ACNET: Attention-based Convolution Network with Additional Discriminative Features for DCM Classification (S)

For dilated cardiomyopathy (DCM) patients, immediate emergency diagnosis and treatment are critical for life saving and later recovery. T1 mapping is a non-invasive and effective diagnostic imaging approach to detect DCM. However, it is a demanding and time-consuming approach. In this paper, we propose an attention-based network structure, which can automatically identify DCM patients in a speedy manner to prioritize their treatment. In the proposed method, we adopt attention modules to generate attention-aware features. Inside each attention module, a bottom-up top-down feed-forward structure is used to unfold the feed-forward and feed-back attention processes into a single feed-forward process. It allows the network to focus more on determining useful information about the current output that is significant in the input data. Moreover, inspired by the residual network idea, we make full use of the characteristics of the original data. Combined residual block, we design down-residual modules for classification tasks. It consists of seven convolution layers and three layers of residual blocks. Our network achieves the most advanced recognition performance on cardiac datasets. We evaluated our approach on CMR(cardiac magnetic resonance) T1 mapping images with lower PSNR(peak signal to noise ratio), and the results demonstrate that our architecture outperforms previous approaches.

[1]  Birgit Funke,et al.  Familial dilated cardiomyopathy caused by an alpha-tropomyosin mutation: the distinctive natural history of sarcomeric dilated cardiomyopathy. , 2010, Journal of the American College of Cardiology.

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

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

[4]  Simon B. Eickhoff,et al.  Dynamic intra- and interhemispheric interactions during unilateral and bilateral hand movements assessed with fMRI and DCM , 2008, NeuroImage.

[5]  Max Q.-H. Meng,et al.  Tumor CE image classification using SVM-based feature selection , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Laurent Itti,et al.  Neuromorphic algorithms for computer vision and attention , 2001, SPIE Optics + Photonics.

[7]  Loris Nanni,et al.  Computer vision for virus image classification , 2015 .

[8]  Nikolaos D. Doulamis,et al.  Semi-supervised deep learning for object tracking and classification , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[9]  Klaus Schotten,et al.  Circulation of CD34+ progenitor cell populations in patients with idiopathic dilated and ischaemic cardiomyopathy (DCM and ICM). , 2007, European heart journal.

[10]  Chunyu Tian.  A Computer Vision-based Classification Method for Pearl , 2009 .

[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]  Rae-Hong Park,et al.  Residual LSTM Attention Network for Object Tracking , 2018, IEEE Signal Processing Letters.

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

[14]  Jiancheng Lv,et al.  Outlier Detection Using Structural Scores in a High-Dimensional Space , 2020, IEEE Transactions on Cybernetics.

[15]  Michael Kohnen,et al.  The IRMA code for unique classification of medical images , 2003, SPIE Medical Imaging.

[16]  Robert B. Fisher,et al.  Object-based visual attention for computer vision , 2003, Artif. Intell..

[17]  Giles M. Foody,et al.  Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification , 2004 .

[18]  M.C. Krishna,et al.  Convolution-Based Interpolation Kernels for Reconstruction of High Resolution EMR Images from Low Sampled k-Space Data , 2007, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007).

[19]  Xin Yu,et al.  A Semi-supervised manifold alignment algorithm and an evaluation method based on local structure preservation , 2017, Neurocomputing.

[20]  Feng Wang,et al.  Survey on the attention based RNN model and its applications in computer vision , 2016, ArXiv.

[21]  Zhezhou Yu,et al.  Combining Deep Learning and Preference Learning for Object Tracking , 2016, ICONIP.

[22]  Archana M. Rajurkar,et al.  Medical image analysis an attempt for mammogram classification using texture based association rule mining , 2013, 2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG).

[23]  Reza Safabakhsh,et al.  English to Persian transliteration using attention-based approach in deep learning , 2017, 2017 Iranian Conference on Electrical Engineering (ICEE).

[24]  Tao Mei,et al.  Learning Deep Contextual Attention Network for Narrative Photo Stream Captioning , 2017, ACM Multimedia.

[25]  Peng Sun,et al.  An Improved SVM Classifier for Medical Image Classification , 2007, RSEISP.

[26]  Hanqing Lu,et al.  Reading Scene Text with Attention Convolutional Sequence Modeling , 2017, ArXiv.

[27]  I. Buciu,et al.  Gabor wavelet based features for medical image analysis and classification , 2009, 2009 2nd International Symposium on Applied Sciences in Biomedical and Communication Technologies.