Format

Send to

Choose Destination
Neuroimage. 2018 Dec;183:650-665. doi: 10.1016/j.neuroimage.2018.07.005. Epub 2018 Aug 18.

Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images.

Author information

1
School of Data and Computer Science, Sun Yat-sen University, China; Computing, School of Science and Engineering, University of Dundee, UK; Department of Computer Science, Technical University of Munich, Germany.
2
School of Data and Computer Science, Sun Yat-sen University, China.
3
Computing, School of Science and Engineering, University of Dundee, UK. Electronic address: j.n.zhang@dundee.ac.uk.
4
School of Data and Computer Science, Sun Yat-sen University, China. Electronic address: wangruix5@mail.sysu.edu.cn.
5
Department of Computer Science, Technical University of Munich, Germany.

Abstract

White matter hyperintensities (WMH) are commonly found in the brains of healthy elderly individuals and have been associated with various neurological and geriatric disorders. In this paper, we present a study using deep fully convolutional network and ensemble models to automatically detect such WMH using fluid attenuation inversion recovery (FLAIR) and T1 magnetic resonance (MR) scans. The algorithm was evaluated and ranked 1st in the WMH Segmentation Challenge at MICCAI 2017. In the evaluation stage, the implementation of the algorithm was submitted to the challenge organizers, who then independently tested it on a hidden set of 110 cases from 5 scanners. Averaged dice score, precision and robust Hausdorff distance obtained on held-out test datasets were 80%, 84% and 6.30 mm respectively. These were the highest achieved in the challenge, suggesting the proposed method is the state-of-the-art. Detailed descriptions and quantitative analysis on key components of the system were provided. Furthermore, a study of cross-scanner evaluation is presented to discuss how the combination of modalities affect the generalization capability of the system. The adaptability of the system to different scanners and protocols is also investigated. A quantitative study is further presented to show the effect of ensemble size and the effectiveness of the ensemble model. Additionally, software and models of our method are made publicly available. The effectiveness and generalization capability of the proposed system show its potential for real-world clinical practice.

KEYWORDS:

Brain lesion segmentation; Deep learning; Ensemble models; MICCAI WMH segmentation challenge; White matter hyperintensities

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center