arXiv subjects

Margaux Roulet

Publications and source records attributed to Margaux Roulet.

4 recordsLinked to original sources

arXiv2025

T2 mapping at 0.55 T using Ultra-Fast Spin Echo MRI

Low-field T2 mapping MRI can democratize neuropediatric imaging by improving accessibility and providing quantitative biomarkers of brain development. \textbf{Purpose:} To evaluate the feasibility of high-resolution T2 mapping using a single-shot fast spin-echo (SS-FSE) sequence at 0.55~T in a healthy control cohort. \textbf{Study Type:} Prospective single-center study. \textbf{Population:} In vivo: ten healthy adults (18--43~years, 5 females/5 males). In vitro: NIST Phantom. \textbf{Field strength/sequence:} Multi-echo ultra-fast spin-echo at 0.55~T and 1.5~T. \textbf{Assessment:} Feasibility was first assessed in vitro using the NIST Phantom, comparing T2 relaxation times to spectrometer references at 0.55~T. Acquisition and T2-fitting parameters optimized in vitro were applied in vivo. Repeatability was evaluated by atlas-based analysis of white matter (WM) and cortical grey matter (GM) regions. Coefficients of variation (CoV) were computed across runs, sessions, and subjects. \textbf{Statistical Tests:} Wilcoxon signed-rank test with Bonferroni correction ($α= 0.05/n_{ROI}$) assessed CoV differences. Pearson correlation coefficients quantified T2 associations. \textbf{Results:} In vitro, mono-exponential fitting under Gaussian--Rician noise yielded deviations $<12\%$ from reference values. In vivo, inter-subject CoV was 5.2\% (WM) and 17.7\% (GM), comparable to 1.5~T. Mean T2 times were 118~ms (WM) and 188~ms (GM) at 0.55~T, with a 16.5-minute acquisition. \textbf{Conclusion:} A rapid, robust high-resolution T2 mapping protocol at 0.55~T for HASTE MRI is presented, employing Gaussian noise-based fitting. We report the first normative T2 values for healthy adult brains at 0.55~T, demonstrating technical feasibility and reliability.

physics.app-ph↗

arXiv2025

Advances in Automated Fetal Brain MRI Segmentation and Biometry: Insights from the FeTA 2024 Challenge

Accurate fetal brain tissue segmentation and biometric analysis are essential for studying brain development in utero. The FeTA Challenge 2024 advanced automated fetal brain MRI analysis by introducing biometry prediction as a new task alongside tissue segmentation. For the first time, our diverse multi-centric test set included data from a new low-field (0.55T) MRI dataset. Evaluation metrics were also expanded to include the topology-specific Euler characteristic difference (ED). Sixteen teams submitted segmentation methods, most of which performed consistently across both high- and low-field scans. However, longitudinal trends indicate that segmentation accuracy may be reaching a plateau, with results now approaching inter-rater variability. The ED metric uncovered topological differences that were missed by conventional metrics, while the low-field dataset achieved the highest segmentation scores, highlighting the potential of affordable imaging systems when paired with high-quality reconstruction. Seven teams participated in the biometry task, but most methods failed to outperform a simple baseline that predicted measurements based solely on gestational age, underscoring the challenge of extracting reliable biometric estimates from image data alone. Domain shift analysis identified image quality as the most significant factor affecting model generalization, with super-resolution pipelines also playing a substantial role. Other factors, such as gestational age, pathology, and acquisition site, had smaller, though still measurable, effects. Overall, FeTA 2024 offers a comprehensive benchmark for multi-class segmentation and biometry estimation in fetal brain MRI, underscoring the need for data-centric approaches, improved topological evaluation, and greater dataset diversity to enable clinically robust and generalizable AI tools.

cs.CV↗

arXiv2024

Evaluating Synthetic Data Generation for Domain Generalization in Fetal Brain MRI Segmentation

Fetal brain tissue segmentation from magnetic resonance imaging (MRI) is crucial for studying neurodevelopment, but remains challenging due to data heterogeneity and limited annotations. Domain randomization (DR) has recently emerged as a promising strategy for single-source domain generalization by synthesizing training images with randomized artifacts, contrast, and resolution. In this work, we investigate how to maximize the out-of-domain (OOD) generalization of DR-based methods. We evaluate several synthetic data generation strategies for DR, with a particular focus on our recently proposed framework, FetalSynthSeg. We show that simple Gaussian mixture-based intensity modeling outperforms more complex physics-based simulations, and that intensity clustering (subdividing tissue classes based on intensity) improves OOD robustness. Evaluated on 348 fetal subjects from four sites spanning 0.55-3T and both T1w and T2w contrasts, FetalSynthSeg reaches state-of-the-art performance on several FeTA 2024 testing datasets (80-85 Dice score) and, for the first time, offers robust segmentation on modalities other than T2w for fetal brain segmentation (80 Dice on dHCP-T1w dataset). Compared with state-of-the-art methods such as BOUNTI, nnU-Net ensemble, and the FeTA 2024 winner, FetalSynthSeg delivers comparable or superior accuracy while maintaining strong robustness across domain shifts. Our code, model weights, and Docker image ready for easy inference are available at https://hub.docker.com/r/vzalevskyi/fetalsynthseg.

eess.IV↗

arXiv2024

Improving cross-domain brain tissue segmentation in fetal MRI with synthetic data

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.

eess.IV↗