A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification
Source abstract
Abstract
Prevention of cervical cancer could be performed using Pap smear image analysis. This test screens pre-neoplastic changes in the cervical epithelial cells; accurate screening can reduce deaths caused by the disease. Pap smear test analysis is exhaustive and repetitive work performed visually by a cytopathologist. This article proposes a workload-reducing algorithm for cervical cancer detection based on analysis of cell nuclei features within Pap smear images. We investigate eight traditional machine learning methods to perform a hierarchical classification. We propose a hierarchical classification methodology for computer-aided screening of cell lesions, which can recommend fields of view from the microscopy image based on the nuclei detection of cervical cells. We evaluate the performance of several algorithms against the Herlev and CRIC databases, using a varying number of classes during image classification. Results indicate that the hierarchical classification performed best when using Random Forest as the key classifier, particularly when compared with decision trees, k-NN, and the Ridge methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: AI in cancer detection · Cervical Cancer and HPV Research · Digital Imaging for Blood Diseases
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Departamento de Computação, Universidade Federal de Ouro Preto (UFOP), Ouro Preto 35400-000, Brazil
Departamento de Análises Clínicas, Universidade Federal de Ouro Preto (UFOP), Ouro Preto 35400-000, Brazil
Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
Departamento de Engenharia de Teleinformática, Universidade Federal do Ceará (UFC), Fortaleza 60020-181, Brazil
Funding
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brazil (CAPES) - Finance Code 001 · Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG) · Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) · Pró-Reitoria de Pesquisa e Inovação: PROPI/UFOP - 19/2020 · Moore-Sloan Foundation, and Office of Science, of the U.S. Department of Energy
References (68)
Show source-provided references
1. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries
2. False-negative rate of papanicolaou testing: A national survey from the Thai society of cytology10.1159/000478770 ↗
3. A study on cervical cancer screening using pap smear test and clinical correlation10.4103/apjon.apjon_15_18 ↗
4. Bethesda 2014: Improving on a paradigm shift10.1111/cyt.12300 ↗
5. Report on consensus conference on cervical cancer screening and management10.1002/(SICI)1097-0215(20000501)86:3<440::AID-IJC22>3.0.CO;2-A ↗
6. Quality assurance and risk reduction guidelines10.1159/000328521 ↗
7. False-negative results in cervical cytologic studies
8. Characteristics of false-negative smears tested in the normal screening situation
9. The false-negative fraction for Papanicolaou smears
10. Fatores associados a resultados falso-negativos de exames citopatológicos do colo uterino10.1590/S0100-72032006000800007 ↗
11. O impacto da fase pré-analítica na qualidade dos esfregaços cervicovaginais
12. A review of Image Analysis and Machine Learning Techniques for Automated Cervical Cancer Screening from pap-smear images10.1016/j.cmpb.2018.05.034 ↗
13. Jantzen, J., Norup, J., Dounias, G., and Bjerregaard, B. (2005, January 4–5). Pap-smear benchmark data for pattern classification. Proceedings of the Nature Inspired Smart Information Systems (NiSIS 2005), Albufeira, Portugal.
14. Evaluation of Three Algorithms for the Segmentation of Overlapping Cervical Cells10.1109/JBHI.2016.2519686 ↗
15. Plissiti, M.E., Dimitrakopoulos, P., Sfikas, G., Nikou, C., Krikoni, O., and Charchanti, A. (2018, January 7–10). SIPAKMED: A new dataset for feature and image based classification of normal and pathological cervical cells in Pap smear images. Proceedings of the 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece.10.1109/ICIP.2018.8451588 ↗
16. An Iterated Local Search-Based Algorithm to Support Cell Nuclei Detection in Pap Smears Test10.1007/978-3-030-40783-4_5 ↗
17. Cervical cancer classification using convolutional neural networks and extreme learning machines10.1016/j.future.2019.09.015 ↗
18. Fine-Grained Classification of Cervical Cells Using Morphological and Appearance Based Convolutional Neural Networks10.1109/ACCESS.2019.2919390 ↗
19. Classification of Cervical Cancer Using Assembled Algorithms in Microscopic Images of Papanicolaou10.13053/rcs-139-1-10 ↗
20. Lakshmi, G.K., and Krishnaveni, K. (March, January 27). Multiple feature extraction from cervical cytology images by Gaussian mixture model. Proceedings of the 2014 World Congress on Computing and Communication Technologies, Trichirappalli, India.10.1109/WCCCT.2014.89 ↗
21. Win, K., Kitjaidure, Y., Paing, M., and Hamamoto, K. (2019, January 17–19). Cervical Cancer Detection and Classification from Pap Smear Images. Proceedings of the 2019 4th International Conference on Biomedical Imaging, Signal Processing (ICBSP ’19), Nagoya, Japan.10.1145/3366174.3366178 ↗
22. A comprehensive study on the multi-class cervical cancer diagnostic prediction on pap smear images using a fusion-based decision from ensemble deep convolutional neural network10.1016/j.tice.2020.101347 ↗
23. Pirovano, A., Almeida, L.G., and Ladjal, S. (2019). Regression Constraint for an Explainable Cervical Cancer Classifier. arXiv.
24. Automated classification of Pap smear images to detect cervical dysplasia10.1016/j.cmpb.2016.10.001 ↗
25. Machine learning for assisting cervical cancer diagnosis: An ensemble approach10.1016/j.future.2019.12.033 ↗
26. Isidoro, D., Carneiro, C., Rezende, M., Medeiros, F., Ushizima, D., and Bianchi, A. (2020, January 21–24). Automatic Classification of Cervical Cell Patches based on Non-geometric Characteristics. Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Barcelona, Spain.10.5220/0009172208450852 ↗
27. Silva, R., Araujo, F., Rezende, M., Oliveira, P., Medeiros, F., Veras, R., and Ushizima, D. (2020). Searching for cell signatures in multidimensional feature spaces. Int. J. Biomed. Eng. Technol., in press.10.1504/IJBET.2021.116988 ↗
28. Inception v3 based cervical cell classification combined with artificially extracted features10.1016/j.asoc.2020.106311 ↗
29. Shen, D., Liu, T., Peters, T.M., Staib, L.H., Essert, C., Zhou, S., Yap, P.T., and Khan, A. (2019). Synthetic Augmentation and Feature-Based Filtering for Improved Cervical Histopathology Image Classification. Medical Image Computing and Computer Assisted Intervention–MICCAI 2019, Springer International Publishing.10.1007/978-3-030-32248-9_98 ↗
30. Diniz, D.N., Souza, M.J.F., Carneiro, C.M., Ushizima, D.M., de Medeiros, F.N.S., Oliveira, P., and Bianchi, A.G.C. (2019, January 3–5). An Iterated Local Search Algorithm for Cell Nuclei Detection from Pap Smear Images. Proceedings of the 21st International Conference on Enterprise Information Systems (ICEIS), Crete, Greece.10.5220/0007718303190327 ↗
31. The irace package: Iterated racing for automatic algorithm configuration
32. Di Ruberto, C., Loddo, A., and Putzu, L. (2017). Histological image analysis by invariant descriptors. International Conference on Image Analysis and Processing, Springer.10.1007/978-3-319-68560-1_31 ↗
33. Critical evaluation of the diagnostic nomenclatures of cervical cytopathological exams used in the Brazilian Unified Health System (SUS)10.1590/S0100-72032011000300008 ↗
34. Nayar, R., and Wilbur, D.C. (2015). The Bethesda System for Reporting Cervical Cytology: Definitions, Criteria, and Explanatory Notes, Springer.10.1007/978-3-319-11074-5 ↗
35. Assessment of the validity and reproducibility of the Pap smear in Mexico: Necessity of a paradigm shift10.1016/j.arcmed.2015.05.013 ↗
36. Inter-Observer Variation in Reporting of Pap Smears
37. Atypical glandular cells: Interobserver variability according to clinical management10.1159/000489968 ↗
38. Scikit-image: Image processing in Python10.7717/peerj.453 ↗
39. Coelho, L.P. (2012). Mahotas: Open source software for scriptable computer vision. arXiv.
40. Burger, W., and Burge, M.J. (2010). Principles of Digital Image Processing: Core Algorithms, Springer Science & Business Media.10.1007/978-1-84800-195-4 ↗
41. Jähne, B. (2005). Digital Image Processing, Springer. [6th ed.].
42. Reiss, T.H. (1993). Recognizing Planar Objects Using Invariant Image Features, Springer. [1st ed.].10.1007/BFb0017553 ↗
43. Characterization of particles and particle systems
44. Textural features for image classification10.1109/TSMC.1973.4309314 ↗
45. Ojala, T., Pietikäinen, M., and Mäenpää, T. (2000). Gray scale and rotation invariant texture classification with local binary patterns. European Conference on Computer Vision, Springer.10.1007/3-540-45054-8_27 ↗
46. Hamilton, N., Pantelic, R., Hanson, K., and Teasdale, R. (2007). Fast automated cell phenotype classification. BMC Bioinform., 8.10.1186/1471-2105-8-110 ↗
47. Image analysis via the general theory of moments10.1364/JOSA.70.000920 ↗
48. Ministério da Saúde (2016). Diretrizes Brasileiras para o Rastreamento do Câncer do colo do útero, Fox Print. [2th ed.].
49. Editorial: Special Issue on Learning from Imbalanced Data Sets10.1145/1007730.1007733 ↗
50. Minority Report in Fraud Detection: Classification of Skewed Data10.1145/1007730.1007738 ↗
51. Addressing data complexity for imbalanced data sets: Analysis of SMOTE-based oversampling and evolutionary undersampling10.1007/s00500-010-0625-8 ↗
52. SMOTE: Synthetic minority over-sampling technique10.1613/jair.953 ↗
53. Huang, D.S., Zhang, X.P., and Huang, G.B. (2005). Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning. Advances in Intelligent Computing, Springer.
54. Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning
55. A decision-theoretic generalization of on-line learning and an application to boosting10.1006/jcss.1997.1504 ↗
56. Multi-class adaboost10.4310/SII.2009.v2.n3.a8 ↗
57. Breiman, L., Friedman, J., Olshen, R., and Stone, C. (1984). Classification and Regression Trees, Wadsworth & Brooks/Cole Advanced Books & Software.
58. An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression10.1080/00031305.1992.10475879 ↗
59. Hinton, G.E. (1990). Connectionist learning procedures. Machine learning, Elsevier.
60. Diagnosis of multiple cancer types by shrunken centroids of gene expression10.1073/pnas.082099299 ↗
61. Random forests10.1023/A:1010933404324 ↗
62. Spiliopoulou, M., Kruse, R., Borgelt, C., Nürnberger, A., and Gaul, W. (2006). A Ridge Classification Method for High-dimensional Observations. From Data and Information Analysis to Knowledge Engineering, Springer.10.1007/3-540-31314-1 ↗
63. Data mining: Practical machine learning tools and techniques with Java implementations10.1145/507338.507355 ↗
64. Dhurandhar, A., and Dobra, A. (2021, February 01). Insights into Cross-Validation. Available online: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.216.1606&rep=rep1&type=pdf.
65. Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer.
66. Explaining the success of adaboost and random forests as interpolating classifiers
67. An analysis of variance test for normality (complete samples)10.1093/biomet/52.3-4.591 ↗
68. Use of ranks in one-criterion variance analysis10.1080/01621459.1952.10483441 ↗