Cervical Cancer Prediction by Merging Features of Different Colposcopic Images and Using Ensemble Classifier

Elham Nikookar, Ebrahim Naderi, Ali Rahnavard

DOI: DOI: 10.4103/jmss.JMSS_16_20

Abstract


Background: Cervical cancer is a significant cause of cancer mortality in women, particularly in low-income countries. In regular cervical screening methods, such as colposcopy, an image is taken from the cervix of a patient. The particular image can be used by computer-aided diagnosis (CAD) systems that are trained using artificial intelligence algorithms to predict the possibility of cervical cancer. Artificial intelligence models had been highlighted in a number of cervical cancer studies. However, there are a limited number of studies that investigate the simultaneous use of three colposcopic screening modalities including Greenlight, Hinselmann, and Schiller. Methods: We propose a cervical cancer predictor model which incorporates the result of different classification algorithms and ensemble classifiers. Our approach merges features of different colposcopic images of a patient. The feature vector of each image includes semantic medical features, subjective judgments, and a consensus. The class label of each sample is calculated using an aggregation function on expert judgments and consensuses. Results: We investigated different aggregation strategies to find the best formula for aggregation function and then we evaluated our method using the quality assessment of digital colposcopies dataset, and our approach performance with 96% of sensitivity and 94% of specificity values yields a significant improvement in the field. Conclusion: Our model can be used as a supportive clinical decision-making strategy by giving more reliable information to the clinical decision makers. Our proposed model also is more applicable in cervical cancer CAD systems compared to the available methods.


Keywords


Aggregation strategy, artificial intelligence, cervical cancer, ensemble classifier, machine learning

Full Text:

PDF

References


Papillomavirus H. Related Cancers. WORLD. Summary Report Update; 2010.

Fernandes K, Cardoso JS, Fernandes J. Temporal segmentation of digital colposcopies. In: Iberian Conference on Pattern Recognition and Image Analysis. IbPRIA 2015, Spain: Springer; 2015.

Vassilakos P, Petignat P, Boulvain M, Campana A. Primary screening for cervical cancer precursors by the combined use of liquid-based cytology, computer-assisted cytology and HPV DNA testing. Br J Cancer 2002;86:382-8.

Lorincz AT. Cancer diagnostic classifiers based on quantitative DNA methylation. Expert Rev Molec Diagn 2014;14:293-305.

Xu T, Zhang H, Xin C, Kim E, Long LR, Xue Z, et al. Multi-feature based Benchmark for cervical dysplasia classification evaluation. Pattern Recognit 2017;63:468-75.

Akbar S, Hayat M, Iqbal M, Jan MA. IACP-GAEnsC: Evolutionary genetic algorithm based ensemble classification of anticancer peptides by utilizing hybrid feature space. Artif Intell Med 2017;79:62-70.

Soares F, Becker K, Anzanello MJ. A hierarchical classifier based on human blood plasma fluorescence for non-invasive colorectal cancer screening. Artif Intell Med 2017;82:1-0.

Wei L, Wan S, Guo J, Wong KK. A novel hierarchical selective ensemble classifier with bioinformatics application. Artif Intell Med 2017;83:82-90.

Duncan ID. Cervical screening. Obstet Gynaecol 2004;6:93-7.

Fusco E, Padula F, Mancini E, Cavaliere A, Grubisic G. History of colposcopy: A brief biography of Hinselmann. J Prenatal Med 2008;2:19.

Ashfaq R, Bartholomew D, Flowers L, Garcia F, Padilla L, Solomon D, O'Connor D. The CERVIX: Colposcopy of the Uterine Cervix.

Tumer K, Ramanujam N, Ghosh J, Richards-Kortum R. Ensembles of radial basis function networks for spectroscopic detection of cervical precancer. IEEE Trans Biomed Eng 1998;45:953-61.

Phoulady HA, Chaudhury B, Goldgof D, Hall LO, Mouton PR, Hakam A, et al. Experiments with Large Ensembles for Segmentation and Classification of Cervical Cancer Biopsy Images. Systems, man and Cybernetics (SMC). 2014 IEEE International Conference on, IEEE; 2014.

Arteta C, Lempitsky V, Noble JA, Zisserman A. Learning to Detect cells Using Non-Overlapping External Regions. International Conference on Medical Image Computing and Computer-Assisted Intervention. MICCAI 2012, France,: Springer; 2012.

Sarwar A, Sharma V, Gupta R. Hybrid ensemble learning technique for screening of cervical cancer using Papanicolaou smear image analysis. Personal Med Univ 2015;4:54-62.

Pfohl S, Triebe O, Marafino B. Guiding the Management of Cervical Cancer with Convolutional Neural Networks; 2017.

Fernandes K, Cardoso JS, Fernandes J. Quality Assessment of Digital Colposcopies Data Set. UCI Machine Learning Repository; 2017.

Catto JW, Linkens DA, Abbod MF, Chen M, Burton JL, Feeley KM, et al. Artificial intelligence in predicting bladder cancer outcome: A comparison of neuro-fuzzy modeling and artificial neural networks. Clin Cancer Res 2003;9:4172-7.

Lisboa PJ, Taktak AF. The use of artificial neural networks in decision support in cancer: A systematic review. Neural Networks 2006;19:408-15.

Antal B, Hajdu A. An ensemble-based system for automatic screening of diabetic retinopathy. Knowled Based Syst 2014;60:20-7.

Fernandes K, Cardoso JS, Fernandes J. Transfer Learning with Partial Observability Applied to Cervical Cancer Screening. Iberian Conference on Pattern Recognition and Image Analysis. IbPRIA 2017, Spain: Springer; 2017.

Chang CC, Lin CJ. LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2011;2:27.

West J, Ventura D, Warnick S. Spring research presentation: A theoretical foundation for inductive transfer. Brigham Young University, College of Physical and Mathematical Sciences. 2007;1.

Trybulec WA. Pigeon hole principle. Formalized Mathem 1990;1:575-9.

Ruta D, Gabrys B. Classifier selection for majority voting. Inform Fusion 2005;6:63-81.

Altman DG, Bland JM. Diagnostic tests. 1: Sensitivity and specificity. BMJ Br Med J 1994;308:1552.

Mason SJ, Graham NE. Areas beneath the relative operating characteristics (ROC) and relative operating levels (ROL) curves: Statistical significance and interpretation. Q J Royal Meteorol Soc 2002;128:2145-66.

Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH. The WEKA data mining software: An update. ACM SIGKDD Explorat Newslett 2009;11:10-8.


Refbacks

  • There are currently no refbacks.