Image Processing Methods for Oral Macules and Spots Segmentation
Oral cancers are the 16th most common type of cancer in the world and present a high mortality rate. This is mainly because they are frequently discovered in an advanced stage due to the lack of specialized professionals. Some clinical characteristics such as borders and symmetry can aid in cancer diagnosis, and therefore the segmentation of the lesions is important. In light of this, this work aimed to present and evaluate different analytic methods to perform automatic segmentation of oral macules and spots from 21 clinical images. From the tested methods, the one with the best result reached an accuracy of 84.9%, a precision of 70.1%, a recall of 75.3%, and an f1-score of 60.8%, which are similar outcomes of published works that used artificial intelligence.
dos Santos, E. S., de M S Veras, R., R T Aires, K., M B F Portela, H., Braz Junior, G., Santos, J. D., and Tavares, J. M. R. (2022). Semi-automatic segmentation of skin lesions based on superpixels and hybrid texture information. Medical Image Analysis, 77:102363.
Gomes, R. F. T., Schmith, J., Figueiredo, R. M. d., Freitas, S. A., Machado, G. N., Romanini, J., and Carrard, V. C. (2023a). Use of artificial intelligence in the classification of elementary oral lesions from clinical images. International Journal of Environmental Research and Public Health, 20(5).
Gomes, R. F. T., Schuch, L. F., Martins, M. D., Honório, E. F., de Figueiredo, R. M., Schmith, J., Machado, G. N., and Carrard, V. C. (2023b). Use of deep neural networks in the detection and automated classification of lesions using clinical images in ophthalmology, dermatology, and oral medicine—a systematic review. Journal of Digital Imaging.
Liu, Y.-J., Yu, C.-C., Yu, M.-J., and He, Y. (2016). Manifold slic: A fast method to compute content-sensitive superpixels. pages 651–659.
Mahmood, H., Shaban, M., Rajpoot, N., and Khurram, S. A. (2021). Artificial inteligence-based methods in head and neck cancer diagnosis: an overview. British Journal of Cancer, 124:1934–1940.
Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 9(1):62–66.
Sarode, G., Maniyar, N., Sarode, S. C., Jafer, M., Patil, S., and Awan, K. H. (2020). Epidemiologic aspects of oral cancer. Disease-a-Month, 66(12):100988. Oral Health Special Issue.
Song, B., Li, S., Sunny, S., Gurushanth, K., Mendonca, P., Mukhia, N., Patrick, S., Peterson, T., Gurudath, S., Raghavan, S., Tsusennaro, I., Leivon, S. T., Kolur, T., Shetty, V., Bushan, V., Ramesh, R., Pillai, V., Wilder-Smith, P., Suresh, A., Kuriakose, M. A., Birur, P., and Liang, R. (2022). Exploring uncertainty measures in convolutional neural network for semantic segmentation of oral cancer images. Journal of Biomedical Optics, 27(11):115001.
Sung, H., Ferlay, J., Siegel, R. L., Laversanne, M., Soerjomataram, I., Jemal, A., and Bray, F. (2021). Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 71(3):209–249.
Tanriver, G., Soluk Tekkesin, M., and Ergen, O. (2021). Automated detection and classification of oral lesions using deep learning to detect oral potentially malignant disorders. Cancers, 13(11).
TelessáudeRS (2022). Quem somos.
Thomas, B., Kumar, V., and Saini, S. (2013). Texture analysis based segmentation and classification of oral cancer lesions in color images using ann. In 2013 IEEE International Conference on Signal Processing, Computing and Control (ISPCC), pages 1–5.
Welikala, R. A., Remagnino, P., Lim, J. H., Chan, C. S., Rajendran, S., Kallarakkal, T. G., Zain, R. B., Jayasinghe, R. D., Rimal, J., Kerr, A. R., Amtha, R., Patil, K., Tilakaratne, W. M., Gibson, J., Cheong, S. C., and Barman, S. A. (2020). Automated detection and classification of oral lesions using deep learning for early detection of oral cancer. IEEE Access, 8:132677–132693.
World Medical Association (2013). World Medical Association Declaration of Helsinki: Ethical Principles for Medical Research Involving Human Subjects. JAMA, 310(20):2191–2194.