Related papers (2022-04-01T22:48:08Z) - Fader Networks for domain adaptation on fMRI: ABIDE-II study [68.5481471934606]
We use 3D convolutional autoencoders to build the domain irrelevant latent space image representation and demonstrate this method to outperform existing approaches on ABIDE data.
arXiv Detail & Related papers (2020-10-14T16:50:50Z) - Domain Shift in Computer Vision models for MRI data analysis: An
Overview [64.69150970967524]
Machine learning and computer vision methods are showing good performance in medical imagery analysis.
Yet only a few applications are now in clinical use.
Poor transferability of themodels to data from different sources or acquisition domains is one of the reasons for that.
arXiv Detail & Related papers (2020-10-14T16:34:21Z) - Incorporating structured assumptions with probabilistic graphical models
in fMRI data analysis [5.23143327587266]
We review a few recently developed algorithms in various domains of fMRI research.
These algorithms all tackle the challenges in fMRI similarly.
We advocate wider adoption of explicit model construction in cognitive neuroscience.
arXiv Detail & Related papers (2020-05-11T06:32:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.