Automatic segmentation of intracerebral hemorrhage in CT images using encoder–decoder convolutional neural network. Issue 6 (November 2020)

• Record Type: Journal Article
• Authors: Hu, Kai; Chen, Kai; He, Xizhi; Zhang, Yuan; Chen, Zhineng; Li, Xuanya; Gao, Xieping
• Is Part Of: Information processing & management. Volume 57:Issue 6(2020:Nov.)
• Publication Date: 2020-11
• Subjects: Intracerebral hemorrhage -- Segmentation -- Convolutional neural networks -- Multi-scale features -- Data imbalance; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2020.102352
• Languages: English
• ISSNs: 0306-4573

Abstract

Highlights: We develop an encoder-decoder convolutional neural network (ED-Net). We introduce a synthetic loss function to overcome the data imbalanced problem. We propose a novel method using ED-Net for intracranial hemorrhage segmentation. We evaluate ED-Net on a multi-center intracranial hemorrhage clinical dataset. Both quantitative and visual results show ED-Net outperforms other methods. Abstract: Intracerebral hemorrhage (ICH) is the most serious type of stroke, which results in a high disability or mortality rate. Therefore, accurate and rapid ICH region segmentation is of great significance for clinical diagnosis and treatment of ICH. In this paper, we focus on deep neural networks to automatically segment ICH regions. Firstly, we propose an encoder-decoder convolutional neural network (ED-Net) architecture to comprehensively utilizing both the low-level and high-level semantic information. Specifically, the encoder is used to extract multi-scale semantic feature information, while the decoder integrates them to form a unified ICH feature representation. Secondly, we introduce a synthetic loss function by paying more attention to the small ICH regions to overcome the data imbalanced problem. Thirdly, to improve the clinical adaptability of the proposed model, we collect 480 patient cases with ICH from four hospitals to construct a multi-center dataset, in which each case contains the first and review CT scans. In particular, CT scans of different patients are diverse, which greatly increases the difficulty of segmentation. Finally, we evaluate ED-Net on the multi-center ICH clinical dataset from different model parameters and different loss functions. We also compare the results of ED-Net with nine state-of-the-art methods in the literature. Both quantitative and visual results have shown that ED-Net outperforms other methods by providing more accurate and stable performance.