Ψ-Net: Focusing on the border areas of intracerebral hemorrhage on CT images. (October 2020)

• Record Type: Journal Article
• Authors: Kuang, Zhuo; Deng, Xianbo; Yu, Li; Wang, Hongkui; Li, Tiansong; Wang, Shengwei
• Is Part Of: Computer methods and programs in biomedicine. Volume 194(2020)
• Publication Date: 2020-10
• Subjects: Intracerebral hemorrhage -- Convolutional neural networks -- Medical image segmentation -- Attention mechanism; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105546
• Languages: English
• ISSNs: 0169-2607

Abstract

Abstract : highlights: A CNN-based architecture is proposed for the ICH segmentation on CT images. It consists of a novel model, named as Ψ-Net, and a multi-level training strategy. With the help of two attention blocks, Ψ-Net could suppress the irrelevant information, and capture the spatial contextual information to fine tune the border areas of the ICH. The multi-level training strategy includes two levels of tasks, classification and segmentation. It speeds up the rate of convergence and alleviate the vanishing gradient and class imbalance problems. Compared to the previous works on the ICH segmentation. Our method takes less time for training, and obtains more accurate and robust performance. Abstract: Background and objective: The volume of the intracerebral hemorrhage (ICH) obtained from CT scans is essential for quantification and treatment planning. However, a fast and accurate volume acquisition brings great challenges. On the one hand, it is both time consuming and operator dependent for manual segmentation, which is the gold standard for volume estimation. On the other hand, low contrast to normal tissues, irregular shapes and distributions of the hemorrhage make the existing automatic segmentation methods hard to achieve satisfactory performance. Method: To solve above problems, a CNN-based architecture is proposed in this work, consisting of a novel model, which is named as Ψ-Net and a multi-level training strategy. In the structure of Ψ-Net, a self-attention block and a contextual-attention block is designed to suppresses the irrelevant information and segment border areas of the hemorrhage more finely. Further, an multi-level training strategy is put forward to facilitate the training process. By adding the slice-level learning and a weighted loss, the multi-level training strategy effectively alleviates the problems of vanishing gradient and the class imbalance. The proposed training strategy could be applied to most of the segmentation networks, especially for complex models and on small datasets. Results: The proposed architecture is evaluated on a spontaneous ICH dataset and a traumatic ICH dataset. Compared to the previous works on the ICH sementation, the proposed architecture obtains the state-of-the-art performance(Dice of 0.950) on the spontaneous ICH, and comparable results(Dice of 0.895) with the best method on the traumatic ICH. On the other hand, the time consumption of the proposed architecture is much less than the previous methods on both training and inference. Morever, experiment results on various of models prove the universality of the multi-level training strategy. Conclusions: This study proposed a novel CNN-based architecture, Ψ-Net with multi-level training strategy. It takes less time for training and achives superior performance than previous ICH segmentaion methods.