Qianqian Tong1, Caizi Li2, Weixin Si3, Xiangyun Liao4, Yaliang Tong5, Zhiyong Yuan2, Pheng Ann Heng6. 1. School of Computer Science, Wuhan University, Wuhan, 430072, China; Guangdong Provincial Key Laboratory of Machine Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China. 2. School of Computer Science, Wuhan University, Wuhan, 430072, China. 3. Guangdong Provincial Key Laboratory of Machine Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China. 4. Guangdong Provincial Key Laboratory of Machine Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China. Electronic address: xyunliao@gmail.com. 5. Department of Cardiology China-Japan Union Hospital of Jilin University, Changchun, 130000, China. 6. Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China; Guangdong Provincial Key Laboratory of Machine Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China.
Abstract
BACKGROUND: Segmentation of anatomical structures of the heart from cardiac magnetic resonance images (MRI) has a significant impact on the quantitative analysis of the cardiac contractile function. Although deep convolutional neural networks (ConvNets) have achieved considerable success in medical imaging segmentation, it is still a challenging task for existing deep ConvNets to precisely and automatically segment multiple heart structures from cardiac MRI. This paper presents a novel recurrent interleaved attention network (RIANet) to comprehensively tackle this issue. METHOD: The proposed RIANet can efficiently reuse parameters to encode richer representative features via introducing a recurrent feedback structure, Clique Block, which incorporates both forward and backward connections between different layers with the same resolution. Further, we integrate a plug-and-play interleaved attention (IA) block to modulate the information passed to the decoding stage of RIANet by effectively fusing multi-level contextual information. In addition, we improve the discrimination capability of our RIANet through a deep supervision mechanism with weighted losses. RESULTS: The performance of RIANet has been extensively validated in the segmentation contest of the ACDC 2017 challenge held in conjunction with MICCAI 2017, with mean Dice scores of 0.942 (left ventricular), 0.923 (right ventricular) and 0.910 (myocardium) for cardiac MRI segmentation. Besides, we visualize intermediate features of our RIANet using guided backpropagation, which can intuitively depict the effects of our proposed components in feature representation. CONCLUSION: Experimental results demonstrate that our RIANet have achieved competitive segmentation results with fewer parameters compared with the state-of-the-art approaches, corroborating the effectiveness and robustness of our proposed RIANet.
BACKGROUND: Segmentation of anatomical structures of the heart from cardiac magnetic resonance images (MRI) has a significant impact on the quantitative analysis of the cardiac contractile function. Although deep convolutional neural networks (ConvNets) have achieved considerable success in medical imaging segmentation, it is still a challenging task for existing deep ConvNets to precisely and automatically segment multiple heart structures from cardiac MRI. This paper presents a novel recurrent interleaved attention network (RIANet) to comprehensively tackle this issue. METHOD: The proposed RIANet can efficiently reuse parameters to encode richer representative features via introducing a recurrent feedback structure, Clique Block, which incorporates both forward and backward connections between different layers with the same resolution. Further, we integrate a plug-and-play interleaved attention (IA) block to modulate the information passed to the decoding stage of RIANet by effectively fusing multi-level contextual information. In addition, we improve the discrimination capability of our RIANet through a deep supervision mechanism with weighted losses. RESULTS: The performance of RIANet has been extensively validated in the segmentation contest of the ACDC 2017 challenge held in conjunction with MICCAI 2017, with mean Dice scores of 0.942 (left ventricular), 0.923 (right ventricular) and 0.910 (myocardium) for cardiac MRI segmentation. Besides, we visualize intermediate features of our RIANet using guided backpropagation, which can intuitively depict the effects of our proposed components in feature representation. CONCLUSION: Experimental results demonstrate that our RIANet have achieved competitive segmentation results with fewer parameters compared with the state-of-the-art approaches, corroborating the effectiveness and robustness of our proposed RIANet.
Authors: Nadine Kawel-Boehm; Scott J Hetzel; Bharath Ambale-Venkatesh; Gabriella Captur; Christopher J Francois; Michael Jerosch-Herold; Michael Salerno; Shawn D Teague; Emanuela Valsangiacomo-Buechel; Rob J van der Geest; David A Bluemke Journal: J Cardiovasc Magn Reson Date: 2020-12-14 Impact factor: 5.364