1. An automatic multi-tissue human fetal brain segmentation benchmark using the Fetal Tissue Annotation Dataset
- Author
-
Hamza Kebiri, Kelly Payette, Raimund Kottke, Ivan Ezhov, Hui Ji, Thi Dao Nguyen, Meritxell Bach Cuadra, Levente Lanczi, Bjoern H. Menze, Monika Béresová, Johannes C. Paetzold, Theofanis Karayannis, Priscille de Dumast, Giancarlo Natalucci, Andras Jakab, Patrice Grehten, Suprosanna Shit, Marianna Nagy, Romesa Khan, Asim Iqbal, University of Zurich, and Payette, Kelly
- Subjects
FOS: Computer and information sciences ,Data Descriptor ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,volume reconstruction ,shape ,1710 Information Systems ,030218 nuclear medicine & medical imaging ,0302 clinical medicine ,Brain segmentation ,Segmentation ,atlas ,1804 Statistics, Probability and Uncertainty ,2613 Statistics and Probability ,Data Curation ,medicine.diagnostic_test ,Image and Video Processing (eess.IV) ,Brain ,Organ Size ,Magnetic Resonance Imaging ,Computer Science Applications ,Benchmarking ,medicine.anatomical_structure ,Brain size ,Brainstem ,Statistics, Probability and Uncertainty ,Biomedical engineering ,Algorithms ,Information Systems ,3304 Education ,Statistics and Probability ,Neurogenesis ,Science ,610 Medicine & health ,Library and Information Sciences ,Grey matter ,Paediatric research ,Congenital Abnormalities ,Education ,White matter ,03 medical and health sciences ,Fetus ,medicine ,FOS: Electrical engineering, electronic engineering, information engineering ,1706 Computer Science Applications ,Humans ,mri ,business.industry ,Magnetic resonance imaging ,Pattern recognition ,Electrical Engineering and Systems Science - Image and Video Processing ,Spinal cord ,10027 Clinic for Neonatology ,images ,10036 Medical Clinic ,Artificial intelligence ,3309 Library and Information Sciences ,business ,intensity ,11493 Department of Quantitative Biomedicine ,030217 neurology & neurosurgery ,superresolution - Abstract
It is critical to quantitatively analyse the developing human fetal brain in order to fully understand neurodevelopment in both normal fetuses and those with congenital disorders. To facilitate this analysis, automatic multi-tissue fetal brain segmentation algorithms are needed, which in turn requires open datasets of segmented fetal brains. Here we introduce a publicly available dataset of 50 manually segmented pathological and non-pathological fetal magnetic resonance brain volume reconstructions across a range of gestational ages (20 to 33 weeks) into 7 different tissue categories (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, deep grey matter, brainstem/spinal cord). In addition, we quantitatively evaluate the accuracy of several automatic multi-tissue segmentation algorithms of the developing human fetal brain. Four research groups participated, submitting a total of 10 algorithms, demonstrating the benefits the dataset for the development of automatic algorithms., Scientific Data, 8 (1), ISSN:2052-4463
- Published
- 2021
- Full Text
- View/download PDF