Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images

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 1 st 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 6.30mm respectively. These were the highest achieved in the challenge, suggesting the proposed method is the state-of-the-art. In this paper, we provide detailed descriptions and quantitative analysis on key components of the system. Furthermore, a study of cross-scanner evaluation is presented to discuss how the combination of modalities and data augmentation 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 test the effect of ensemble size. 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.

arXiv commentfinal version in NeuroImage

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• Popular Ensemble Methods: An Empirical Study
• Fully Convolutional Networks for Semantic Segmentation
• Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
• Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation

Cited by in corpus (19)

• The Liver Tumor Segmentation Benchmark (LiTS)
• Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge
• Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation
• Unsupervised brain lesion segmentation from MRI using a convolutional autoencoder
• Automated Claustrum Segmentation in Human Brain MRI Using Deep Learning
• Simultaneous synthesis of FLAIR and segmentation of white matter hypointensities from T1 MRIs
• Ensembling Low Precision Models for Binary Biomedical Image Segmentation
• Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation
• Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns
• Multi-Scale Convolutional-Stack Aggregation for Robust White Matter Hyperintensities Segmentation
• Brain Atlas Guided Attention U-Net for White Matter Hyperintensity Segmentation
• A post-processing method to improve the white matter hyperintensity segmentation accuracy for randomly-initialized U-net
• Random Bundle: Brain Metastases Segmentation Ensembling through Annotation Randomization
• Ensemble Methods for Multi-Organ Segmentation in CT Series
• Automatic Brain Structures Segmentation Using Deep Residual Dilated U-Net
• Self-supervised Lesion Change Detection and Localisation in Longitudinal Multiple Sclerosis Brain Imaging
• ACEnet: Anatomical Context-Encoding Network for Neuroanatomy Segmentation
• Ensemble of Multi-sized FCNs to Improve White Matter Lesion Segmentation
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation