• 2022-05
  • 2022-04
  • 2021-03
  • 2020-08
  • 2020-07
  • 2020-03
  • 2019-11
  • 2019-10
  • 2019-09
  • 2019-08
  • 2019-07
  • br We believe that the obtained results


    We believe that the obtained results are important for special-ists interested in the study of colorectal cancer, in that they al-low for detailed analyses involving different types of features and classifiers. The indications of the best associations with histolog-ical properties are also relevant contributions. In future work, it Thapsigargin is interesting to test the method in different colour models, such as HSV and CMYK, as well as on non-normalized and color nor-malized images, in order to know the discriminative capability of the features on different conditions. Moreover, we expect to in-vestigate this approach by applying genetic algorithm or convolu-tional neural network in order to define the best associations and corresponding weights among the features. The method can also be expanded by applying both the Higuchi’s fractal dimension and different selection algorithms. Even more, we desired to apply the proposal herein to other types of images with the goal of analysing the robustness of the selected features.
    Author contribution statement
    Matheus Gonçalves Ribeiro developed the method and carried out the experiment; Leandro Alves Neves conceived and planned the method, as well as contributed to the writing and review; Marcelo Zanchetta do Nascimento presented critical feedback and helped define the research, analysis and manuscript; Guilherme Freire Roberto contributed to the experiments; Alessandro Santana Martins contributed to the experiments; Thaína Aparecida Azevedo Tosta contributed to the writing and review.
    This study was financed in part by the Coordenao de Aper-fei oamento de Pessoal de Nvel Superior (CAPES) - Finance Code 33004153073P9, National Council for Scientific and Technological Development (CNPq) - Finance Code 427114/2016-0 and the Minas Gerais State Research Foundation (FAPEMIG) - Finance Code APQ-00578-18.
    Bianconi, F., Bello-Cerezo, R., & Napoletano, P. (2017). Improved opponent color local binary patterns: An effective local image descriptor for color texture classifica-tion. Journal of Electronic Imaging, 27(1), 011002.
    Boubchir, L., Al-Maadeed, S., & Bouridane, A. (2014). Haralick feature extraction from time-frequency images for epileptic seizure detection and classification of eeg data. In Microelectronics (ICM), 2014 26th international conference on (pp. 32–35). IEEE.
    Candes, E. J., & Donoho, D. L. (2000). Curvelets: A surprisingly effective nonadaptive representation for objects with edges. Technical Report. Stanford Univ Ca Dept of Statistics.
    Chakraborty, M., Mukhopadhyay, S., Dasgupta, A., Patsa, S., Anjum, N., & Ray, J. (2016). A new approach of oral cancer detection using bilateral tex-ture features in digital infrared thermal images. In Engineering in medicine and biology society (EMBC), 2016 IEEE 38th annual international conference of the (pp. 1377–1380). IEEE.
    Charfi, S., & El Ansari, M. (2018). Computer-aided diagnosis system for colon abnor-malities detection in wireless capsule endoscopy images. Multimedia Tools and Applications, 77(3), 4047–4064.
    Charisis, V. S., & Hadjileontiadis, L. J. (2016). Potential of hybrid adaptive filtering in inflammatory lesion detection from capsule endoscopy images. World Journal of Gastroenterology, 22(39), 8641.
    Demanet, L. (2008). The curvelet organization.
    Eid, A., Charisis, V. S., Hadjileontiadis, L. J., & Sergiadis, G. D. (2013). A curvelet-based lacunarity approach for ulcer detection from wireless capsule endoscopy images. In Computer-based medical systems (CBMS), 2013 IEEE 26th international symposium on (pp. 273–278). IEEE.
    Fawcett, T. (2004). Roc graphs: Notes and practical considerations for researchers.
    Gould, H., Tobochnik, J., & Wolfgang, C. (2005). An introduction to computer simula-tion methods: Applications to physical systems ((3rd edition)). Boston, MA, USA: Addison-Wesley Longman Publishing Co., Inc.
    Hoshen, J., & Kopelman, R. (1976). Percolation and cluster distribution. i. cluster multiple labeling technique and critical concentration algorithm. Physical Review B, 14(8), 3438.
    IARC (2012). Cancer fact sheets: Colorectal cancer. Technical Report. Lyon, France:
    International Agency for Research on Cancer.
    INCA (2017). Estimate/2018 cancer incidence in Brazil. Technical Report. Rio de Janeiro, Brazil: Instituto Nacional de Câncer José Alencar Gomes da Silva. 
    John, G. H., & Langley, P. (1995). Estimating continuous distributions in Bayesian classifiers. In Proceedings of the eleventh conference on uncertainty in artificial in-telligence (pp. 338–345). Morgan Kaufmann Publishers Inc.