Display options
Cite
Huong AKC, Tay KG, Ngu XTI. Five-Class Classification of Cervical Pap Smear Images: A Study of CNN-Error-Correcting SVM Models. Healthc Inform Res. 2021;27(4):298-306doi: 10.4258/hir.2021.27.4.298.
Huong, A. K. C., Tay, K. G., & Ngu, X. T. I. (2021). Five-Class Classification of Cervical Pap Smear Images: A Study of CNN-Error-Correcting SVM Models. Healthcare informatics research, 27(4), 298-306. https://doi.org/10.4258/hir.2021.27.4.298
Huong, Audrey K C, et al. "Five-Class Classification of Cervical Pap Smear Images: A Study of CNN-Error-Correcting SVM Models." Healthcare informatics research vol. 27,4 (2021): 298-306. doi: https://doi.org/10.4258/hir.2021.27.4.298
Huong AKC, Tay KG, Ngu XTI. Five-Class Classification of Cervical Pap Smear Images: A Study of CNN-Error-Correcting SVM Models. Healthc Inform Res. 2021 Oct;27(4):298-306. doi: 10.4258/hir.2021.27.4.298. Epub 2021 Oct 31. PMID: 34788910; PMCID: PMC8654336.
Copy Download .nbib Format: NLM
Share it on

Healthc Inform Res. 2021 Oct;27(4):298-306. doi: 10.4258/hir.2021.27.4.298. Epub 2021 Oct 31.

Five-Class Classification of Cervical Pap Smear Images: A Study of CNN-Error-Correcting SVM Models.

Healthcare informatics research

Audrey K C Huong, Kim Gaik Tay, Xavier T I Ngu

Affiliations

  1. Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Malaysia.

PMID: 34788910 PMCID: PMC8654336 DOI: 10.4258/hir.2021.27.4.298

Abstract

OBJECTIVES: Different complex strategies of fusing handcrafted descriptors and features from convolutional neural network (CNN) models have been studied, mainly for two-class Papanicolaou (Pap) smear image classification. This paper explores a simplified system using combined binary coding for a five-class version of this problem.

METHODS: This system extracted features from transfer learning of AlexNet, VGG19, and ResNet50 networks before reducing this problem into multiple binary sub-problems using error-correcting coding. The learners were trained using the support vector machine (SVM) method. The outputs of these classifiers were combined and compared to the true class codes for the final prediction.

RESULTS: Despite the superior performance of VGG19-SVM, with mean ± standard deviation accuracy and sensitivity of 80.68% ± 2.00% and 80.86% ± 0.45%, respectively, this model required a long training time. There were also false-negative cases using both the VGGNet-SVM and ResNet-SVM models. AlexNet-SVM was more efficient in terms of running speed and prediction consistency. Our findings also showed good diagnostic ability, with an area under the curve of approximately 0.95. Further investigation also showed good agreement between our research outcomes and that of the state-of-the-art methods, with specificity ranging from 93% to 100%.

CONCLUSIONS: We believe that the AlexNet-SVM model can be conveniently applied for clinical use. Further research could include the implementation of an optimization algorithm for hyperparameter tuning, as well as an appropriate selection of experimental design to improve the efficiency of Pap smear image classification.

Keywords: Cervix Uteri; Diagnosis; Nerve Net; Papanicolaou Test; Support Vector Network

References

  1. Clin Ther. 2016 Mar;38(3):459-66 - PubMed
  2. Radiother Oncol. 2020 Jul;148:211-212 - PubMed
  3. Prev Med. 2017 Jul;100:243-247 - PubMed
  4. IEEE J Biomed Health Inform. 2017 Nov;21(6):1633-1643 - PubMed
  5. BMC Womens Health. 2016 Aug 03;16:51 - PubMed
  6. Tissue Cell. 2020 Aug;65:101347 - PubMed
  7. Future Oncol. 2020 Nov;16(33):2687-2690 - PubMed
  8. Biomed Res Int. 2018 Nov 8;2018:6456724 - PubMed
  9. Comput Methods Programs Biomed. 2018 Oct;164:15-22 - PubMed
  10. World J Gastroenterol. 2010 Feb 7;16(5):531-7 - PubMed
  11. Syst Rev. 2019 Jun 7;8(1):132 - PubMed
  12. Hum Pathol. 2003 Nov;34(11):1193-203 - PubMed
  13. BMJ. 1989 Oct 28;299(6707):1083-6 - PubMed
  14. J Womens Health (Larchmt). 2019 Feb;28(2):244-249 - PubMed

Publication Types

Grant support