A fully automatic computer-aided diagnosis system for hepatocellular carcinoma using convolutional neural networks

• Autorzy: Li Jing , Wu Yurun , Shen Nanyan , Zhang Jiawen , Chen Enlong , Sun Jie , Deng Zongqian , Zhang Yuchen

Identyfikatory

DOI

10.1016/j.bbe.2019.05.008

• Języki publikacji: EN

Abstrakty

EN

The cancer of liver, which is the leading cause of cancer death, is commonly diagnosed by comparing the changes of gray level of liver tissue in the different phases of the patient's CT images. To aid the doctor in reducing misdiagnosis or missed diagnosis, a fully automatic computer-aided diagnosis (CAD) system is proposed to diagnose hepatocellular carcinoma (HCC) using convolutional neural network (CNN) classifier. The automatic segmentation and classification are two core technologies of the proposed CAD system, which are both realized based on CNN. The segmentation of liver and tumor is implemented by a fully convolutional networks (FCN) based on a fine tuning VGG-16 model with two additional 'skip structures' using a weighted loss function which helps to solve the problem of inaccurate tumor segmentation caused by the inevitably unbalanced training data. HCC classification is implemented by a 9-layer CNN classifier, whose input is a 4-channel image data constructed by combining the segmentation result of FCN with the original CT image. A total of 165 venous phase CT images including 46 diffuse tumors, 43 nodular tumors, and 76 massive tumors are used to evaluate the performance of the proposed CAD system. The classification accuracy of CNN classifier for diffuse, nodular and massive tumors are 98.4%, 99.7% and 98.7% respectively, which are significantly improved in contrast with the traditional feature-based ANN and SVM classifiers. The proposed CAD system, which is unaffected by the difference of preprocessing method and feature type, is proved satisfactory and feasible by the test set.

Słowa kluczowe

EN

venous phase; weighted loss function; fully convolutional network; liver segmentation; hepatocellular carcinoma

PL

funkcja strat; konwolucyjna sieć neuronowa; segmentacja wątroby; rak komórkowo-wątrobowy

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 1
• Strony: 238--248
• Opis fizyczny: Bibliogr. 37 poz., rys., tab., wykr.

Twórcy

autor

Li Jing

• Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China

autor

Wu Yurun

• Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China

autor

Shen Nanyan

• Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China; Room 431, Building 9, No. 333, Nanchen Road, Baoshan District, Shanghai 200444, China

autor

Zhang Jiawen

• Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China

autor

Chen Enlong

• Department of Radiology, Pudong New Area People's Hospital, Shanghai, China

autor

Sun Jie

• Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China

autor

Deng Zongqian

• Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China

autor

Zhang Yuchen

• Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China

Bibliografia

• [1] Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2018;68:394–424.
• [2] Yoshida H, Yoshida H, Shiina S, Omata M. Early liver cancer: concepts, diagnosis, and management. Int J Clin Oncol 2005;10:384–90.
• [3] França AVC, Elias Júnior J, Lima BLG de, Martinelli ALC, Carrilho FJ. Diagnosis, staging and treatment of hepatocellular carcinoma. Brazilian J Med Biol Res 2004;37:1689–705.
• [4] Kumar SS, Moni RS, Rajeesh J. An automatic computer-aided diagnosis system for liver tumours on computed tomography images. Comput Electr Eng 2013;39:1516–26.
• [5] Chang C-C, Chen H-H, Chang Y-C, Yang M-Y, Lo C-M, Ko W-C, et al. Computer-aided diagnosis of liver tumors on computed tomography images. Comput Methods Programs Biomed 2017;145:45–51.
• [6] Sethi G, Saini BS. Computer aided diagnosis system for abdomen diseases in computed tomography images. Biocybern Biomed Eng 2016;36:42–55.
• [7] Sayed GI, Hassanien AE, Schaefer G. An automated computer-aided diagnosis system for abdominal CT liver images. Procedia Comput Sci 2016;90:68–73.
• [8] O'Shea K, Nash R. An introduction to convolutional neural networks; 2015, ArXiv Prepr ArXiv151108458.
• [9] LeCun Y, Bottou L, Bengio Y, Haffner P, et al. Gradient-based learning applied to document recognition. Proc IEEE 1998;86:2278–324.
• [10] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. Proc IEEE Conf Comput Vis Pattern Recognit. 2015. pp. 3431–40.
• [11] Shi W, Caballero J, Theis L, Huszar F, Aitken A, Ledig C, et al. Is the deconvolution layer the same as a convolutional layer?; 2016, ArXiv Prepr ArXiv160907009.
• [12] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521:436.
• [13] Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. Proc. 27th Int. Conf. Mach. Learn.. 2010. pp. 807–14.
• [14] Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, et al. Imagenet large scale visual recognition challenge. Int J Comput Vis 2015;115:211–52.
• [15] Rumelhart DE, Hinton GE, Williams RJ, et al. Learning representations by back-propagating errors. Cogn Model 1988;5:1.
• [16] Nesterov YE. A method for solving the convex programming problem with convergence rate O (1/k^ 2). Dokl akad Nauk Sssr 1983;269:543–7.
• [17] Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 2011;12:2121–59.
• [18] Tieleman T, Hinton G. Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA Neural Networks Mach Learn 2012;4:26–31.
• [19] Kingma DP, Ba J. Adam: a method for stochastic optimization; 2014, ArXiv Prepr ArXiv14126980.
• [20] Luo S, Li X, Li J. Review on the methods of automatic liver segmentation from abdominal images. J Comput Commun 2014;2:1.
• [21] Meiburger KM, Acharya UR, Molinari F. Automated localization and segmentation techniques for B-mode ultrasound images: a review. Comput Biol Med 2018;92:210–35.
• [22] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition; 2014, ArXiv Prepr ArXiv14091556.
• [23] Gondara L. Medical image denoising using convolutional denoising autoencoders. 2016 IEEE 16th Int. Conf. Data Min. Work. 2016. pp. 241–6.
• [24] Khan SH, Hayat M, Bennamoun M, Sohel FA, Togneri R. Cost-sensitive learning of deep feature representations from imbalanced data. IEEE Trans Neural Networks Learn Syst 2018;29:3573–87.
• [25] García-Gómez JM, Tortajada S. Definition of loss functions for learning from imbalanced data to minimize evaluation metrics. Data Min Clin Med Springer 2015;19–37.
• [26] Chung Y-A, Lin H-T, Yang S-W. Cost-aware pre-training for multiclass cost-sensitive deep learning; 2015, ArXiv Prepr ArXiv151109337.
• [27] Sun Y, Wong AKC, Kamel MS. Classification of imbalanced data: a review. Int J Pattern Recognit Artif Intell 2009;23:687–719.
• [28] Jesson A, Arbel T. Brain tumor segmentation using a 3D FCN with multi-scale loss. Int. MICCAI Brainlesion Work. 2017. pp. 392–402.
• [29] Xie S, Tu Z. Holistically-nested edge detection. Proc. IEEE Int. Conf. Comput. Vis. 2015. pp. 1395–403.
• [30] Rahman MA, Wang Y. Optimizing intersection-over-union in deep neural networks for image segmentation. Int Symp Vis Comput 2016;234–44.
• [31] Sokolova M, Japkowicz N, Szpakowicz S. Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. Australas. Jt. Conf. Artif. Intell.. 2006. pp. 1015–21.
• [32] Davis J, Goadrich M. The relationship between Precision– Recall and ROC curves. Proc. 23rd Int. Conf. Mach. Learn.. 2006. pp. 233–40.
• [33] Flach PA. ROC analysis. In: Sammut C, Webb GI, editors. Encycl. Mach. Learn. Data Min.. Boston, MA: Springer US; 2017. p. 1109–16. http://dx.doi.org/10.1007/978-1-4899-7687-1_739.
• [34] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. Int. Conf. Med. Image Comput. Comput. Interv.. 2015. pp. 234–41.
• [35] Li C, Xu C, Gui C, Fox MD. Distance regularized level set evolution and its application to image segmentation. IEEE Trans Image Process 2010;19:3243–54.
• [36] Krinidis S, Chatzis V. A robust fuzzy local information C-means clustering algorithm. IEEE Trans Image Process 2010;19:1328–37.
• [37] Abdi H, Williams LJ. Principal component analysis. Wiley Interdiscip Rev Comput Stat 2010;2:433–59.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).