DPA-UNet
Detail preserving attention UNet for cardiac MRI ventricle region segmentation
Abstract
Cardiac Magnetic Resonance Image (MRI) plays an integral part in examining the clinical problems of cardiac disorders. The purpose is to extract effectual information from ventricle regions in which the structure varies due to systolic and diastolic phases of the heart. The proposed methodology – Detail Preserving Attention UNet (DPA-UNet) improves the level of clinical diagnosis to identify the requisite parts of analysis precisely. Thus it provides the best possible results with appropriate accuracy. In recent years, the attention and awareness towards deep learning approaches have widely been increased, where a neural network can automatically learn image features. The latter is in direct disparity with conventional deep learning approaches. UNet with attention-based models is considered the most crucial semantic segmentation framework for Cardiac MRI. The ventricle regions can be extracted by the methodology of DPA-UNet which performs through two modules such as spatial and channel attention. Initially, the channel attention module is processed with max-pool to extract the dominant features to segment the area of concentration. Subsequently, the spatial attention module is processed with an average pool to extract the global features of the ventricular regions. The process of integration proceeds subsequently.
Downloads
References
Mohammad Hesam Hesamian, WenjingJia, Xiangjian He, Paul Kennedy, “Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges”, Journal of Digital Imaging, https://doi.org/10.1007/s10278-019-00227-x, 2019
Bengio, Y., Courville, A., Vincent, P.: Representation learning: A review and new perspectives. Pattern Analysis and Machine Intelligence, IEEE Transactions on 35(8), 1798–1828 (2013)
Alvarez, J.M., et al.: Road scene segmentation from a single image. In: Computer Vision–ECCV 2012, pp. 376–389. Springer (2012).
Hariharan1, B., et al.: Simultaneous detection and segmentation. arXiv preprint arXiv:1407.1808 (2014).
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3431–3440 (2015)
Mohammad Havaei,” Deep learning trends for focal brain pathology segmentation in MRI”, Machine Learning for Health Informatics, arXiv:1607.05258v3 [cs.CV] 24 Jan 2017.
Chen Chen1, Chen Qin, HuaqiQiu, Giacomo Tarroni, JinmingDuan, Wenjia Bai and Daniel Rueckert, “Deep Learning for Cardiac Image Segmentation: A Review” Frontiers in cardiovascular medicine, Volume 7, article 25, March 2020.
Shervin Minaee, Yuri Boykov, FatihPorikli, Antonio Plaza, Nasser Kehtarnavaz, and Demetri Terzopoulos, “Image Segmentation Using Deep Learning: A Survey”, arXiv:2001.05566v5 [cs.CV] 15 Nov 2020.
Shaoqiong Huang, “Medical image segmentation using deep learning with feature enhancement”, ET Image Process., 2020, Vol. 14 Iss. 14, pp. 3324-3332.
Olaf Ronneberger, “U-Net: Convolutional Networks for Biomedical Image Segmentation”, Springer International Publishing Switzerland 2015, MICCAI 2015, Part III, LNCS 9351, pp. 234–241, DOI: 10.1007/978-3-319-24574-4_28.
Dominik Müller, “MIScnn: a framework for medical image segmentation with convolutional neural networks and deep learning”, Müller and Kramer BMC Med Imaging (2021) 21:12
NAHIAN SIDDIQUE, “U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications”, IEEE, VOLUME 9, 2021.
V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: a deep convolutional encoder-decoder architecture for image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 12, pp. 2481–2495, 2017.
Jonathan Long, “Fully Convolutional Networks for Semantic Segmentation”, IEEE, 978-1-4673-6964-0/15
Liset Vázquez Romaguera, Francisco Perdigón Romero, “Left ventricle segmentation in cardiac MRI images using fully convolutional neural networks”, February 2017 DOI: 10.1117/12.2253901.
Chen Li, Yusong Tan, “ANU-Net: Attention-based nested U-Net to exploit full resolution features for medical image segmentation”, Computers & Graphics, MAY 2020.
Christian F. Baumgartner, “An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation”, LNCS 10663, pp. 111–119, 2018.https://doi.org/10.1007/978-3-319-75541-0_18
Fabian Isensee, “Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain-Specific Features”, LNCS 10663, pp. 120–129, 2018.https://doi.org/10.1007/978-3-319-75541-0_13
Yeonggul Jang, “Automatic Segmentation of LV and RV in Cardiac MRI”, LNCS 10663, pp. 161–169, 2018.https://doi.org/10.1007/978-3-319-75541-0_17
MahendraKhened, “Densely Connected Fully Convolutional Network for Short-Axis Cardiac Cine MR Image Segmentation and Heart Diagnosis Using Random Forest”, LNCS 10663, pp. 140–151, 2018.https://doi.org/10.1007/978-3-319-75541-0_18
Jay Patravali, “2D-3D Fully Convolutional Neural Networks for Cardiac MR Segmentation”, 7, LNCS 10663, pp. 130–139, 2018.https://doi.org/10.1007/978-3-319-75541-0_14
Marc-Michel Rohé, MaximeSermesant, Xavier Pennec. Automatic Multi-Atlas Segmentation of Myocardium with SVF-Net. STACOM: Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges, Sep 2017, Québec, Canada. pp.170-177, ff10.1007/978-3-319-75541- 0_18ff. ffhal-01575297f
Jelmer M. Wolterink, “Automatic Segmentation and Disease Classification Using Cardiac Cine MR Images”, LNCS 10663, pp. 101–110, 2018.https://doi.org/10.1007/978-3-319-75541-0_11
Xin Yang,” Class-Balanced Deep Neural Network for Automatic Ventricular Structure Segmentation”, LNCS 10663, pp. 152–160, 2018.https://doi.org/10.1007/978-3-319-75541-0_16.
G. Gomathi, Dr.V.Subha, “Semantic Segmentation of Ventricular and Myocardium Regions in Cardiac MRI”, ISSN: 0011-9342, Issue: 9, Pages: 8510-8522, 2021.
Sanghyun Woo,” CBAM: Convolutional Block Attention Module”, arXiv:1807.06521v2 [cs.CV] 18 Jul 2018.
Trinh Le Ba Khanh, “Enhancing U-Net with Spatial-Channel Attention Gate for Abnormal Tissue Segmentation in Medical Imaging”, Appl. Sci. 2020, 10, 5729; doi:10.3390/app10175729reeLong Chen, “SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning”, IEEE
Jingfei Hu, “SA-Net: A scale-attention network for medical image segmentation”, PLOS ONE | https://doi.org/10.1371/journal.pone.0247388 April 14, 202
Peng Zhao, “SCAU-Net: Spatial-Channel AttentionU-Net for Gland Segmentation”, Frontiers, published: 03 July 2020, DOI: 10.3389/fbioe.2020.00670.
YutongCai, “ MA-UNet: An improved version of UNet based on multi-scale and attention mechanism for medical image segmentation”,arXiv:2012.10952v1 [eess.IV] 20 Dec 2020
Published
How to Cite
Issue
Section
Copyright (c) 2022 International journal of health sciences
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in the International Journal of Health Sciences (IJHS) are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJHS right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.
Articles published in IJHS can be copied, communicated and shared in their published form for non-commercial purposes provided full attribution is given to the author and the journal. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
This copyright notice applies to articles published in IJHS volumes 4 onwards. Please read about the copyright notices for previous volumes under Journal History.
