Fetal brain tissue annotation and segmentation challenge results

Payette, Kelly; Li, Hongwei; Dumast, Priscille de; Licandro, Roxane; Ji, Hui; Siddiquee, Md Mahfuzur Rahman; Xu, Daguang; Myronenko, Andriy; Líu, Hao; Pei, Yuchen; Wang, Lisheng; Peng, Ying; Xie, Jun; Zhang, Huiquan; Dong, Guohai; Fu, Hao; Wang, Guotai; Rieu, ZunHyan; Kim, Donghyeon; Kim, Hyun Gi; Karimi, Davood; Gholipour, Ali; Torres, Helena R.; Oliveira, Bruno; Vilaça, João L.; Lin, Yang; Avisdris, Netanell; Ben-Zvi, Ori; Bashat, Dafna Ben; Fidon, Lucas; Aertsen, Michaël; Vercauteren, Tom; Sobotka, Daniel; Alenyà, Mireia; Villanueva, Maria Inmaculada; Cámara, Óscar; Fadida, Bella Specktor; Joskowicz, Leo; Liao, Weibin; Lv, Yi; Li, Xuesong; Mazher, Moona; Qayyum, Abdul; Puig, Domènec; Kebiri, Hamza; Zhang, Zelin; Xu, Xinyi; Wu, Dan; Liao, Kuanlun; Wu, Yixuan; Chen, Jintai; Xu, Yinlong; Li, Zhao; Vasung, Lana; Menze, Bjoern H.; Cuadra, Meritxell Bach; Jakab, András

doi:10.1016/j.media.2023.102833

Cited by 19 publications

(6 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A possible solution to these problems would be to perform landmark, sulcal, surface-based analyses ( Lefèvre et al, 2016 ; Bozek et al, 2018 ; Lebenberg et al, 2018 ; Ahmad et al, 2019 ; Oishi et al, 2019 ), however, there the fidelity and topological correctness of meshes and segmentation accuracy in fetal brain remains a critical challenge ( de Dumast et al, 2022 ; Payette et al, 2023 ). A newer approach might be to learn registrations by deep learning ( Wei et al, 2020 ), however, it is not yet clear how efficient these networks are for fetal and neonatal development.…”

Section: Discussionmentioning

confidence: 99%

Characterization of dynamic patterns of human fetal to neonatal brain asymmetry with deformation-based morphometry

Steger,

Moatti,

Payette

et al. 2023

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

IntroductionDespite established knowledge on the morphological and functional asymmetries in the human brain, the understanding of how brain asymmetry patterns change during late fetal to neonatal life remains incomplete. The goal of this study was to characterize the dynamic patterns of inter-hemispheric brain asymmetry over this critically important developmental stage using longitudinally acquired MRI scans.MethodsSuper-resolution reconstructed T2-weighted MRI of 20 neurotypically developing participants were used, and for each participant fetal and neonatal MRI was acquired. To quantify brain morphological changes, deformation-based morphometry (DBM) on the longitudinal MRI scans was utilized. Two registration frameworks were evaluated and used in our study: (A) fetal to neonatal image registration and (B) registration through a mid-time template. Developmental changes of cerebral asymmetry were characterized as (A) the inter-hemispheric differences of the Jacobian determinant (JD) of fetal to neonatal morphometry change and the (B) time-dependent change of the JD capturing left-right differences at fetal or neonatal time points. Left-right and fetal-neonatal differences were statistically tested using multivariate linear models, corrected for participants’ age and sex and using threshold-free cluster enhancement.ResultsFetal to neonatal morphometry changes demonstrated asymmetry in the temporal pole, and left-right asymmetry differences between fetal and neonatal timepoints revealed temporal changes in the temporal pole, likely to go from right dominant in fetal to a bilateral morphology in neonatal timepoint. Furthermore, the analysis revealed right-dominant subcortical gray matter in neonates and three clusters of increased JD values in the left hemisphere from fetal to neonatal timepoints.DiscussionWhile these findings provide evidence that morphological asymmetry gradually emerges during development, discrepancies between registration frameworks require careful considerations when using DBM for longitudinal data of early brain development.

show abstract

Section: Discussionmentioning

confidence: 99%

Characterization of dynamic patterns of human fetal to neonatal brain asymmetry with deformation-based morphometry

Steger,

Moatti,

Payette

et al. 2023

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our study’s primary objective is to assess the practicality and efficacy of utilizing simulated data for training DL models in the context of segmentation tasks, prioritizing practical applications over the pursuit of a marginal, residual performance gain. To achieve this goal, we chose to employ the widely accessible nnU-Net implementation 53 , renowned for its robustness in similar tasks, as demonstrated by its strong performance in the FeTA Challenge 2021 17 . To evaluate the impact of simulated data, we conducted a comparative analysis, employing the same nnU-Net model while varying the input data.…”

Section: Methodsmentioning

confidence: 99%

“…However, such atlases average brain scans across several fetuses at a given gestational age (GA), thus resulting in high-resolution (HR) images far from a realistic clinical set-up, with smoothed inter-individual heterogeneities and features. Recently, the Fetal Tissue Annotations (FeTA) dataset has been proposed as a benchmark for automated multi-tissue fetal brain segmentation 16,17 . However, only super-resolution (SR) reconstructions 18,19 of the fetal brain volume and their associated semi-automated annotations have been made publicly available, but not the original clinical acquisitions.…”

Section: Background and Summarymentioning

confidence: 99%

Maturation-informed synthetic Magnetic Resonance Images of the Developing Human Fetal Brain

Lajous,

Boeuf Fló,

Gordaliza

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Magnetic resonance imaging is a powerful modality to investigate abnormal developmental patterns in utero. However, since it is not the first-line diagnostic tool in this sensitive population, data remain scarce and heterogeneous between scanners and centers. In addressing the data scarcity issue while generating data representative of real fetal brain MRI, we proposed FaBiAN, a `Fetal Brain magnetic resonance Acquisition Numerical phantom. Here, we present a novel synthetic dataset of 594 two-dimensional, low-resolution series of T2-weighted images corresponding to 78 developing human fetal brains between 20.0 and 34.8 weeks of gestational age. Data are generated with substantive improvements from the original FaBiAN to account for local heterogeneities within white matter tissues throughout maturation. These synthetic-yet-highly-realistic images cover both healthy and pathological development trajectories simulated with standard clinical settings and anatomically informed by the Fetal Tissue Annotations (FeTA) dataset. Two independent radiologists qualitatively assessed the realism of the simulated images. We also quantitatively demonstrate the simulated data's increased fidelity to real data compared to the previous FaBiAN version. The reuse potential of the proposed dataset was also evaluated in the context of automated fetal brain tissue segmentation. Besides, our dataset that combines images generated from various clinical scenarios has been made publicly available to support the continuous endeavor of the community to develop advanced post-processing methods aswell as cutting-edge artificial intelligence models.

show abstract

“…Fig. 1 MRS graph shows the different chemical peaks of a suspected brain tumor [1] Recently deep learning models have been used in medical image analysis for segmentation, classification, and object recognition [4], [5], [6], [7]. The 2D and 3D segmentation models have been proposed for segmentation of medical imaging [8], [9], [10].…”

Section: Introductionmentioning

confidence: 99%

Magnetic Resonance Spectroscopy (MRS) Reconstruction Using Style Transfer Deep Depth wise Framework

Qayyum,

Niederer,

Khan

et al. 2024

Proceedings of International Conference on Artificial Life and Robotics

View full text Add to dashboard Cite

The human brain is a complex and heterogeneous organ composed of distinct compartments such as cerebral cortex, the cerebellum, the brainstem, and the subcortical regions. To analyze the chemical composition of tissues in brain, in vivo magnetic resonance spectroscopy allows non-invasive measurements of neurochemicals in either single voxel or multiple voxels. The reconstruction spectra using 1/3rd of original data than current Edited-MRS scans will not only result in four times faster edited-MRS scans but also extensively reduction in radiations. In this work, we present a deep depth-wise channel attention module (DCAM) based fine-tuned network for magnetic resonance spectroscopy image reconstruction. Besides, we have used channel-wise convolutions and average pooling without dimensionality reduction. We have trained the initial network from scratch on track-1 simulated dataset, however due to the limited dataset, we finetune the network on track-2 and track-3. Experiments are conducted on Edited-MRS-Rec-Challenge dataset1 that showed significantly better performance.

show abstract

Fetal brain tissue annotation and segmentation challenge results

Cited by 19 publications

References 70 publications

Characterization of dynamic patterns of human fetal to neonatal brain asymmetry with deformation-based morphometry

Characterization of dynamic patterns of human fetal to neonatal brain asymmetry with deformation-based morphometry

Maturation-informed synthetic Magnetic Resonance Images of the Developing Human Fetal Brain

Magnetic Resonance Spectroscopy (MRS) Reconstruction Using Style Transfer Deep Depth wise Framework

Contact Info

Product

Resources

About