Ensemble classification for predicting the malignancy level of pulmonary nodules on chest computed tomography images

Xiao,Ning; Qiang,Yan; Bilal Zia,Muhammad; Wang,Sanhu; Lian,Jianhong

doi:10.3892/ol.2020.11576

Ensemble classification for predicting the malignancy level of pulmonary nodules on chest computed tomography images

Authors:
- Ning Xiao
- Yan Qiang
- Muhammad Bilal Zia
- Sanhu Wang
- Jianhong Lian
View Affiliations

Affiliations: College of Information and Computer, Taiyuan University of Technology, Taiyuan, Shanxi 030600, P.R. China, Department of Computer Science and Technology, Lvliang University, Lvliang, Shanxi 033000, P.R. China, Department of Thoracic Surgery, Shanxi Cancer Hospital, Taiyuan, Shanxi 030000, P.R. China
Published online on: April 27, 2020 https://doi.org/10.3892/ol.2020.11576
Pages: 401-408

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

Early identification and classification of pulmonary nodules are essential for improving the survival rates of individuals with lung cancer and are considered to be key requirements for computer‑assisted diagnosis. To address this topic, the present study proposed a method for predicting the malignant phenotype of pulmonary nodules based on weighted voting rules. This method used the pulmonary nodule regions of interest as the input data and extracted the features of the pulmonary nodules using the Denoising Auto Encoder, ResNet‑18. Moreover, the software also modifies texture and shape features to assess the malignant phenotype of the pulmonary nodules. Based on their classification accuracy (Acc), the different classifiers were assigned to different weights. Finally, an integrated classifier was obtained to score the malignant phenotype of the pulmonary nodules. The present study included training and testing experiments conducted by extracting the corresponding lung nodule image data from the Lung Image Database Consortium‑Image Database Resource Initiative. The results of the present study indicated a final classification Acc of 93.10±2.4%, demonstrating the feasibility and effectiveness of the proposed method. This method includes the powerful feature extraction ability of deep learning combined with the ability to use traditional features in image representation.

View Figures

View References

1	Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA and Jemal A: Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 68:394–424. 2018. View Article : Google Scholar : PubMed/NCBI
2	Rzechonek A, Grzegrzolka J, Blasiak P, Ornat M, Piotrowska A, Nowak A and Dziegiel P: Correlation of expression of tenascin C and blood vessel density in non-small cell lung cancers. Anticancer Res. 38:1987–1991. 2018.PubMed/NCBI
3	Chen S, Harmon S, Perk T, Li X, Chen M, Li Y and Jeraj R: Diagnostic classification of solitary pulmonary nodules using dual time ¹⁸F-FDG PET/CT image texture features in granuloma-endemic regions. Sci Rep. 7:93702017. View Article : Google Scholar : PubMed/NCBI
4	Dai M, Qi J, Zhou Z and Gao F: The classification of pulmonary nodules based on texture features over local jet transformation space. Chin J Biomed Eng. 36:12–19. 2017.
5	Felix A, Oliveira M, Machado A and Raniery J: Using 3D texture and margin sharpness features on classification of small pulmonary nodules. In: Proceedings of 29th Conference on Graphics. (Patterns and Images (SIBGRAPI), Sao Paulo). 394–400. 2016.
6	Song J, Hui L, Geng F and Zhang C: Weakly-supervised classification of pulmonary nodules based on shape characters. In: Proceedings of 2016 IEEE 14th Intl Conf on Dependable, Autonomic and Secure Computing, 14th Intl Conf on Pervasive Intelligence and Computing, 2nd Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech). (Auckland). 228–232. 2016.
7	Niehaus R, Raicu DS, Furst J and Armato S III: Toward understanding the size dependence of shape features for predicting spiculation in lung nodules for computer-aided diagnosis. J Digit Imaging. 28:704–717. 2015. View Article : Google Scholar : PubMed/NCBI
8	Dhara AK, Mukhopadhyay S, Dutta A, Garg M and Khandelwal N: A Combination of shape and texture features for classification of pulmonary nodules in lung CT images. J Digit Imaging. 29:466–475. 2016. View Article : Google Scholar : PubMed/NCBI
9	Li W, Cao P, Zhao D and Wang J: Pulmonary nodule classification with deep convolutional neural networks on computed tomography images. Comput Math Methods Med. 2016:62150852016. View Article : Google Scholar : PubMed/NCBI
10	Tartar A, Akan A and Kilic N: A novel approach to malignant-benign classification of pulmonary nodules by using ensemble learning classifiers. Conf Proc IEEE Eng Med Biol Soc. 2014:4651–4654. 2014.PubMed/NCBI
11	Nibali A, Zhen H and Wollersheim D: Pulmonary nodule classification with deep residual networks. Int J Comput Assist Radiol Surg. 12:1799–1808. 2017. View Article : Google Scholar : PubMed/NCBI
12	Shen W, Zhou M, Yang F, Yang C and Tian J: Multi-scale convolutional neural networks for lung nodule classification. Inf Process Med Imaging. 24:588–599. 2015.PubMed/NCBI
13	Kumar D, Wong A and Clausi DA: Lung nodule classification using deep features in CT images. In: Proceedings of the 2015 12th Conference on Computer and Robot Vision. (Halifax, Canada. IEEE). 133–138. 2015.
14	Kaya A and Can AB: A weighted rule based method for predicting malignancy of pulmonary nodules by nodule characteristics. J Biomed Inform. 56:69–79. 2015. View Article : Google Scholar : PubMed/NCBI
15	Li G, Kim H, Tan JK, Ishikawa S, Hirano Y, Kido S and Tachibana R: Semantic characteristics prediction of pulmonary nodule using artificial neural networks. Conf Proc IEEE Eng Med Biol Soc. 2013:5465–5468. 2013.PubMed/NCBI
16	Chen S, Ni D, Qin J, Lei B, Wang T and Cheng JZ: Bridging computational features toward multiple semantic features with multi-task regression: A study of ct pulmonary nodules. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer. (Cham). 53–60. 2016.
17	Shewaye TN and Mekonnen AA: Benign-malignant lung nodule classification with geometric and appearance histogram features. arXiv: Computer Vision and Pattern Recognition. (arXiv:1605.08350v1 [cs.CV]). 2016.
18	Orozco HM, Villegas OOV, de Jesús Ochoa Domínguez O and Sánchez VGC: Lung nodule classification in CT thorax images using support vector machines. Mexican International Conference on Artificial Intelligence. IEEE. 277–283. 2014.
19	Zhao A, Qi L, Li J, Dong J and Yu H: LSTM for diagnosis of neurodegenerative diseases using gait data. In: Proceedings of the 9th International Conference on Graphics and Image Processing. SPIE Press. 2018.
20	Jacobs C, van Rikxoort EM, Twellmann T, Scholten ET, de Jong PA, Kuhnigk JM, Oudkerk M, de Koning HJ, Prokop M, Schaefer-Prokop C and van Ginneken B: Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images. Med Image Anal. 18:374–384. 2014. View Article : Google Scholar : PubMed/NCBI
21	Ma J, Wang Q, Ren Y, Hu H and Zhao J: Automatic lung nodule classification with radiomics approach. Medical Imaging 2016: PACS and Imaging Informatics: Next Generation and Innovations. 9789:SPIE Proceedings. 2016.
22	Armato SG III, McLennan G, Bidaut L, McNitt-Gray MF, Meyer CR, Reeves AP, Zhao B, Aberle DR, Henschke CI, Hoffman EA, et al: The lung image database consortium (LIDC) and image database resource initiative (IDRI): A completed reference database of lung nodules on CT scans. Med Phys. 38:915–931. 2011. View Article : Google Scholar : PubMed/NCBI
23	Chen M, Weinberger KQ, Sha F and Bengio YO: Marginalized denoising auto-encoders for nonlinear representations. Proceedings of the 31st International Conference on Machine Learning. PMLR. 32:1476–1484. 2014.
24	Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V and Rabinovich A: Going deeper with convolutions. arXiv: Computer Vision and Pattern Recognition. (arXiv:1409.4842v1 [cs.CV]). 2015. View Article : Google Scholar
25	Simonyan K and Zisserman A: Very deep convolutional networks for large-scale image recognition. arXiv: Computer Vision and Pattern Recognition arXiv:1409.1556v6 [cs.CV]. 2014.
26	Hu J, Shen L, Albanie S, Sun G and Wu E: Squeeze-and-excitation networks. arXiv: Computer Vision and Pattern Recognition. (arXiv:1709.01507v4 [cs.CV]). 2017.
27	He K, Zhang X, Ren S and Sun J: Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition. 770–778. 2016.
28	Haralick RM, Shanmugam K and Dinstein IH: Textural features for image classification. IEEE Transactions on Systems. (Man, and Cybernetics. Vol SMC-3. IEEE). 610–621. 1973.
29	Pan L, Qiang Y, Yuan J and Wu L: Rapid retrieval of lung nodule CT images based on hashing and pruning methods. Biomed Res Int. 2016:31626492016. View Article : Google Scholar : PubMed/NCBI
30	Li X, Yang Y, Xiong H, Song S and Jia H: Pulmonary nodules detection algorithm based on robust cascade classifier for CT images. Control and Decision Conference. IEEE. 231–235. 2017.
31	Zinovev D, Furst J and Raicu D: Building an ensemble of probabilistic classifiers for lung nodule interpretation. Proceedings of the 10th International Conference on Machine Learning and Applications and Workshops. IEEE Computer Society. 155–161. 2011.
32	Zou KH, O'Malley AJ and Mauri L: Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models. Circulation. 115:654–657. 2007. View Article : Google Scholar : PubMed/NCBI
33	Zinovev D, Feigenbaum J, Furst J and Raicu D: Probabilistic lung nodule classification with belief decision trees. Conf Proc IEEE Eng Med Biol Soc. 2011:4493–4498. 2011.PubMed/NCBI
34	Shen W, Zhou M, Yang F, Yu D, Dong D, Yang C, Zang Y and Tian J: Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification. Pattern Recogn. 61:663–673. 2017. View Article : Google Scholar
35	Rodrigues MB, Da NóBrega RVM, Alves SSA, Filho PPR, Duarte JBF, Sangaiah AK and De Albuquerque VHC: Health of things algorithms for malignancy level classification of lung nodules. IEEE Access. 6:18592–18601. 2018. View Article : Google Scholar
36	Sun W, Huang X, Tseng TL, Zhang J and Qian W: Computerized lung cancer malignancy level analysis using 3D texture features. Medical Imaging 2016: PACS and Imaging Informatics: Next Generation and Innovations. 9785:SPIE Proceedings. 2016.
37	Seo N, Seok J, Lim S and Cho A: Radiologic diagnosis (CT, MRI, & PET-CT). Surg Gastric Cancer. 67–86. 2019. View Article : Google Scholar
38	Oliva MR and Saini S: Liver cancer imaging: Role of CT, MRI, US and PET. Cancer Imaging. 4:S42–S46. 2004. View Article : Google Scholar : PubMed/NCBI
39	Muhammad MN, Raicu DS, Furst JD and Varutbangkul E: Texture versus shape analysis for lung nodule similarity in computed tomography studies. Medical Imaging 2008: PACS and Imaging Informatics. 6919:SPIE Proceedings. 2008.
40	Wormanns D, Fiebich M, Saidi M, Diederich S and Heindel W: Automatic detection of pulmonary nodules at spiral CT: Clinical application of a computer-aided diagnosis system. Eur Radiol. 12:1052–1057. 2002. View Article : Google Scholar : PubMed/NCBI