Abstract
The U-Net has become the most popular structure in medical image segmentation in recent years. Although its performance for medical image segmentation is outstanding, a large number of experiments demonstrate that the classical U-Net network architecture seems to be insufficient when the size of segmentation targets changes and the imbalance happens between target and background in different forms of segmentation. To improve the U-Net network architecture, we develop a new architecture named densely connected U-Net (DenseUNet) network in this article. The proposed DenseUNet network adopts a dense block to improve the feature extraction capability and employs a multi-feature fuse block fusing feature maps of different levels to increase the accuracy of feature extraction. In addition, in view of the advantages of the cross entropy and the dice loss functions, a new loss function for the DenseUNet network is proposed to deal with the imbalance between target and background. Finally, we test the proposed DenseUNet network and compared it with the multi-resolutional U-Net (MultiResUNet) and the classic U-Net networks on three different datasets. The experimental results show that the DenseUNet network has significantly performances compared with the MultiResUNet and the classic U-Net networks.
- Ozan Oktay, Enzo Ferrante, Konstantinos Kamnitsas, Mattias Heinrich, Wenjia Bai, and Jose Caballero. 2018. Anatomically constrained neural networks (ACNNs): Application to cardiac image enhancement and segmentation. IEEE Trans. Med. Imag. 37, 2 (2018), 384–392.Google Scholar
Cross Ref
- Noel Codella, David Gutman, Emre Celebi, Brian Helba, Michael Marchetti, and Stephen. 2018. Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). In Proceedings of the2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI’18), 168–172.Google Scholar
Cross Ref
- Zongwei Zhou, Md MAhfuzur Rahman Siddiquee, Nima Tajbakhsh, and Jianming Liang. 2018. UNet: A nested U-Net architecture for medical image segmentation. In Proceedings of theDeep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (DLMIA’18). Lecture Notes in Computer Science, 11045, 3–11.Google Scholar
Cross Ref
- Jinzhong Yang, Harini Veeraraghavan, Samuel G Armato, Keyvan Farahani, Justin S. Kirby, Jayashree Kalpathy-Kramer, Wouter van Elmpt, Andre Dekker, Xiao Han, Xue Feng, Paul Aljabar, Bruno Oliveira, Brent van der Heyden, Leonid Zamdborg, Dao Lam, Mark Gooding, Gregory C. Sharp. 2018. Autosegmentation for thoracic radiation treatment planning: A grand challenge at AAPM 2017. Medical Physics 45, 10 (2018), 4568–4581.Google Scholar
Cross Ref
- Rouhi Rahimeh, Jafari Mehdi, Kasaei Shohreh, and Peiman Keshavarzian. 2015. Benign and malignant breast tumors classification based on region growing and cnn segmentation. Exp. Syst. Appl. 42, 3 (2015), 990–1002. Google Scholar
Digital Library
- Ke Liang, Yongmei Jiang, Meng Long, and Guangming Liang. 2018. Adaptive dual threshold based moving target detection algorithm. In Proceedings of 2018 IEEE 4th Information Technology and Mechatronics Engineering Conference (ITOEC’18), 1111–1115.Google Scholar
Cross Ref
- Yanli Ji, Yue Zhan, Yang Yang, Xing Xu, Fumin Shen, and Heng Tao Shen. 2019. A context knowledge map guided coarse-to-fine action recognition. IEEE Trans. Image Process. 29 (2019), 2742–2752.Google Scholar
Cross Ref
- Yujia Chen, Linlin Xu, Yuan Fang, Junhuan Peng, Wenfu Yang, Alexander Wong, and David A. Clausi. 2020. Unsupervised bayesian subpixel mapping of hyperspectral imagery based on band-weighted discrete spectral mixture model and Markov random field. IEEE Trans. Geosci. Remote Sens. 18, 1 (2020), 162–166.Google Scholar
Cross Ref
- Chunfeng Lian, Su Ruan, Thierry Denoeux, Hua Li, and Pierre Vera. 2019. Joint tumor segmentation in PET-CT images using co-clustering and fusion based on belief functions. IEEE Trans. Image Process. 28, 2 (2019), 755–766.Google Scholar
Digital Library
- ChunGuang Li, Chong You, and Rene Vidal. 2017. Structured sparse subspace clustering: A joint affinity learning and subspace clustering framework. IEEE Trans. Image Process. 26, 6 (2017), 2988–3001. Google Scholar
Digital Library
- Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521 (2015), 436–444.Google Scholar
Cross Ref
- Yann Lecun, Leon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE, 86, 11 (2015), 2278–2324.Google Scholar
Cross Ref
- Krizhevsky, Alex, Sutskever, Ilya, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, 1097–1105. Google Scholar
Digital Library
- Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu. 2014. Rob Fergus and Yann LeCun. OverFeat: Integrated recognition, localization and detection using convolutional networks. https://arxiv.org/abs/1312.6229.Google Scholar
- Ciresan Dan, Giusti Alessandro, Luca M. Gambardella, and Schmidhuber. 2012. Deep neural networks segment neuronal memberanes in electron microscopy images. In Advances in Neural Information Processing Systems, Vol. 25, 2843–2851. Google Scholar
Digital Library
- Jonathan Long, Evan Shelhamer, and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In Proceedings of theIEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), 3431–3440.Google Scholar
Cross Ref
- V. Badrinarayanan, A. Kendall, and R. Cipolla. 2017. SegNet: A. deep convolutional Encoder-Decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 12 (2017), 2481–2495.Google Scholar
Cross Ref
- Liang-Chieh Chen, George Papandreou, Iasinas Kokkinos, Kevin Murphy, and Alan L. Yuille. 2017. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connectedCRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40, 4 (2017), 834–848.Google Scholar
Cross Ref
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention, Vol. 9651, 234–241.Google Scholar
- Ibtehaz M. Nabil and Sohel Rahman. 2020. MultiResUNet: Rethinking the U-Net architecture for multimodel biomedical image segmentation. Neur. Netw. (2020), 74–87.Google Scholar
- Michal Drozdzal, Eugene Vorontsov, Gabriel Chartrand, Samuel Kadoury, and Chris Pal. 2016. The importance of skip connections in biomedical iamge segmentation. In Deep Learning and Data Labeling for Medical Applications, 179–187.Google Scholar
- Matthew D. Zeiler, Dilip Krishnan, Graham W. Taylor, and Rob Fergus. 2010. Deconvolutional networks. In Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2528–2535.Google Scholar
Cross Ref
- Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521 (2015), 436–444.Google Scholar
Cross Ref
- Szegedy Christian, Liu Wei, Yangqing Jia, Pierre Sermanet, Scott Reed, and Dragomir Anguelov. 2015. Going deeper with convolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–9.Google Scholar
- Gao Huang, Zhuang Liu, Kilian Q. Weinberger. 2017. Densely connected convolutional networks. In Proceedings of theIEEE Computer Society Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. 2016. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. In Proceedings of the2016 4th International Conference on 3D Vision (3DV’16), 11, 565–571.Google Scholar
Cross Ref
- Albert Cardona, Stephan Saalfeld, Schmid Stephan, Cheng Benjamin, Pulokas Anchi, and Jim. 2010. An integrated micro-and macroarchitectural analysis of the drosophila brain by computer-assisted serial section electron microscopy. PLos Biol. 8, 10 (2010), 1–17.Google Scholar
Cross Ref
- DRIVE. Retrieved from http://www.isi.uu.nl/Research/Databases/DRIVE/.2019.Google Scholar
- Noel Codella, C. F. Gutman, M. Emre Celebi, Brian Helba, Michael A. Marchetti, and Stephen W. Dusza. 2018. Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). In Proceedings of the 2018 IEEE 15th International Symposium Biomedical Imaging (ISBI’18). 168–172.Google Scholar
- Philipp Tschandl, Cliff Rosendahl, and Harald Kittler. 2018. The ham10000 dataset: A. large collection of multi-source dermoscopic images of common pigmented skin lesions. arXiv:1803.10417. Retrieved from https://arxiv.org/abs/1803.10417.Google Scholar
- Van Rossum and Guido. 2007. Python programming language. In Proceedings of theUSENIX Annual Technical Conference, 41, 36.Google Scholar
- Diederik Kingma and Jimmy Ba. 2014. Adam: A. method for stochastic optimization. arXiv:14126980. Retrieved from https://arxiv.org/abs/14126980.Google Scholar
- Narinder Singh Punn, and Sonali Agarwal. 2020. Inception U-Net architecture for semantic segmentation to identify nuclei in microscopy cell images. ACM Trans. Multimedia Comput. Commun. Appl. 16, 1, Article 12 (Febr. 2020), 15. Google Scholar
Digital Library
- Xueping Wang, Yunhong Wang, and Weixin Li. 2019. U-Net conditional GANs for photo-realistic and identity-preserving facial expression synthesis. ACM Trans. Multimedia Comput. Commun. Appl. 15, 3s, Article 88 (Oct. 2019), 23. Google Scholar
Digital Library
- Junfeng Zhang, Haifeng Hu, and Guobin Shen. 2020. Joint stacked hourglass network and salient region attention ref- inement for robust face alignment. ACM Trans. Multimedia Comput. Commun. Appl. 16, 1, Article 10 (Febr. 2020), 18. Google Scholar
Digital Library
Index Terms
A Densely Connected Network Based on U-Net for Medical Image Segmentation
Recommendations
Lung computed tomography image segmentation based on U-Net network fused with dilated convolution
Highlights- A U-Net network fused with dilated convolution is proposed.
- DC-U-Net, Otsu and ...
Abstract PurposeIn order to solve the problem of accurate and effective segmentation of the patient's lung computed tomography (CT) images, so as to improve the efficiency of treating lung cancer.
Method ...Hybrid dilation and attention residual U-Net for medical image segmentation
AbstractMedical image segmentation is a typical task in medical image processing and critical foundation in medical image analysis. U-Net is well-liked in medical image segmentation, but it doesn't fully explore useful features of the channel ...
Graphical abstractDisplay Omitted
Highlights- A medical image segmentation method is proposed based on U-Net.
- A novel channel ...
Precise segmentation of non-enhanced computed tomography in patients with ischemic stroke based on multi-scale U-Net deep network model
Highlights- Multi-scale U-Net deep network model can effectively segment the ischemic stroke lesions.
Abstract Background and ObjectiveAcute ischemic stroke requires timely diagnosis and thrombolytic therapy, but it is difficult to locate and quantify the lesion site manually. The purpose of this study was to explore a more rapid ...






Comments