Segmentação de Núcleos Celulares Baseada em Agrupamento e Características de Forma

• Samuel P. B. D. Lélis UFPI
• Lucas B. M. de Souza UFPI
• Romuere R. V. Silva UFPI

DOI: https://doi.org/10.5753/enucompi.2021.17751

Abstract

Among the types of cancer, cervical cancer is the fourth most common worldwide among women. Diagnosis is made mainly through the pap smear, which offers a good detection rate in the primary stages of the disease, offering more chances of cure. Thus, automated results evaluation methods obtained a very valuable tool in combating this disease. This work evaluates the parameters for the combination of nuclei in pap smear images in the CRIC database. With the variation and study of the parameters we obtained an average data result of 0.7023 with the best combination of parameters.

References

Bandyopadhyay, H. and Nasipuri, M. (2020). Segmentation of pap smear images for cervical cancer detection. In 2020 IEEE Calcutta Conference (CALCON), pages 30–33. IEEE.

Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on pattern analysis and machine intelligence, (6):679–698.

Cheng, Y. (1995). Mean shift, mode seeking, and clustering. IEEE transactions on pattern analysis and machine intelligence, 17(8):790–799.

Comaniciu, D. and Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. IEEE Transactions on pattern analysis and machine intelligence, 24(5):603– 619.

Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3):273– 297.

Ho, T. K. (1995). Random decision forests. In Proceedings of 3rd international conference on document analysis and recognition, volume 1, pages 278–282. IEEE.

Jantzen, J., Norup, J., Dounias, G., and Bjerregaard, B. (2005a). Pap-smear benchmark data for pattern classication. Nature inspired Smart Information Systems (NiSIS 2005), pages 1–9.

Jantzen, J., Norup, J., Dounias, G., and Bjerregaard, B. (2005b). Pap-smear benchmark data for pattern classication. Nature inspired Smart Information Systems (NiSIS 2005), pages 1–9.

Redmon, J. and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.

Rezende, M. T., Silva, R., Tobias, A. H. G., Oliveira, P., Sombra de Medeiros, F. N., Ushizima, D., Carneiro, C. M., and Bianchi, A. G. C. (2020). Cric cervix classication.

Silva, R. R., Araujo, F. H., Ushizima, D. M., Bianchi, A. G., Carneiro, C. M., and Medeiros, F. N. (2019). Radial feature descriptors for cell classication and recommendation. Journal of Visual Communication and Image Representation, 62:105–116.

Talukdar, J., Nath, C. K., and Talukdar, P. (2013). Fuzzy clustering based image segmentation of pap smear images of cervical cancer cell using fcm algorithm. markers, 3(1):460–2.

Wang, P., Wang, L., Li, Y., Song, Q., Lv, S., and Hu, X. (2019). Automatic cell nuclei segmentation and classication of cervical pap smear images. Biomedical Signal Processing and Control, 48:93–103.

WHO (2021). Cervical cancer. https://www.who.int/health-topics/cervical-cancer\#tab=tab\_1. Accessed on 2021-06-11.

William, W., Ware, A., Basaza-Ejiri, A. H., and Obungoloch, J. (2019). Cervical cancer classication from pap-smears using an enhanced fuzzy c-means algorithm. Informatics in Medicine Unlocked, 14:23–33.

Xiang, Y., Sun, W., Pan, C., Yan, M., Yin, Z., and Liang, Y. (2020). A novel automationassisted cervical cancer reading method based on convolutional neural network. Biocybernetics and Biomedical Engineering, 40(2):611–623.

Zhao, M., Wang, H., Han, Y., Wang, X., Dai, H.-N., Sun, X., Zhang, J., and Pedersen, M. (2021). Seens: Nuclei segmentation in pap smear images with selective edge enhancement. Future Generation Computer Systems, 114:185–194.