Fetal Brain Tissue Annotation and Segmentation Challenge Results
Abstract
In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, brainstem, deep grey matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.
Cite
@article{arxiv.2204.09573,
title = {Fetal Brain Tissue Annotation and Segmentation Challenge Results},
author = {Kelly Payette and Hongwei Li and Priscille de Dumast and Roxane Licandro and Hui Ji and Md Mahfuzur Rahman Siddiquee and Daguang Xu and Andriy Myronenko and Hao Liu and Yuchen Pei and Lisheng Wang and Ying Peng and Juanying Xie and Huiquan Zhang and Guiming Dong and Hao Fu and Guotai Wang and ZunHyan Rieu and Donghyeon Kim and Hyun Gi Kim and Davood Karimi and Ali Gholipour and Helena R. Torres and Bruno Oliveira and João L. Vilaça and Yang Lin and Netanell Avisdris and Ori Ben-Zvi and Dafna Ben Bashat and Lucas Fidon and Michael Aertsen and Tom Vercauteren and Daniel Sobotka and Georg Langs and Mireia Alenyà and Maria Inmaculada Villanueva and Oscar Camara and Bella Specktor Fadida and Leo Joskowicz and Liao Weibin and Lv Yi and Li Xuesong and Moona Mazher and Abdul Qayyum and Domenec Puig and Hamza Kebiri and Zelin Zhang and Xinyi Xu and Dan Wu and KuanLun Liao and YiXuan Wu and JinTai Chen and Yunzhi Xu and Li Zhao and Lana Vasung and Bjoern Menze and Meritxell Bach Cuadra and Andras Jakab},
journal= {arXiv preprint arXiv:2204.09573},
year = {2023}
}
Comments
Results from FeTA Challenge 2021, held at MICCAI; Manuscript submitted