AMCNet: Attention-Based Multiscale Convolutional Network for DCM MRI Segmentation

For patients with dilated cardiomyopathy (DCM), fast and accurate diagnosis is important to save lives. MRI is a non-invasive, effective medical imaging method that allows doctors to diagnose DCM. However, manual and semi-automatic segmentation is subjective, non-reproducible and time-consuming task. In this paper, a new attention-based convolutional encoder-decoder network is proposed to automatically segment my-ocardium in DCM, which assisting the doctor to quickly diagnose. In the proposed method, the attention mechanism module is used, which is able to fully highlight useful features that facilitate segmentation while suppress useless features that are not conducive to segmentation. Combining with the multi-scale convolution, our encoder-decoder network can accurately segment the my-ocardium in DCM. We verified our approach on 1155 myocardial MRI. Our network achieves the most advanced segmentation performance on the cardiac DCM dataset. Experiment results demonstrate the effectiveness of the proposed method.

[1]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[2]  Xiaogang Wang,et al.  Residual Attention Network for Image Classification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Jeroen J. Bax,et al.  MRI to Evaluate Left Atrial and Ventricular Reverse Remodeling After Restrictive Mitral Annuloplasty in Dilated Cardiomyopathy , 2005, Circulation.

[4]  Max A. Viergever,et al.  Deep Learning for Multi-Task Medical Image Segmentation in Multiple Modalities , 2016, MICCAI.

[5]  Jiancheng Lv,et al.  Manifold Alignment Based on Sparse Local Structures of More Corresponding Pairs , 2013, IJCAI.

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Mark Benaroia,et al.  Patient-directed intelligent and interactive computer medical history-gathering systems: A utility and feasibility study in the emergency department , 2007, Int. J. Medical Informatics.

[8]  Liu Fu New algorithm of CT/MRI medical image fusion based on wavelet domain , 2013 .

[9]  J. Towbin,et al.  Dilated cardiomyopathy , 2010, The Lancet.

[10]  G. Clarke,et al.  Measuring signal-to-noise ratio in partially parallel imaging MRI. , 2011, Medical physics.

[11]  Zhang Yi,et al.  An Efficient Representation-Based Method for Boundary Point and Outlier Detection , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Xiaojie Li,et al.  How Does the Data set Affect CNN-based Image Classification Performance? , 2018, 2018 5th International Conference on Systems and Informatics (ICSAI).

[13]  Martin Weiß,et al.  An improvement of the convergence proof of the ADAM-Optimizer , 2018, ArXiv.

[14]  S. Bauer,et al.  A survey of MRI-based medical image analysis for brain tumor studies , 2013, Physics in medicine and biology.

[15]  K. S. Prasad,et al.  Multimodal Medical Image Fusion of MRI-PET Using Wavelet Transform , 2012, 2012 International Conference on Advances in Mobile Network, Communication and Its Applications.

[16]  Ronald M. Summers,et al.  Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016 .

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  M J Dunn,et al.  Bovine dilated cardiomyopathy: Proteomic analysis of an animal model of human dilated cardiomyopathy , 1999, Electrophoresis.

[19]  Hayit Greenspan,et al.  Chest pathology detection using deep learning with non-medical training , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[20]  J. Daubert,et al.  Four Chamber Pacing in Dilated Cardiomyopathy , 1994, Pacing and clinical electrophysiology : PACE.

[21]  Ana Morales,et al.  Clinical and genetic issues in dilated cardiomyopathy: A review for genetics professionals , 2010, Genetics in Medicine.

[22]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.