A deep attention network via high-resolution representation for liver and liver tumor segmentation

• Autorzy: Li Yang , Zou Beiji , Liu Qing

Identyfikatory

DOI

10.1016/j.bbe.2021.08.010

• Języki publikacji: EN

Abstrakty

EN

The segmentation of liver and liver tumor is an essential step for computer-aided liver disease diagnosis, treatment and prognosis. Although deep convolutional neural networks have contributed to liver and tumor segmentation, their architectures can not maintain spatial details and long-range context information. Besides, the fixed receptive fields of these networks limit the segmentation performance of livers and tumors with variant sizes and shapes. To address above problems, we propose a deep attention neural network which contains high-resolution branch and multi-scale features aggregation for cascaded liver and tumor segmentation from CT images. To be specific, the high-resolution branch can maintain the resolution of the input image and thus preserves the spatial details. The multi-scale features exchange and fusion enable the receptive fields of the network to adapt to liver and tumor with variant shapes and sizes. The appended attention module evaluates the similarities between every two pixels to model the long-range dependence and context information so that the network can segment liver and tumor areas located in distant regions. Experimental results on the LiTS and the 3D-IRCADb datasets demonstrate that our method can generate satisfying performance.

Słowa kluczowe

EN

liver tumor; deep neural network; attention

PL

guz wątroby; głęboka sieć neuronowa; moduł uwagi

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 4
• Strony: 1518--1532
• Opis fizyczny: Bibliogr. 37 poz., rys., tab.

Twórcy

autor

Li Yang

• School of Computer Science and Engineering, Central South University, Changsha, China; Hunan Engineering Research Center of Machine Vision and Wise Medical, Changsha, China

autor

Zou Beiji

• School of Computer Science and Engineering, Central South University, Changsha, China; Hunan Engineering Research Center of Machine Vision and Wise Medical, Changsha, China; Mobile Health Ministry of Education China Mobile Joint Laboratory, Changsha, China

autor

Liu Qing

• School of Computer Science and Engineering, Central South University, Changsha 410083, China

Bibliografia

• [1] Zhang JJ, Meng X, Li Y, et al. Effects of melatonin on liver injuries and diseases. Int J Mol Sci 2017;18(4):673–700.
• [2] Ferenci P, Fried M, Labrecque D, et al. World gastroenterology organisation guideline. Hepatocellular carcinoma (HCC): a global perspective. J Gastrointest Liver Dis 2010;19(3):311–7.
• [3] Gunasekhar P, Vijayalakshmi S. Optimal biomarker selection using adaptive Social Ski-Driver optimization for liver cancer detection. Biocybernet Biomed Eng 2020;40:1611–25.
• [4] Liu Z, Jiang YF, Yuan HB, et al. The trends in incidence of primary liver cancer caused by specific etiologies: results from the global burden of disease study 2016 and implications for liver cancer prevention. J Hepatol 2019;70 (4):647–83.
• [5] WHO. The World Health Report-World Health Organization. WHO 2018.
• [6] Deng X, Du GW. Editorial: 3d segmentation in the clinic: a grand challenge II-liver tumor segmentation. Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention 2008:1–12.
• [7] Patrick C, Florian E, Felix G, et al. LiTS-Liver tumor segmentation challenge. https://competitions.codalab.org/competitions/17094, 2018-4-27.
• [8] Sun K, Zhao Y, Jiang BR, et al. High-resolution representations for labeling pixels and regions. IEEE Int Conf Computer Vision and Pattern Recogintion 2019.
• [9] Huang ZL, Wang XX, Huang LC, et al. CCNet: Criss-cross attention for semantic segmentation. IEEE Int Conf Computer Vision and Pattern Recogintion 2019:603–12.
• [10] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 2014;39(4):640–51.
• [11] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Int Conf Med Image Comput Comput Assist Interv 2015;9351 234241.
• [12] Baazaoui A, Barhoumi W, Ahmed A, et al. Semi-automated segmentation of single and multiple tumors in liver CT images using entropy-based fuzzy region growing. Innov Res Biomed Eng 2017;38(2):98–108.
• [13] Das A, Sabut SK. Kernelized fuzzy c-means clustering with adaptive thresholding for segmenting liver tumors. Procedia Comput Sci 2016;92(57):389–95.
• [14] Anter AM, Hassenian AE. CT liver tumor segmentation hybrid approach using neutrosophic sets, fast fuzzy c-means and adaptive watershed algorithm. Artif Intell Med 2018:1–13.
• [15] Yugander P, Reddy GR. Liver tumor segmentation in noisy CT images using distance regularized level set evolution based on fuzzy c-means clustering. In: 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT). p. 1530–4.
• [16] Wu WW, Wu SC, Zhou ZH, et al. 3D liver tumor segmentation in ct images using improved fuzzy c-means and graph cuts. Biomed Res Int 2017;2017:1–11.
• [17] Krishna A, Edwin D, Hariharan S. Classification of liver tumor using SFTA based Nave Bayes classifier and support vector machine. In: International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT). p. 1066–70.
• [18] Zhu W, Oh BS, Huang W, et al. Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation. In: 2015 10th International Conference on Information, Communications and Signal Processing (ICICS). p. 1–4.
• [19] Conze PH, Noblet V, Rousseau F, et al. Scale-adaptive supervoxel-based random forests for liver tumor segmentation in dynamic contrast-enhanced CT scans. Int J Comput Assist Radiol Surg 2017;12(2):223–33.
• [20] Li J, Wu YR, Shen NY, et al. A fully automatic computer-aided diagnosis system for hepatocellular carcinoma using convolutional neural networks. Biocybernet Biomed Eng 2020;40:238–48.
• [21] Christ PF, Ettlinger F, Grn F, et al. Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. Med Image Comput Comput Assist Interv 2016:415–23.
• [22] Sun C, Guo S, Zhang H, et al. Automatic segmentation of liver tumors from multiphase contrast-enhanced ct images based on fcns. Artif Intell Med 2017;83:58–66.
• [23] Chlebus G, Meine H, Moltz JH, et al. Neural network-based automatic liver tumor segmentation with random forest-based candidate filtering. arXiv preprint, 2017, arXiv:1706.00842.
• [24] Han X. Automatic liver lesion segmentation using a deep convolutional neural network method. arXiv preprint, 2017, arXiv:1704.07239.
• [25] Li XM, Chen H, Qi XJ, et al. H-DenseUNet: Hybrid densely connected UNet for liver and tumor segmentation from CT volumes. IEEE Trans Med Imaging 2018;37(12):2663–74.
• [26] Chen XY, Zhang R, Yan PK. Feature fusion encoder decoder network for automatic liver lesion segmentation. In: IEEE 16th International Symposium on Biomedical Imaging (ISBI). p. 430–3.
• [27] Hyunseok S, Charles H, Maxime B, et al. Modified U-Net (mUNet) with incorporation of object-dependent high level features for improved liver and liver-tumor segmentation in CT images. IEEE Trans Med Imaging 2020.
• [28] Jin Q, Meng Z, Sun C, et al. RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans. arXiv preprint, arXiv:1811.01328v1, 2018.
• [29] Wang XL, Girshick R, Gupta A, et al. Non-local neural networks. Int Conf Comput Vision Pattern Recogn 2018:7794–803.
• [30] Fu J, Liu J, Tian HJ, et al. Dual attention network for scene segmentation. Int Conf Comput Vision Pattern Recogn 2019:3141–9.
• [31] Soler L, Hostettler A, Agnus V, et al. 3D Image reconstruction for comparison of algorithm database: A patient specific anatomical and medical image database. https://www.ircad.fr/research/3dircadb/, 2018-7-25.
• [32] Kaluva K C, Khened M, Kori A, et al. 2D-Densely connected convolution neural networks for automatic liver and tumor segmentation. arXiv preprint, arXiv:1802.02182, 2018.
• [33] Bi L, Kim J, Kumar A, et al. Automatic liver lesion detection using cascaded deep residual networks. arXiv preprint, arXiv:1704.02703, 2017.
• [34] Bellver M, Maninis K K, Pont-Tuset J, et al. Detection-aided liver lesion segmentation using deep learning. arXiv preprint, arXiv:1711.11069, 2017.
• [35] Zhang J, Xie Y, Zhang P, et al. Light-weight hybrid convolutional network for liver tumor segmentation. Twenty Eighth International Joint Conference on Artificial Intelligence IJCAI-19 2019.
• [36] Chen LC, Papandreou G, Schroff F, et al. Rethinking atrous convolution for semantic image segmentation. Int Conf Comput Vision Pattern Recogn 2018.
• [37] Zhao HS, Shi JP, Qi XJ, et al. Pyramid scene parsing network. Int Conf Comput Vision Pattern Recogn 2017:6230–9.