10.5281/zenodo.4541606
https://zenodo.org/records/4541606
oai:zenodo.org:4541606
Payette, Kelly
Kelly
Payette
Center for MR-Research, University Children's Hospital Zürich
Jakab, Andras
Andras
Jakab
Center for MR-Research, University Children's Hospital Zürich
Fetal Tissue Annotation Dataset FeTA
Zenodo
2021
fetal
machine learning
image segmentation
MRI
brain development
deep learning
magnetic resonance imaging
fetus
brain
Jakab, Andras
Andras
Jakab
Center for MR Research, University Children's Hospital Zurich
Payette, Kelly
Kelly
Payette
Center for MR Research, University Children's Hospital Zurich
Kottke, Raimund
Raimund
Kottke
Diagnostic Imaging, University Children's Hospital Zurich
Ji, Hui
Hui
Ji
Center for MR Research, University Children's Hospital Zurich
Lanczi, Levente
Levente
Lanczi
University of Debrecen, Hungary
Nagy, Marianna
Marianna
Nagy
University of Debrecen, Hungary
Beresova, Monika
Monika
Beresova
University of Debrecen, Hungary
Nguyen, Thi Dao
Thi Dao
Nguyen
Newborn Research Zurich, Department of Neonatology, University Hospital and University of Zurich, Zurich, Switzerland
Natalucci, Giancarlo
Giancarlo
Natalucci
Newborn Research Zurich, Department of Neonatology, University Hospital and University of Zurich, Zurich, Switzerland
2021-02-15
eng
https://arxiv.org/abs/2010.15526
https://arxiv.org/abs/2010.12391
10.5281/zenodo.4541605
1.2.1
The Fetal Tissue Annotation Dataset (FeTA) consist of manually annotated, T2-weighted, super-resolution reconstructed fetal cerebral magnetic resonance images. It is a mixture of normally developing cases and pathologies. The dataset is a valuable source for developing automated image segmentation algorithms as it provides open source MRI data and expert manual annotations, which is a particularly time consuming process. Each fetal brains were labeled for 7 tissue categories: grey matter, white matter, external CSF spaces, ventricle system, deep gray matter, cerebellum and brainstem.
From May 2021, access to the FeTA dataset is only possible on the Synapse platform. We released the second version with 80 cases, which must be used for participants of the MICCAI Fetal Tissue Annotation Challenge in 2021. Please visit the following sites for further information:
https://feta-2021.grand-challenge.org/
https://www.synapse.org/#!Synapse:syn25649159/wiki/610007
Background
Congenital disorders are one of the leading causes of infant mortality worldwide. Recently, fetal MRI has started to emerge as a valuable tool for investigating the neurological development of fetuses with congenital disorders in order to aid in prenatal planning. Moreover, fetal MRI is a powerful tool to portray the complex neurodevelopmental events during human gestation, which remain to be completely characterized. Automated segmentation and quantification of the highly complex and rapidly changing brain morphology in MRI data would improve the diagnostic process, as manual segmentation is both time consuming and prone to human error and inter-rater variability. The automatic segmentation of the developing human brain would be a first step in being able to perform such an analysis. The FeTA Dataset and the Challenge we plan to organize are important steps in the development of reproducible methods of analyzing high resolution MR images of the developing fetal brain. Such new algorithms will have the potential to better understand the underlying causes of congenital disorders and ultimately to support decision-making and prenatal planning.