Artificial classification of cervical squamous lesions in ThinPrep cytologic tests using a deep convolutional neural network

Liu,Li; Wang,Yuanhua; Ma,Qiang; Tan,Liwen; Wu,Yi; Xiao,Jingjing

doi:10.3892/ol.2020.11974

Artificial classification of cervical squamous lesions in ThinPrep cytologic tests using a deep convolutional neural network

Authors:
- Li Liu
- Yuanhua Wang
- Qiang Ma
- Liwen Tan
- Yi Wu
- Jingjing Xiao
View Affiliations

Affiliations: Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Third Military Medical University (Army Medical University), Chongqing 400038, P.R. China, Department of Pathology, Third Affiliated Hospital, Third Military Medical University (Army Medical University), Chongqing 400042, P.R. China, Department of Medical Engineering, Second Affiliated Hospital, Third Military Medical University (Army Medical University), Chongqing 400037, P.R. China
Published online on: August 12, 2020 https://doi.org/10.3892/ol.2020.11974
Article Number: 113
Copyright: © Liu 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

The diagnosis of squamous cell carcinoma requires the accurate classification of cervical squamous lesions in the ThinPrep cytologic test (TCT). It primarily relies on a pathologist's interpretation under a microscope. Deep convolutional neural networks (DCNN) have played an increasingly important role in digital pathology. However, they have not been applied to diverse datasets and externally validated. In the present study, a DCNN model based on VGG16 and an ensemble training strategy (ETS) based on 5‑fold cross‑validation was employed to automatically classify normal and abnormal cervical squamous cells from a multi‑center dataset. First, we collected a dataset comprising 82 TCT samples from four hospitals and fine‑tuned our model twice on the dataset with and without the ETS. Then, we compared the classifications obtained from the models with those provided by two skilled pathologists to discriminate the performance of the models in terms of classification accuracy and efficiency. Finally, paired sample t‑tests were used to validate the consistency between the classification provided by the proposed methods and that of the pathologists. The results showed that ETS slightly, though not significantly, improved the classification accuracy compared with that of the pathologists: P₀=0.387>0.05 (DCNN without ETS vs. DCNN with ETS), P₁=0.771>0.05 (DCNN with ETS vs. pathologist 1), P₂=0.489>0.05 (DCNN with ETS vs. pathologist 2). The DCNN model was almost 6‑fold faster than that of the pathologists. The accuracy of our automated scheme was similar to that of the pathologists, but a higher efficiency in the accurate identification of cervical squamous lesions was provided by the scheme. This result allows for wider and more efficient screening and may provide a replacement for pathologists in the future. Future research should address the viability of the practical implementation of such DCNN models in the laboratory setting.

View Figures

View References

1	Small W Jr, Bacon MA, Bajaj A, Chuang LT, Fisher BJ, Harkenrider MM, Jhingran A, Kitchener HC, Mileshkin LR, Viswanathan AN and Gaffney DK: Cervical cancer: A global health crisis. Cancer. 123:2404–2412. 2017. View Article : Google Scholar : PubMed/NCBI
2	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
3	Globocan, . 2018.China factsheet. July 18–2020
4	Cheng WQ, Zheng QS, Zhang SW, Zeng HM, Zuo TT, Jia MM, Xia CF, Zhou XN and He J: Analysis of incidence and death of malignant tumors in China in 2012. China Cancer. 25:1–8. 2016.
5	Chacho MS, Mattie ME and Schwartz PE: Cytohistologic correlation rates between conventional Papanicolaou smears and ThinPrep cervical cytology: A comparison. Cancer. 99:135–140. 2003. View Article : Google Scholar : PubMed/NCBI
6	Behtash N and Mehrdad N: Cervical cancer: screening and prevention. Asian Pac J Cancer Prev. 7:683–686. 2006.PubMed/NCBI
7	Ritu N and Wilbur D: The Bethesda System for reporting cervical cytology: Definitions, criteria, and explanatory notes. Springer International Publishing; Berlin: 2015, PubMed/NCBI
8	Xie Y, Zhang J, Xia Y and Shen C: A mutual bootstrapping model for automated skin lesion segmentation and classification. IEEE Trans Med Imaging. 39:2482–2493. 2020. View Article : Google Scholar : PubMed/NCBI
9	Gehlot S, Gupta A and Gupta R: SDCT-AuxNet°: DCT augmented stain deconvolutional CNN with auxiliary classifier for cancer diagnosis. Med Image Anal. 61:1016612020. View Article : Google Scholar : PubMed/NCBI
10	Murugan A, Nair SAH and Kumar KPS: Detection of skin cancer using SVM, random forest and kNN classifiers. J Med Syst. 43:2692019. View Article : Google Scholar : PubMed/NCBI
11	Abdulkerim C, Abdülkadir A, Aslı Ü, Nurullah Ç, Gökhan B, Ilknur T, Aslı Ç, Behçet UT and Lütfiye DA: Segmentation of precursor lesions in cervical cancer using convolutional neural networks. 25^th Signal Processing and Communications Applications Conference (SIU). 2017.
12	Chankong T, Theera-Umpon N and Auephanwiriyakul S: Automatic cervical cell segmentation and classification in Pap smears. Comput Methods Programs Biomed. 113:539–556. 2014. View Article : Google Scholar : PubMed/NCBI
13	Zhang L, Lu L, Nogues I, Summers RM, Liu S and Yao J: DeepPap: Deep convolutional networks for cervical cell classification. IEEE J Biomed Health Inform. 21:1633–1643. 2017. View Article : Google Scholar : PubMed/NCBI
14	Wu M, Yan C, Liu H, Liu Q and Yin Y: Automatic classification of cervical cancer from cytological images by using convolutional neural network. Biosci Rep. 38:BSR201817692018. View Article : Google Scholar : PubMed/NCBI
15	Tian Y, Yang L, Wang W, Zhang J, Tang Q, Ji M, Yu Y, Li Y, Yang H and Qian A: Computer-aided detection of squamous carcinoma of the cervix in whole slide images. arXiv 1905.10959. 2019.
16	Liu L, Wang Y, Wu D, Zhai Y, Tan L and Xiao J: Multi-task learning for pathomorphology recognition of squamous intraepithelial lesion in Thinprep cytologic test. ISICDM. 10:73–77. 2018.
17	Miyagi Y, Takehara K, Nagayasu Y and Miyake T: Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images combined with HPV types. Oncol Lett. 19:1602–1610. 2020.PubMed/NCBI
18	Weiss S, Xu ZZ, Shyamal P, Amir A, Bittinger K, Gonzalez A, Lozupone C, Zaneveld JR, Vázquez-Baeza Y, Birmingham A, et al: Normalization and microbial differential abundance strategies depend upon data characteristics. Microbiome. 5:272017. View Article : Google Scholar : PubMed/NCBI
19	Simonyan K and Zisserman A: Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556. 2014.
20	Saikia AR, Bora K, Mahanta LB and Das AK: Comparative assessment of CNN architectures for classification of breast FNAC images. Tissue Cell. 57:8–14. 2019. View Article : Google Scholar : PubMed/NCBI
21	Sharma S and Mehra R: Conventional machine learning and deep learning approach for multi-classification of breast cancer histopathology images-a comparative insight. J Digit Imaging. 33:632–654. 2020. View Article : Google Scholar : PubMed/NCBI
22	Pan SJ and Yang Q: A survey on transfer learning. IEEE Trans Knowledge Data Eng. 10:1345–1359. 2010. View Article : Google Scholar
23	Deng J, Dong W, Socher R, Li LJ, Li K and Li FF: ImageNet: A large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition. 248–255. 2009.
24	Takase T, Oyama S and Kurihara M: Effective neural network training with adaptive learning rate based on training loss. Neural Netw. 101:68–78. 2018. View Article : Google Scholar : PubMed/NCBI
25	Mo Z, Wang Q, Tian S, Yan R, Geng J, Yao Z and Lu Q: Evaluating treatment via flexibility of dynamic MRI community structures in depression. J Southeast Univ. 33:273–276. 2017.
26	Hyvärinen A and Oja E: Independent component analysis: Algorithms and applications. Neural Netw. 13:411–430. 2000. View Article : Google Scholar : PubMed/NCBI
27	Taqi AM, Awad A, Al-Azzo F and Milanova M: The impact of multi-optimizers and data augmentation on TensorFlow convolutional neural network performance. IEEE Conference on Multimedia Information Processing Retrieval. 140–145. 2018.