Diagnosis of mesothelioma with deep learning

Hu,Xue; Yu,Zebo

doi:10.3892/ol.2018.9761

Diagnosis of mesothelioma with deep learning

Authors:
- Xue Hu
- Zebo Yu
View Affiliations

Affiliations: Department of Blood Transfusion, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, P.R. China
Published online on: November 26, 2018 https://doi.org/10.3892/ol.2018.9761
Pages: 1483-1490
Copyright: © Hu et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

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

Malignant mesothelioma (MM) is a rare but aggressive cancer. The definitive diagnosis of MM is critical for effective treatment and has important medicolegal significance. However, the definitive diagnosis of MM is challenging due to its composite epithelial/mesenchymal pattern. The aim of the current study was to develop a deep learning method to automatically diagnose MM. A retrospective analysis of 324 participants with or without MM was performed. Significant features were selected using a genetic algorithm (GA) or a ReliefF algorithm performed in MATLAB software. Subsequently, the current study constructed and trained several models based on a backpropagation (BP) algorithm, extreme learning machine algorithm and stacked sparse autoencoder (SSAE) to diagnose MM. A confusion matrix, F‑measure and a receiver operating characteristic (ROC) curve were used to evaluate the performance of each model. A total of 34 potential variables were analyzed, while the GA and ReliefF algorithms selected 19 and 5 effective features, respectively. The selected features were used as the inputs of the three models. SSAE and GA+SSAE demonstrated the highest performance in terms of classification accuracy, specificity, F‑measure and the area under the ROC curve. Overall, the GA+SSAE model was the preferred model since it required a shorter CPU time and fewer variables. Therefore, the SSAE with GA feature selection was selected as the most accurate model for the diagnosis of MM. The deep learning methods developed based on the GA+SSAE model may assist physicians with the diagnosis of MM.

View Figures

View References

1	Remon J, Lianes P, Martinez S, Velasco M, Querol R and Zanui M: Malignant mesothelioma: New insights into a rare disease. Cancer Treat Rev. 39:584–591. 2013. View Article : Google Scholar : PubMed/NCBI
2	Remon J, Reguart N, Corral J and Lianes P: Malignant pleural mesothelioma: New hope in the horizon with novel therapeutic strategies. Cancer Treat Rev. 41:27–34. 2015. View Article : Google Scholar : PubMed/NCBI
3	Thellung S, Favoni RE, Wurth R, Nizzari M, Pattarozzi A, Daga A, Florio T and Barbieri F: Molecular pharmacology of malignant spleural amesothelioma: Challenges and perspectives from preclinical and clinical studies. Curr Drug Targets. 17:824–849. 2016. View Article : Google Scholar : PubMed/NCBI
4	Zucali PA, Ceresoli GL, De Vincenzo F, Simonelli M, Lorenzi E, Gianoncelli L and Santoro A: Advances in the biology of malignant pleural mesothelioma. Cancer Treat Rev. 37:543–558. 2011. View Article : Google Scholar : PubMed/NCBI
5	Ascoli V, Murer B, Nottegar A, Luchini C, Carella R, Calabrese F, Lunardi F, Cozzi I and Righi L: What's new in mesothelioma. Pathologica. 110:12–28. 2018.PubMed/NCBI
6	Ascoli V: Pathologic diagnosis of malignant mesothelioma: Chronological prospect and advent of recommendations and guidelines. Ann Ist super sanita. 51:52–59. 2015.PubMed/NCBI
7	Er O, Tanrikulu AC, Abakay A and Temurtas F: An approach based on probabilistic neural network for diagnosis of Mesothelioma's disease. Comput Electr Eng. 38:75–81. 2012. View Article : Google Scholar
8	Avci D and Dogantekin A: An expert diagnosis system for parkinson disease based on genetic algorithm-wavelet kernel-extreme learning machine. Parkins Dis. 2016:52647432016.
9	Liu X, Wang X, Su Q, Zhang M, Zhu Y and Wang Q and Wang Q: A hybrid classification system for heart disease diagnosis based on the RFRS method. Comput Math Methods Med. 2017:82720912017. View Article : Google Scholar : PubMed/NCBI
10	Chaisaowong K, Aach T, Jager P, Vogel S, Knepper A and Kraus T: Computer-assisted diagnosis for early stage pleural mesothelioma: Towards automated detection and quantitative assessment of pleural thickening from thoracic CT images. Methods Inf Med. 46:324–331. 2007. View Article : Google Scholar : PubMed/NCBI
11	Chen M, Helm E, Joshi N, Gleeson F and Brady M: Computer-aided volumetric assessment of malignant pleural mesothelioma on CT using a random walk-based method. Int J Comput Assist Radiol Surg. 12:529–538. 2017. View Article : Google Scholar : PubMed/NCBI
12	Armato SG III and Sensakovic WF: Automated lung segmentation for thoracic CT impact on computer-aided diagnosis. Acad Radiol. 11:1011–1021. 2004. View Article : Google Scholar : PubMed/NCBI
13	Jiang R, You R, Pei XQ, Zou X, Zhang MX, Wang TM, Sun R, Luo DH, Huang PY, Chen QY, et al: Development of a ten-signature classifier using a support vector machine integrated approach to subdivide the M1 stage into M1a and M1b stages of nasopharyngeal carcinoma with synchronous metastases to better predict patients' survival. Oncotarget. 7:3645–3657. 2016.PubMed/NCBI
14	Huang MW, Chen CW, Lin WC, Ke SW and Tsai CF: SVM and SVM ensembles in breast cancer prediction. PLoS One. 12:e01615012017. View Article : Google Scholar : PubMed/NCBI
15	Huang G, Huang GB, Song S and You K: Trends in extreme learning machines: A review. Neural Netw. 61:32–48. 2015. View Article : Google Scholar : PubMed/NCBI
16	Ortiz A, Munilla J, Gorriz JM and Ramirez J: Ensembles of deep learning architectures for the early diagnosis of the Alzheimer's disease. Int J Neural Syst. 26:16500252016. View Article : Google Scholar : PubMed/NCBI
17	Komura D and Ishikawa S: Machine learning methods for histopathological image analysis. Comput Struct Biotechnol J. 16:34–42. 2018. View Article : Google Scholar : PubMed/NCBI
18	LeCun Y, Bengio Y and Hinton G: Deep learning. Nature. 521:436–444. 2015. View Article : Google Scholar : PubMed/NCBI
19	van Tulder G and de Bruijne M: Combining generative and discriminative representation learning for lung CT analysis with convolutional restricted boltzmann machines. IEEE Trans Med Imag. 35:1262–1272. 2016. View Article : Google Scholar
20	Shin HC, Orton MR, Collins DJ, Doran SJ and Leach MO: Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data. IEEE Trans Pattern Anal Mach Intell. 35:1930–1943. 2013. View Article : Google Scholar : PubMed/NCBI
21	Brosch T and Tam R: Efficient training of convolutional deep belief networks in the frequency domain for application to high-resolution 2D and 3D images. Neural Comput. 27:211–227. 2015. View Article : Google Scholar : PubMed/NCBI
22	Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM and Thrun S: Dermatologist-level classification of skin cancer with deep neural networks. Nature. 542:115–118. 2017. View Article : Google Scholar : PubMed/NCBI
23	Grewal PS, Oloumi F, Rubin U and Tennant MTS: Deep learning in ophthalmology: A review. Can J Ophtalmol. 53:309–313. 2018. View Article : Google Scholar
24	Yan Y, Tan Z, Su N and Zhao C: Building extraction based on an optimized stacked sparse autoencoder of structure and training samples using LIDAR DSM and optical images. Sensors (Basel). 17:E19572017.25. View Article : Google Scholar : PubMed/NCBI
25	Jia W, Yang M and Wang SH: Three-category classification of magnetic resonance hearing loss images based on deep autoencoder. J Med Syst. 41:1652017. View Article : Google Scholar : PubMed/NCBI
26	Deng L, Fan C and Zeng Z: A sparse autoencoder-based deep neural network for protein solvent accessibility and contact number prediction. BMC Bioinformatics. 18:5692017. View Article : Google Scholar : PubMed/NCBI
27	Wang YB, You ZH, Li X, Jiang TH, Chen X, Zhou X and Wang L: Predicting protein-protein interactions from protein sequences by a stacked sparse autoencoder deep neural network. Mol BioSyst. 13:1336–1344. 2017. View Article : Google Scholar : PubMed/NCBI
28	Zhao W, Meng QH, Zeng M and Qi PF: Stacked sparse auto-encoders (SSAE) based electronic nose for chinese liquors classification. Sensors (Basel). 17:E28552017.29. View Article : Google Scholar : PubMed/NCBI
29	Podolsky MD, Barchuk AA, Kuznetcov VI, Gusarova NF, Gaidukov VS and Tarakanov SA: Evaluation of machine learning algorithm utilization for lung cancer classification based on gene expression levels. Asian Pacific J Cancer Prev. 17:835–838. 2016. View Article : Google Scholar
30	Wang L, Wang Y and Chang Q: Feature selection methods for big data bioinformatics: A survey from the search perspective. Methods. 111:21–31. 2016. View Article : Google Scholar : PubMed/NCBI
31	Chen L and Hao Y: Feature extraction and classification of EHG between pregnancy and labour group using Hilbert-Huang transform and extreme learning machine. Comput Math Methods Med. 2017:79495072017. View Article : Google Scholar : PubMed/NCBI
32	Urbanowicz RJ, Meeker M, La Cava W, Olson RS and Moore JH: Relief-based feature selection: Introduction and review. J Biomed Inform. 85:189–203. 2018. View Article : Google Scholar : PubMed/NCBI
33	Urbanowicz RJ, Olson RS, Schmitt P, Meeker M and Moore JH: Benchmarking relief-based feature selection methods for bioinformatics data mining. J Biomed Inform. 85:168–188. 2018. View Article : Google Scholar : PubMed/NCBI
34	Dai Q, Cheng JH, Sun DW and Zeng XA: Advances in feature selection methods for hyperspectral image processing in food industry applications: A review. Crit Rev Food Sci Nutr. 55:1368–1382. 2015. View Article : Google Scholar : PubMed/NCBI
35	Cao J, Cui H, Shi H and Jiao L: Big data: A parallel particle swarm optimization-back-propagation neural network algorithm based on mapreduce. PLoS One. 11:e01575512016. View Article : Google Scholar : PubMed/NCBI
36	Song Y and Zhang J: Automatic recognition of epileptic EEG patterns via extreme learning machine and multiresolution feature extraction. Expert Syst Appl. 40:5477–5489. 2013. View Article : Google Scholar
37	Song Y, Crowcroft J and Zhang J: Automatic epileptic seizure detection in EEGs based on optimized sample entropy and extreme learning machine. J Neurosci Methods. 210:132–146. 2012. View Article : Google Scholar : PubMed/NCBI
38	Xu J, Xiang L, Liu Q, Gilmore H, Wu J, Tang J and Madabhushi A: Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images. IEEE Trans Med Imaging. 35:119–130. 2016. View Article : Google Scholar : PubMed/NCBI
39	Langkvist M and Loutfi A: Learning feature representations with a cost-relevant sparse autoencoder. Int J Neural Syst. 25:14500342015. View Article : Google Scholar : PubMed/NCBI
40	Tsinalis O, Matthews PM and Guo Y: Automatic sleep stage scoring using time-frequency analysis and stacked sparse autoencoders. Ann Biomed Eng. 44:1587–1597. 2016. View Article : Google Scholar : PubMed/NCBI
41	Chen LL and Hao YR: Discriminating pregnancy and labour in electrohysterogram by sample entropy and support vector machine. J Med Imaging Health Inform. 7:584–591. 2017. View Article : Google Scholar
42	Janowczyk A, Basavanhally A and Madabhushi A: Stain normalization using sparse auto encoders (StaNoSA): Application to digital pathology. Comput Med Imaging Graph. 57:50–61. 2017. View Article : Google Scholar : PubMed/NCBI
43	Su H, Xing F, Kong X, Xie Y, Zhang S and Yang L: Robust cell detection and segmentation in histopathological images using sparse reconstruction and stacked denoising auto encoders. Med Image Comput Comput Assist Interv. 9351:383–390. 2015.PubMed/NCBI
44	Paydar K, Niakan Kalhori SR, Akbarian M and Sheikhtaheri A: A clinical decision support system for prediction of pregnancy outcome in pregnant women with systemic lupus erythematosus. Int J Med Inform. 97:239–246. 2017. View Article : Google Scholar : PubMed/NCBI
45	Somu N, M R RG, V K, Kirthivasan K and V S SS: An improved robust heteroscedastic probabilistic neural network based trust prediction approach for cloud service selection. Neural Netw. 108:339–354. 2018. View Article : Google Scholar : PubMed/NCBI