Feature assisted cervical cancer screening through DIC cell images

• Autorzy: Adhikary Shreya , Seth Sayan , Das Seema , Naskar Tapan Kumar , Barui Ananya , Maity Santi P.

Identyfikatory

DOI

10.1016/j.bbe.2021.07.005

• Języki publikacji: EN

Abstrakty

EN

The mortality rate of cervical cancer is increasing alarmingly. Conventional cytological methods are not always efficient to diagnose cancer at an early stage. Several label-free, quantitative screening approaches are emerging rapidly for fast and accurate detection of cervical cancer. Differential interference contrast (DIC) imaging is one of such label-free methods for the detection of cellular abnormality. The combination of DIC imaging and prediction algorithm enables the development of an efficient computer-aided diagnosis (CAD) system for cervical cancer detection at an early stage. In the present study, the DIC dataset is categorized into 2-classes (abnormal and normal) and 3-classes (normal, pre-cancer, and squamous cell carcinoma). After segmentation of the cells using the modified valley-based Otsu’s thresholding method, three classifiers, namely support vector machine (SVM), multilayer perceptron (MLP), and k-nearest neighbour (k-NN) are applied. Further, to improve the classification performances, principal component analysis (PCA) is applied for feature selection. The experimental results reveal that the SVM classifier has the greatest accuracy of 0.97 (2-class classification) and 0.90 (3-class classification).

Słowa kluczowe

EN

DIC imaging; differential interference contrast; elliptical difference; cervical cancer detection; feature selection; artificial neural network

PL

obrazowanie DIC; różnica eliptyczna; rak szyjki macicy; selekcja cech; sztuczna sieć neuronowa

• 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. 3
• Strony: 1162--1181
• Opis fizyczny: Bibliogr. 44 poz., rys., tab., wykr.

Twórcy

autor

Adhikary Shreya

• Centre for Healthcare Science and Technology, Indian Institute of Engineering Science and Technology, Shibpur, Howrah, India

autor

Seth Sayan

• Qualcomm India Private Limited, Bangalore, India

autor

Das Seema

• Department of Obstetrics and Gynaecology, R. G. Kar Medical College and Hospital, Kolkata, India

autor

Naskar Tapan Kumar

• Department of Obstetrics and Gynaecology, Medical College and Hospital, Kolkata, India

autor

Barui Ananya

• Centre for Healthcare Science and Technology, Indian Institute of Engineering Science and Technology, Shibpur, Howrah, India

autor

Maity Santi P.

• Department of Information Technology, Indian Institute of Engineering Science and Technology, Shibpur, Howrah, India

Bibliografia

• [1] Cervical cancer, World Health Organization, 2021, [Online]. Available: https://www.who.int/health-topics/cervicalcancer#tab=tab_1 (accessed. 01.02.2021).
• [2] B. R. Sivakumar N, Narwal A, Kumar S, Kamboj M, Devi A, Pandiar D, Application of the Bethesda system of reporting for cervical cytology to evaluate human papilloma virus induced changes in oral leukoplakia, oral squamous cell carcinoma, and oropharyngeal squamous cell carcinoma: A cytomorphological and genetic study, Diagnostic Cytopathology, vol. 24, no. 7, 2021, 10.1002/dc.24813.
• [3] Zheng L, Yu K, Cai S, Wang Y, Zeng B, Xu M. Lung cancer diagnosis with quantitative DIC microscopy and a deep convolutional neural network. Biomed Opt Express 2019;10 (5):2446–56. https://doi.org/10.1364/BOE.10.002446.
• [4] Adhikary S, Paul RR, Mandal M, Maity SP, Barui A. Overlapping oral epithelial cells segmentation: voronoi-based hybrid active contour model. In: Advanced Machine Learning Approaches in Cancer Prognosis. Cham: Springer; 2021. p. 247–74. https://doi.org/10.1007/978-3-030-71975-3_9.
• [5] Dey S, Sarkar R, Chatterjee K, Datta P, Barui A, Maity SP. Precancer risk assessment in habitual smokers from DIC images of oral exfoliative cells using active contour and SVM analysis. Tissue Cell 2017;49(2):296–306. https://doi.org/10.1016/j.tice.2017.01.009.
• [6] Jia D, Zhang C, Wu N, Guo Z, Ge H. Multi-layer segmentation framework for cell nuclei using improved GVF Snake model, Watershed, and ellipse fitting. Biomed Signal Process Control 2021;67(January):1–16. https://doi.org/10.1016/j.bspc.2021.102516.
• [7] Truong MTN, Kim S. Automatic image thresholding using Otsu’s method and entropy weighting scheme for surface defect detection. Soft Comput 2018;22(13):4197–203. https://doi.org/10.1007/s00500-017-2709-1.
• [8] Tareef A, Song Y, Huang H, Feng D, Chen M, Wang Y, et al. Multi-pass fast Watershed for accurate segmentation of overlapping cervical cells. IEEE Trans Med Imaging 2018;37 (9):2044–59. https://doi.org/10.1109/TMI.2018.2815013.
• [9] Chen B, Huang S, Liang Z, Chen W, Pan B. A fractional order derivative based active contour model for inhomogeneous image segmentation. Appl Math Model 2019;65:120–36. https://doi.org/10.1016/j.apm.2018.08.009.
• [10] Thiyaneswaran B. Early detection of melanoma images using gray level co-occurrence matrix features and machine learning techniques for effective clinical diagnosis. Imag Syst Technol 2020;10(October):1–13. https://doi.org/10.1002/ima.22514.
• [11] Abdoh SF, Rizka MABO, Maghraby FA. Cervical cancer diagnosis using random forest classifier with SMOTE and feature reduction techniques. IEEE Access 2018;6:59475–85. https://doi.org/10.1109/ACCESS.2018.2874063.
• [12] Malli PK, Nandyal S. Machine learning Technique for detection of Cervical Cancer using k-NN and Artificial Neural Network, vol. 6, no. 4, 2017.
• [13] Pap-Smear (DTU/HERLEV) Databaes & related Studies, MBELAB, 2008, [Online]. Available: http://mde-lab.aegean.gr/index.php/downloads.
• [14] Sokouti B, Haghipour S, Tabrizi AD. A framework for diagnosing cervical cancer disease based on feedforward MLP neural network and ThinPrep histopathological cell image features. Neural Comput Appl 2014;24(1):221–32. https://doi.org/10.1007/s00521-012-1220-y.
• [15] Chankong T, Theera-Umpon N, Auephanwiriyakul S. Automatic cervical cell segmentation and classification in Pap smears. Comput Methods Programs Biomed 2014;113(2):539–56. https://doi.org/10.1016/j.cmpb.2013.12.012.
• [16] Sarkar R et al. Risk prediction for oral potentially malignant disorders using fuzzy analysis of cytomorphological and autofluorescence alterations in habitual smokers. Future Oncol 2017;13(6):499–511.
• [17] Wang P, Wang L, Li Y, Song Q, Lv S, Hu X. Automatic cell nuclei segmentation and classification of cervical Pap smear images. Biomed Signal Process Control 2019;48:93–103. https://doi.org/10.1016/j.bspc.2018.09.008.
• [18] Somasundaram D, Gnanasaravanan S, Madian N. Automatic segmentation of nuclei from pap smear cell images: a step toward cervical cancer screening. Int J Imaging Syst Technol 2020;30(4):1209–19. https://doi.org/10.1002/ima.22444.
• [19] Jia FAD, Zhengyi SB, Zhang TCC. Detection of cervical cancer cells based on strong feature CNN-SVM network. Neurocomputing 2020;411:112–27. https://doi.org/10.1016/j.neucom.2020.06.006.
• [20] Jia D, Member S, Li Z, Zhang C. A parametric optimization oriented, AFSA based random forest algorithm: application to the detection of cervical epithelial cells. IEEE Access 2020;8:64891–905. https://doi.org/10.1109/ACCESS.2020.2984657.
• [21] Wentzensen N, Tokugawa D, Lahrmann B, Clarke MA, Kinney W, Poitras N, et al. Accuracy and efficiency of deep-learning – based automation of dual stain cytology in cervical cancer screening. J Nat Cancer Inst 2020;113(November 2019):1–8. https://doi.org/10.1093/jnci/djaa066.
• [22] Elakkiya R, Sai K, Teja S, Deborah LJ, Bisogni C. Imaging based cervical cancer diagnostics using small object detection – generative adversarial networks. Multim Tools Appl 2021;1–17. https://doi.org/10.1007/s11042-021-10627-31191.
• [23] Ijaz MF, Attique M, Son Y. Data-driven cervical cancer prediction model with outlier detection and over-sampling methods. Sensors (Basel, Switzerland) 2020;20(10):1–22. https://doi.org/10.3390/s20102809.
• [24] Adem K, Kiliçarslan S, Cömert O. Classification and diagnosis of cervical cancer with stacked autoencoder and softmax classification. Expert Syst Appl 2019;115:557–64. https://doi.org/10.1016/j.eswa.2018.08.050.
• [25] Zhang T, Luo Y, Li P, Liu P, Du Y, Sun P. Cervical precancerous lesions classification using pre-trained densely connected convolutional networks with colposcopy images. Biomed Signal Process Control 2020;55. https://doi.org/10.1016/j.bspc.2019.101566 101566.
• [26] Xu T et al. Multi-feature based Benchmark for Cervical Dysplasia Classification Evaluation Reference: To appear in: pattern recognition. Pattern Recog 2016;63:468–75. https://doi.org/10.1016/j.patcog.2016.09.027.
• [27] Sanyal P, Ganguli P, Barui S. Performance characteristics of an artificial intelligence based on convolutional neural network for screening conventional Papanicolaou-stained cervical smears. Med J Armed Forces India 2020;76(4):418–24. https://doi.org/10.1016/j.mjafi.2019.08.001.
• [28] Kudva V, Prasad K, Guruvare S. Hybrid transfer learning for classification of uterine cervix images for cervical cancer screening. J Digit Imaging 2020;33(3):619–31. https://doi.org/10.1007/s10278-019-00269-1.
• [29] Kashyap D, Somani A, Shekhar J. Cervical cancer detection and classification using independent level sets and multi SVMs. In: International Conference on Telecommmunications and Signal Processing (TSP). p. 523–8. https://doi.org/10.1109/TSP.2016.7760935.
• [30] Liu Y, Fan H, Dong Di, Liu P, He B, Meng L, et al. Computed tomography-based radiomic model at node level for the prediction of normal-sized lymph node metastasis in cervical cancer. Transl Oncol 2021;14(8):101113. https://doi.org/10.1016/j.tranon.2021.101113.
• [31] Huo X, Zhou X, Peng P, Yu M, Zhang Y, Yang J, et al. Identification of a six-gene signature for predicting the overall survival of cervical cancer patients. OncoTargets Therapy 2021;14:809–22. https://doi.org/10.2147/OTT.S276553.
• [32] Chandran V, Sumithra MG, Karthick A, George T, Deivakani M, Elakkiya B, et al.Diagnosis of cervical cancer based on ensemble deep learning network using colposcopy images. J DigitImaging 2021;2021:1–15. https://doi.org/10.1155/2021/5584004.
• [33] Gui B, Autorino R, Miccò M, Nardangeli A, Pesce A, Lenkowicz J, et al. Pretreatment MRI radiomics based response prediction model in locally advanced cervical cancer. Diagnostics (Basel) 2021;11(4):631. https://doi.org/10.3390/diagnostics11040631.
• [34] Bhatt AR, Ganatra A, Kotecha K. Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing. PeerJ Comp Sci 2021;1–18. https://doi.org/10.7717/peerj-cs.348.
• [35] Stenhouse K, Roumeliotis M, Banerjee R. Development of a machine learning model for optimal applicator selection in high-dose-rate cervical brachytherapy. Front Oncol 2021;11(March):1–10. https://doi.org/10.3389/fonc.2021.611437.
• [36] Xing J, Yang P, Qingge L. Automatic thresholding using a modified valley emphasis. IET Image Proc 2020;14(3):536–44. https://doi.org/10.1049/iet-ipr.2019.0176.
• [37] Yu H, He F, Pan Y. A scalable region-based level set method using adaptive bilateral filter for noisy image segmentation. Multimedia Tools Appl 2020;79(9–10):5743–65. https://doi.org/10.1007/s11042-019-08493-1.
• [38] Geetha R, Sivasubramanian S, Kaliappan M, Vimal S, Annamalai S. Cervical cancer identification with synthetic minority oversampling technique and PCA analysis using random forest classifier. J Med Syst 2019;43(9):286. https://doi.org/10.1007/s10916-019-1402-6.
• [39] Kimori Y. Morphological image processing for quantitative shape analysis of biomedical structures: effective contrast enhancement. J Synchrotron Radiat 2013;20(6):848–53. https://doi.org/10.1107/S0909049513020761.
• [40] Saha R, Bajger M, Lee G. Circular shape constrained fuzzy clustering (CiscFC) for nucleus segmentation in Pap smear images. Comput Biol Med 2017;85(March):13–23.
• [41] Fan J-L, Lei B. A modified valley-emphasis method for automatic thresholding. Pattern Recogn Lett 2012;33(6):703–8. https://doi.org/10.1016/j.patrec.2011.12.009.
• [42] Wu Y, Peng X, Ruan K, Hu Z. Improved image segmentation method based on morphological reconstruction. Multimedia Tools Appl 2017;76(19):19781–93. https://doi.org/10.1007/s11042-015-3192-2.
• [43] Wang XF, Min H, Zou L, Zhang YG. A novel level set method for image segmentation by incorporating local statistical analysis and global similarity measurement. Pattern Recogn 2015;48(1):189–204. https://doi.org/10.1016/j.patcog.2014.07.008.
• [44] He B, Chen W, Liu L, Hou Z, Zhu H, Cheng H. Prediction models for prognosis of cervical cancer: systematic review and critical appraisal. Front Public Health 2021;9(May):1–10. https://doi.org/10.3389/fpubh.2021.654454.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).