Multi-channel Groupwise Registration to Construct an Ultrasound-Specific Fetal Brain Atlas

Namburete, Ana I. L.; Kampen, Raquel van; Papageorghiou, Aris T.; Papież, Bartłomiej W.

doi:10.1007/978-3-030-00807-9_8

Cited by 8 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To obtain atlas labels for our dataset , template images had to be generated for our dataset ( K and K clust ). These template images were created using all images in our dataset ( χ train , χ val , χ test , χ analysis ), as these were available from earlier work [46]. However, the effect on the appearance of the template images of using all images versus only the one used for training is very small, and as such not expected to have a significant effect on the resulting atlas labels.…”

Section: Methodsmentioning

confidence: 99%

“…2). Template images were created by registering a subset of s rigidly aligned images to each other using a Demons diffeomorphic groupwise registration approach [46], resulting in a set of non-rigid transformations that can transform each image from the rigidly aligned orientation to a reference space R defined by: . The registered images were subsequently averaged to obtain a template image .…”

Section: Methodsmentioning

confidence: 99%

“…All network training code as well as the weights of the trained networks can be requested by emailing the corresponding author. The groupwise registration algorithm used to generate the template image in this work was adopted from [46], and requests for this code can be addressed to the corresponding author of that paper.…”

Section: Data and Code Availability Statementmentioning

confidence: 99%

See 2 more Smart Citations

Subcortical Segmentation of the Fetal Brain in 3D Ultrasound using Deep Learning

Hesse

Aliasi

Moser

et al. 2021

Preprint

View full text Add to dashboard Cite

The quantification of subcortical volume development from 3D fetal ultrasound can provide important diagnostic information during pregnancy monitoring. However, manual segmentation of subcortical structures in ultrasound volumes is time-consuming and challenging due to low soft tissue contrast, speckle and shadowing artifacts. For this reason, we developed a convolutional neural network (CNN) for the automated segmentation of the choroid plexus (CP), lateral posterior ventricle horns (LPVH), cavum septum pellucidum et vergae (CSPV), and cerebellum (CB) from 3D ultrasound. As ground-truth labels are scarce and expensive to obtain, we applied few-shot learning, in which only a small number of manual annotations (n = 9) are used to train a CNN. We compared training a CNN with only a few individually annotated volumes versus many weakly labelled volumes obtained from atlas-based segmentations. This showed that segmentation performance close to intra-observer variability can be obtained with only a handful of manual annotations. Finally, the trained models were applied to a large number (n = 278) of ultrasound image volumes of a diverse, healthy population, obtaining novel US-specific growth curves of the respective structures during the second trimester of gestation.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Data and Code Availability Statementmentioning

confidence: 99%

See 1 more Smart Citation

Subcortical Segmentation of the Fetal Brain in 3D Ultrasound using Deep Learning

Hesse

Aliasi

Moser

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We used a diffeomorphic Demons-based approach 59,60 to estimate the mapping that brought each brain image's anatomy into spatial correspondence with all other brain images in the population set. As a consequence of the rapid structural evolution of the brain during intrauterine life, we opted for multi-channel groupwise registration 61,62 : a template-free approach to reduce bias introduced by selecting a fixed reference brain image, and the ability to supplement the US intensity images with (several) extra noise-suppressed edge images. That is, no initial template was selected as input to the non-rigid registration; instead, the atlas was completely derived from the set of population images following an iterative optimization procedure.…”

Section: Atlas Constructionmentioning

confidence: 99%

Normative spatiotemporal fetal brain maturation with satisfactory development at 2 years

Namburete,

Papież,

Fernandes

et al. 2023

Nature

Self Cite

View full text Add to dashboard Cite

Maturation of the human fetal brain should follow precisely scheduled structural growth and folding of the cerebral cortex for optimal postnatal function1. We present a normative digital atlas of fetal brain maturation based on a prospective international cohort of healthy pregnant women2, selected using World Health Organization recommendations for growth standards3. Their fetuses were accurately dated in the first trimester, with satisfactory growth and neurodevelopment from early pregnancy to 2 years of age4,5. The atlas was produced using 1,059 optimal quality, three-dimensional ultrasound brain volumes from 899 of the fetuses and an automated analysis pipeline6–8. The atlas corresponds structurally to published magnetic resonance images9, but with finer anatomical details in deep grey matter. The between-study site variability represented less than 8.0% of the total variance of all brain measures, supporting pooling data from the eight study sites to produce patterns of normative maturation. We have thereby generated an average representation of each cerebral hemisphere between 14 and 31 weeks’ gestation with quantification of intracranial volume variability and growth patterns. Emergent asymmetries were detectable from as early as 14 weeks, with peak asymmetries in regions associated with language development and functional lateralization between 20 and 26 weeks’ gestation. These patterns were validated in 1,487 three-dimensional brain volumes from 1,295 different fetuses in the same cohort. We provide a unique spatiotemporal benchmark of fetal brain maturation from a large cohort with normative postnatal growth and neurodevelopment.

show abstract

“…However, the selection of a single subject as reference space introduces bias to the registrations which propagates to subsequent analysis. For example, if the selected reference volume has atypical anatomical features then all registrations are potentially more challenging and will estimate atypical and/or implausible transformations (Namburete et al 2018). Choosing an adequate reference is a challenging problem, 125 particularly for the paediatric cancer population, known to be heterogeneous and prone to deviations in anatomy.…”

mentioning

confidence: 99%

Atlas construction and spatial normalisation to facilitate radiation-induced late effects research in childhood cancer

et al. 2021

View full text Add to dashboard Cite

Reducing radiation-induced side effects is one of the most important challenges in paediatric cancer treatment. Recently, there has been growing interest in using spatial normalisation to enable voxel-based analysis of radiation-induced toxicities in a variety of patient groups. The need to consider three-dimensional distribution of doses, rather than dose-volume histograms, is desirable but not yet explored in paediatric populations. In this paper, we investigate the feasibility of atlas construction and spatial normalisation in paediatric radiotherapy. We used planning computed tomography (CT) scans from twenty paediatric patients historically treated with craniospinal irradiation to generate a template CT that is suitable for spatial normalisation. This childhood cancer population representative template was constructed using groupwise image registration. An independent set of 53 subjects from a variety of childhood malignancies was then used to assess the quality of the propagation of new subjects to this common reference space using deformable image registration (i.e. spatial normalisation). The method was evaluated in terms of overall image similarity metrics, contour similarity and preservation of dose-volume properties. After spatial normalisation, we report a dice similarity coefficient of 0.95 ± 0.05, 0.85 ± 0.04, 0.96 ± 0.01, 0.91 ± 0.03, 0.83 ± 0.06 and 0.65 ± 0.16 for brain and spinal canal, ocular globes, lungs, liver, kidneys and bladder. We then demonstrated the potential advantages of an atlas-based approach to study the risk of second malignant neoplasms after radiotherapy. Our findings indicate satisfactory mapping between a heterogeneous group of patients and the template CT. The poorest performance was for organs in the abdominal and pelvic region, likely due to respiratory and physiological motion and to the highly deformable nature of abdominal organs. More specialised algorithms should be explored in the future to improve mapping in these regions. This study is the first step toward voxel-based analysis in radiation-induced toxicities following paediatric radiotherapy.

show abstract

Multi-channel Groupwise Registration to Construct an Ultrasound-Specific Fetal Brain Atlas

Cited by 8 publications

References 20 publications

Subcortical Segmentation of the Fetal Brain in 3D Ultrasound using Deep Learning

Subcortical Segmentation of the Fetal Brain in 3D Ultrasound using Deep Learning

Normative spatiotemporal fetal brain maturation with satisfactory development at 2 years

Atlas construction and spatial normalisation to facilitate radiation-induced late effects research in childhood cancer

Contact Info

Product

Resources

About