Showing papers by "Maria Deprez published in 2022"

The Developing Human Connectome Project Neonatal Data Release

Abstract: The Developing Human Connectome Project has created a large open science resource which provides researchers with data for investigating typical and atypical brain development across the perinatal period. It has collected 1228 multimodal magnetic resonance imaging (MRI) brain datasets from 1173 fetal and/or neonatal participants, together with collateral demographic, clinical, family, neurocognitive and genomic data from 1173 participants, together with collateral demographic, clinical, family, neurocognitive and genomic data. All subjects were studied in utero and/or soon after birth on a single MRI scanner using specially developed scanning sequences which included novel motion-tolerant imaging methods. Imaging data are complemented by rich demographic, clinical, neurodevelopmental, and genomic information. The project is now releasing a large set of neonatal data; fetal data will be described and released separately. This release includes scans from 783 infants of whom: 583 were healthy infants born at term; as well as preterm infants; and infants at high risk of atypical neurocognitive development. Many infants were imaged more than once to provide longitudinal data, and the total number of datasets being released is 887. We now describe the dHCP image acquisition and processing protocols, summarize the available imaging and collateral data, and provide information on how the data can be accessed.

Retrospective motion correction in foetal MRI for clinical applications: existing methods, applications and integration into clinical practice

Abstract: Foetal MRI is a complementary imaging method to antenatal ultrasound. It provides advanced information for detection and characterisation of foetal brain and body anomalies. Even though modern single shot sequences allow fast acquisition of 2D slices with high in-plane image quality, foetal MRI is intrinsically corrupted by motion. Foetal motion leads to loss of structural continuity and corrupted 3D volumetric information in stacks of slices. Furthermore, the arbitrary and constantly changing position of the foetus requires dynamic readjustment of acquisition planes during scanning.

Motion corrected fetal body magnetic resonance imaging provides reliable 3D lung volumes in normal and abnormal fetuses

Abstract: To calculate 3D‐segmented total lung volume (TLV) in fetuses with thoracic anomalies using deformable slice‐to‐volume registration (DSVR) with comparison to 2D‐manual segmentation. To establish a normogram of TLV calculated by DSVR in healthy control fetuses.

3D black blood MRI atlases of congenital aortic arch anomalies and the normal fetal heart: application to automated multi-label segmentation

Abstract: Background 3D image-domain reconstruction of black blood contrast T2w SSTSE fetal MRI datasets using slice-to-volume registration methods showed to provide high-resolution 3D images of the heart with superior visualisation of fetal aortic arch anomalies [1]. However, there is a lack of formalisation of the MRI appearance of fetal cardiovascular anatomy and standardisation of vessel segmentation protocols. Methods In this work, we present the first set of 3D fetal MRI atlases defining normal and abnormal fetal aortic arch anatomy created from 3D reconstructed images from 87 subjects scanned between 29-34 weeks of gestation with postnatally confirmed outcomes. We also implement and evaluate atlas-guided registration and deep learning (UNETR) methods for automated 3D multi-label fetal heart vessel segmentation. Results We created four atlases representing the average anatomy of the normal fetal heart, coarctation of the aorta, right aortic arch and suspected double aortic arch. Inspection of atlases confirmed the expected pronounced differences in the anatomy of the aortic arch. The results of the multi-label heart vessel UNETR segmentation showed 100% per-vessel detection rate for both normal and abnormal aortic arch anatomy. Conclusions This work introduces the first set of 3D black blood T2w MRI atlases of the normal and abnormal fetal cardiovascular anatomy along with detailed segmentation of the major cardiovascular structures. We also demonstrated the feasibility of using deep learning for multi-label vessel segmentation.

Segmentation of Periventricular White Matter in Neonatal Brain MRI: Analysis of Brain Maturation in Term and Preterm Cohorts

Abstract: AbstractMRI is conventionally employed in neonatal brain diagnosis and research studies. However, the traditional segmentation protocols omit differentiation between heterogeneous white matter (WM) tissue zones that rapidly evolve and change during the early brain development. There is a reported correlations of characteristics of the transient WM compartments (including periventricular regions, subplate, etc.) with brain maturation [23, 26] and neurodevelopment scores [22]. However, there are no currently available standards for parcellation of these regions in MRI scans. Therefore, in this work, we propose the first deep learning solution for automated 3D segmentation of periventricular WM (PWM) regions that would be the first step towards tissue-specific WM analysis. The implemented segmentation method based on UNETR [13] was then used for assessment of the differences between term and preterm cohorts (200 subjects) from the developing Human Connectome Project (dHCP) (dHCP) project [1] in terms of the ROI-specific volumetry and microstructural diffusion MRI indices.KeywordsNeonatal brain MRIPeriventricular white matterBrain maturationAutomated segmentation

3D black blood cardiovascular magnetic resonance atlases of congenital aortic arch anomalies and the normal fetal heart: application to automated multi-label segmentation

Abstract: Abstract Background Image-domain motion correction of black-blood contrast T2-weighted fetal cardiovascular magnetic resonance imaging (CMR) using slice-to-volume registration (SVR) provides high-resolution three-dimensional (3D) images of the fetal heart providing excellent 3D visualisation of vascular anomalies [1]. However, 3D segmentation of these datasets, important for both clinical reporting and the application of advanced analysis techniques is currently a time-consuming process requiring manual input with potential for inter-user variability. Methods In this work, we present novel 3D fetal CMR population-averaged atlases of normal and abnormal fetal cardiovascular anatomy. The atlases are created using motion-corrected 3D reconstructed volumes of 86 third trimester fetuses (gestational age range 29-34 weeks) including: 28 healthy controls, 20 cases with postnatally confirmed neonatal coarctation of the aorta (CoA) and 38 vascular rings (21 right aortic arch (RAA), 17 double aortic arch (DAA)). We used only high image quality datasets with isolated anomalies and without any other deviations in the cardiovascular anatomy.In addition, we implemented and evaluated atlas-guided registration and deep learning (UNETR) methods for automated 3D multi-label segmentation of fetal cardiac vessels. We used images from CoA, RAA and DAA cohorts including: 42 cases for training (14 from each cohort), 3 for validation and 6 for testing. In addition, the potential limitations of the network were investigated on unseen datasets including 3 early gestational age (22 weeks) and 3 low SNR cases. Results We created four atlases representing the average anatomy of the normal fetal heart, postnatally confirmed neonatal CoA, RAA and DAA. Visual inspection was undertaken to verify expected anatomy per subgroup. The results of the multi-label cardiac vessel UNETR segmentation showed 100 $$\%$$ % per-vessel detection rate for both normal and abnormal aortic arch anatomy. Conclusions This work introduces the first set of 3D black-blood T2-weighted CMR atlases of normal and abnormal fetal cardiovascular anatomy including detailed segmentation of the major cardiovascular structures. Additionally, we demonstrated the general feasibility of using deep learning for multi-label vessel segmentation of 3D fetal CMR images.

Automated atlas-based multi-label fetal cardiac vessel segmentation in Congenital Heart Disease

Abstract: Congenital heart disease (CHD) is the most commonly diagnosed birth defect. T2w black blood MRI provides optimal vessel visualisation, aiding prenatal CHD diagnosis. Common clinical practice involves manual segmentation of fetal heart and vessels for visualisation and reporting purposes. We propose an automated multi-label fetal cardiac vessels deep learning segmentation approach for T2w black blood MRI. Our network is trained using single-label manual segmentations obtained through current clinical practice, combined with a multi-label anatomical atlas with desired multi-label segmentation protocol. Our framework combines deep learning label propagation with 3D residual U-Net segmentation to produce high-quality multi-label output well adapted to the individual subject anatomy. We train and evaluate the network using forty fetal subjects with suspected coarctation of the aorta, achieving a dice score of 0.79 ± 0.02 for the fetal cardiac vessels region. The proposed network outperforms the label propagation and achieves a statistically equivalent performance to a 3D residual U-Net trained exclusively on manual single-label data (p-value>0.05). This multi-label framework therefore represents an advancement over the single-label approach, providing label-specific anatomical information, particularly useful for assessing specific anomaly areas in CHD.

Automated Multi-class Fetal Cardiac Vessel Segmentation in Aortic Arch Anomalies Using T2-Weighted 3D Fetal MRI

Abstract: Congenital heart disease (CHD) encompasses a range of cardiac malformations present from birth, representing the leading congenital diagnosis. 3D volumetric reconstructions of T2w black blood fetal MRI provide optimal vessel visualisation, supporting prenatal CHD diagnosis, a key step for optimal patient management. We present a framework for automated multi-class fetal vessel segmentation in the setting where binary manual labels of the vessels region of interest (ROI) are available for training, as well as a multi-class labelled atlas. We combine deep learning label propagation from multi-class labelled condition-specific atlases with 3D Attention U-Net segmentation to achieve the desired multi-class output. We train a single network to segment 12 fetal cardiac vessels for three distinct aortic arch anomalies (double aortic arch, right aortic arch, and suspected coarctation of the aorta). Our segmentation network is trained by combination of a multi-class loss, which uses the propagated multi-class labels; and a binary loss which uses binary labels generated by expert clinicians. Our proposed method outperforms label propagation in accuracy of vessel segmentation, while succeeding in segmenting the anomaly area of all three CHD diagnoses included, achieving a 100% vessel detection rate.

Attention-Driven Multi-channel Deformable Registration of Structural and Microstructural Neonatal Data

Abstract: Image registration of structural and microstructural data allows accurate alignment of anatomical and diffusion channels. However, existing techniques employ simple fusion-based approaches, which use a global weight for each modality, or empirically-driven approaches, which rely on pre-calculated local certainty maps. Here, we present a novel attention-based deep learning deformable image registration solution for aligning multi-channel neonatal MRI data. We learn optimal attention maps to weigh each modality-specific velocity field in a spatially varying fashion, thus allowing for local fusion of structural and microstructural images. We evaluate our proposed method on registrations of 30 multi-channel neonatal MRI to a standard structural and microstructural atlas, and compare it against models trained without the use of attention maps on either single or both modalities. We show that by combining the two channels through attention-driven image registration, we take full advantage of the two complementary modalities, and achieve the best overall alignment of both structural and microstructural data.