Abstract
Convolutional neural networks originate from image classification tasks. The pooling operation can expand the receptive field and reduce the amount of calculation, but a large amount of pixel information can be lost, which is obviously harmful to pixel-level segmentation accuracy. Dilation convolution expands the receptive field and keeps the resolution unchanged, but it increases the amount of data storage and calculation. Therefore, dilation convolution can only be applied to a limited number of deep layers in a network. It is common that different samples have different sizes in medical image dataset. The resize operation is widely used in the field to obtain uniform sizes. However, the resize operation adds, deletes and modifies a large number of pixels based on the interpolation method. In this way, an image after resizing is damaged to a certain extent at the pixel level, which also significantly affects the performance of the segmentation network. We propose a resolution-consistent network (RCN), which removes all pooling layers and keeps all resolutions consistent to solve the data loss problem caused by downsampling operations. To solve the problem of the increased amount of data storage and calculation caused by dilated convolution and the data damage caused by the resize operation, we propose a nondamage data preprocessing method that includes a coarse segmentation network, cardiac center point positioning algorithm and nondamage cropping to avoid any resize operations. We achieve state-of-the-art performance and reach first place with respect to some indicators on the widely-used automated cardiac diagnosis challenge (ACDC) dataset. Our average dice scores are 0.951 (left ventricle), 0.915 (right ventricle) and 0.910 (myocardium) on the test set.
Similar content being viewed by others
Code Availability
Our code link is https://github.com/542250984/ACDC-cardiac-segmentation.
References
Ang Y, Hong Y, Ha S et al (2017) Automatic segmentation of LV and RV in cardiac MRI. In: International workshop on statistical atlases and computational models of the heart. Springer, pp 161–169
Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39:2481–2495
Bernard O, Lalande A, Zotti C et al (2018) Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans Med Imaging 37:2514–2525
Bustamante M, Gupta V, Forsberg D et al (2018) Automated multi-atlas segmentation of cardiac 4D flow MRI. Med Image Anal 49:128–140
Calisto MB, Lai-Yuen SK (2020) Adaen-net: An ensemble of adaptive 2D–3D Fully Convolutional Networks for medical image segmentation. Neural Netw 126:76–94
Chaurasia A, Culurciello E (2017) Linknet: Exploiting encoder representations for efficient semantic segmentation. In: 2017 IEEE visual communications and image processing (VCIP). IEEE, pp 1–4
Chen K, Franko K, Sang R (2021) Structured model pruning of convolutional networks on tensor processing units. https://doi.org/10.48550/arXiv.2107.04191. arXiv:2107.04191
Chen LC, Papandreou G, Kokkinos I et al (2014) Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv:1412.7062
Chen LC, Papandreou G, Kokkinos I et al (2017) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40:834–848
Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587
Chen C, Wang G, Peng C, Zhang D, Fang Y, Qin H (2020) Exploring rich and efficient spatial temporal interactions for real time video salient object detection. arXiv:2008.02973
Chen C, Wang G, Peng C, Zhang X, Qin H (2019) Improved robust video saliency detection based on long-term spatial-temporal information. IEEE Trans Image Process 29:1090–1100
Chen C, Wei J, Peng C, Zhang W, Qin H (2020) Improved saliency detection in RGB-d images using two-phase depth estimation and selective deep fusion. IEEE Trans Image Process 29:4296–4307
Dou Q, Yu L, Chen H et al (2017) 3D deeply supervised network for automated segmentation of volumetric medical images. Med Image Anal 41:40–54
Duan J, Bello G, Schlemper J et al (2019) Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach. IEEE Trans Med Imaging 38:2151–2164
Fan DP, Wang W, Cheng MM, Shen J (2019) Shifting more attention to video salient object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8554–8564
Ganaye PA, Sdika M, Triggs B et al (2019) Removing segmentation inconsistencies with semi-supervised non-adjacency constraint. Med Image Anal 58:101551. https://doi.org/10.1016/j.media.2019.101551
Geng L, Zhang S, Tong J, Xiao Z (2019) Lung segmentation method with dilated convolution based on VGG-16 network. Computer Assisted Surgery 24:27–33
Guan D, Huang J, Lu S, Xiao A (2021) Scale variance minimization for unsupervised domain adaptation in image segmentation. Pattern Recogn 112:107764. https://doi.org/10.1016/j.patcog.2020.107764
Ieracitano C, Paviglianiti A, Campolo M, Hussain A, Pasero E, Morabito FC (2021) A novel automatic classification system based on hybrid unsupervised and supervised machine learning for electrospun nanofibers. IEEE/CAA Journal of Automatica Sinica 8(1):64–76. https://doi.org/10.1109/JAS.2020.1003387
Iglesias JE, Sabuncu MR (2015) Multi-atlas segmentation of biomedical images: a survey. Med Image Anal 24:205–219
Isensee F, Jaeger PF, Full PM et al (2017) Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features. In: International workshop on statistical atlases and computational models of the heart. Springer, pp 120–129
Islam MA, Rochan M, Bruce NDB, Wang Y (2017) Gated feedback refinement network for dense image labeling. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3751–3759
Jégou S, Drozdzal M, Vazquez D, Romero A, Bengio Y (2017) The one hundred layers tiramisu: Fully convolutional densenets for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 11–19
Khened M, Alex V, Krishnamurthi G (2017) Densely connected fully convolutional network for short-axis cardiac cine MR image segmentation and heart diagnosis using random forest. In: International workshop on statistical atlases and computational models of the heart. Springer, pp 140–151
Kirisli HA, Schaap M, Klein S et al (2010) Fully automatic cardiac segmentation from 3D CTA data: a multi-atlas based approach. In: Medical Imaging 2010: Image Processing. International Society for Optics and Photonics. 7623:762305. https://doi.org/10.1117/12.838370
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
Kudo Y, Aoki Y (2017) Dilated convolutions for image classification and object localization. In: 2017 Fifteenth IAPR international conference on machine vision applications (MVA). IEEE, pp 452–455
Lecun Y, Bottou L (1998) Gradient-based learning applied to document recognition. Proc IEEE 86:2278–2324
Lieman-Sifry J, Le M, Lau F, Sall S, Golden D (2017) FastVentricle: cardiac segmentation with ENet. In: International conference on functional imaging and modeling of the heart. Springer, pp 127–138
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440
Painchaud N, Skandarani Y, Judge T et al (2020) Cardiac segmentation with strong anatomical guarantees. IEEE Trans Med Imaging 39:3703–3713
Poudel RPK, Lamata P, Montana G (2016) Recurrent fully convolutional neural networks for multi-slice MRI cardiac segmentation. In: Reconstruction, segmentation, and analysis of medical images. Springer, pp 83–94
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234–241
Santos CFGD, Moreira TP, Colombo D et al (2020) Does removing pooling layers from convolutional neural networks improve results? SN Computer Science 1:1–10
Skandarani Y, Painchaud N, Jodoin PM, Lalande A (2020) On the effectiveness of GAN generated cardiac MRIs for segmentation. arXiv:2005.09026
Tran PV (2016) A fully convolutional neural network for cardiac segmentation in short-axis MRI. https://doi.org/10.48550/arXiv.1604.00494. arXiv:1604.00494
Ullah I, Jian M, Hussain S et al (2020) DSFMA: Deeply supervised fully convolutional neural networks based on multi-level aggregation for saliency detection. Multimed Tools Appl 80:7145–7165
Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, Cottrell G (2018) Understanding convolution for semantic segmentation. In: 2018 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 1451–1460, DOI https://doi.org/10.1109/WACV.2018.00163, (to appear in print)
Wei Z, Shi F, Song H, Ji W, Han G (2020) Attentive boundary aware network for multi-scale skin lesion segmentation with adversarial training. Multimed Tools Appl 79:27115–27136
Wu H, Zhang J, Huang K, Liang K, Yu Y (2019) Fastfcn: Rethinking dilated convolution in the backbone for semantic segmentation. arXiv:1903.11816
Xia P, He J, Yin J (2020) Boosting image caption generation with feature fusion module. Multimed Tools Appl 79(33):24225–24239
Xiao Y, Tian Z, Yu J et al (2020) A review of object detection based on deep learning. Multimed Tools Appl 79(33):23729–23791
Yamashita T, Furukawa H, Fujiyoshi H (2018) Multiple skip connections of dilated convolution network for semantic segmentation. In: 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, pp 1593–1597
Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122
Zhang Q, Cui Z, Niu X, Geng S, Qiao Y (2017) Image segmentation with pyramid dilated convolution based on ResNet and U-Net. In: International Conference on Neural Information Processing. Springer, pp 364–372
Zhang J, Lu C, Wang J et al (2019) Concrete cracks detection based on FCN with dilated convolution. Appl Sci 9(13):2686. https://doi.org/10.3390/app9132686
Zhou R, Liao Z, Pan T et al (2017) Cardiac atlas development and validation for automatic segmentation of cardiac substructures. Radiother Oncol 122:66–71
Zhou L, Zhang C, Wu M (2018) D-linknet: Linknet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 182–186
Zhuang X, Bai W, Song J, Zhan S, Qian X, Shi W, Lian Y, Rueckert D (2015) Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection. Med Phys 42(7):3822–3833
Zhuang X, Li L, Payer C et al (2019) Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge. Med Image Anal 58:101537. https://doi.org/10.1016/j.media.2019.101537
Zotti C, Luo Z, Lalande A et al (2018) Convolutional neural network with shape prior applied to cardiac MRI segmentation. IEEE J Biomed Health Inform 23:1119–1128
Zuluaga MA, Cardoso MJ, Modat M, Ourselin S (2013) Multi-atlas propagation whole heart segmentation from MRI and CTA using a local normalised correlation coefficient criterion. In: International conference on functional imaging and modeling of the heart. Springer, pp 174–181
Funding
This research is supported in part by Beijing Natural Science Foundation (5182018), the National Natural Science Foundation of China (No. 62172246), the Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems (VRLAB2021A05), and the Youth Innovation and Technology Support Plan of Colleges and Universities in Shandong Province (2021KJ062).
Author information
Authors and Affiliations
Contributions
Conceived and designed the experiments: YY CC JG. Performed the experiments: YY. Analyzed the data: YY CC. Wrote the paper: YY CC JG.
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no competing interests.
Additional information
Availability of data and material
We use the public automated cardiac diagnosis challenge (ACDC) dataset. The data are downloaded from: https://acdc.creatis.insa-lyon.fr/
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yan, Y., Chen, C. & Gao, J. Lossless segmentation of cardiac medical images by a resolution consistent network with nondamage data preprocessing. Multimed Tools Appl 82, 20951–20973 (2023). https://doi.org/10.1007/s11042-022-14202-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-14202-2