Detec¸c˜ao de cˆancer em tecidos animais: uma abordagem de wavelet
Conteúdo do artigo principal
Resumo
Considerando que o biospeckle laser ´e um fenˆomeno interferom´etrico dinˆamico adotado para monitorar mudan¸cas em amostras biol´ogicas e que a varia¸c˜ao temporal do padr˜ao do speckle depende do n´ıvel de atividade da superf´ıcie da amostra iluminada, este trabalho prop˜oe analisar a matriz de mistura ao longo do tempo. Utilizando a transformada bidimensional de ondaletas, s˜ao obtidos v´arios resumos descritivos variando no tempo a partir da matriz de mistura. Esses descritores s˜ao assinaturas de regularidade e fractalidade da imagem, ´uteis na classifica¸c˜ao dos tecidos. Neste trabalho propomos verificar o comportamento do fluxo de energia entre as escalas, considerando um conjunto de 128 imagens obtidas variando no tempo para classificar ´areas de cˆancer em imagens de um carcinoma mam´ario anapl´asico em uma cadela e em imagens de cˆancer de pele em um gato. Os declives espectrais variando no tempo aplicados na an´alise de dissimilaridades dos tecidos permitiram observar que os descritores da ´area saud´avel tˆem valores mais baixos do que os descritores da ´area de cˆancer, resultando em expoentes de Hurst maiores. Ao usar as propriedades de dimensionamento de imagens de tecido, capturamos informa¸c˜oes contidas na imagens dos tecidos que n˜ao s˜ao utilizadas quando se considera apenas a an´alise morfol´ogica tradicional.
Detalhes do artigo
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Referências
BRAGA,R.A., RABELO,G.F., BARRETO,F.M., PEREIRA,J., MURAMATSU,M. in: H.J. Rabal, R.A. Braga (Eds.),Dynamic laser speckle and applications, CRC/Taylor & Francis, Boca Raton, 2008.
BRAGA, R. A., CARDOSO, R.R., BEZERRA, P.S., WOUTERS,F., SAMPAIO,G.R. and VARASCHIM, M.S. Biospeckle numerical values over spectral image mapsof activity. Optics Communications, v.285, p.553-561, 2012.
BURDETT, C. J., et al. Nonlinear indicators of malignancy. Biomedical Image Processing and Biomedical Visualization. Vol. 1905. International Society for Opticsand Photonics, 1993.
CHENG, C. F. Speckle intensity correlation in the diffraction region near rough surfaces and simulational experiments for extraction of surface parameters.Europhysics letters, v. 65, p.779, 2004.
DAINTY, J., ENNOS, A., FRANC ̧ON, M., GOODMAN, J., McKECHNIE, T.,PARRY, G., and GOODMAN, J. Statistical properties of laser speckle patterns,in [Laser Speckle and Related Phenomena].Topics in Applied Physicsv.9, p.9-75, Springer Berlin / Heidelberg, 1975.
FLANDRIN, F.. Wavelet analysis and synthesis of fractional Brownian motion. IEEE Transactions on Information Theory, v.38, p.910-917, 1992.
GEORGE, N., Experiments on the space and wavelength dependenceof speckle.Applied physics. A, Materials science & processing, v.7, n.3, p.157, 1975.
JEON, S., NICOLIS, O. and VIDAKOVIC, B., Mammogram Diagnostics via2-D Complex Wavelet-based Self-similarity Measures.S ̃ao Paulo Journal of Mathematical Sciences, v.8, n.2, p.264-284, 2014.
KANG, M.Non-decimated Wavelet Transform is Statistical Assessment of Scaling: Theory and Applications. Thesis (Ph.D.), Georgia Institute of Technology. 2016,URL https:// smartech.gatech.edu.
KURACHI, C., VOLLET, J.D.; BAGNATO, V.S.; in V,S. Bagnato (Ed) , Detecção óptica no diagnóstico. Livraria da Física, São Paulo, 2008.
MARQUES, R. A., SÁFADI,T. Temporal Analysis of Hurst Exponents on Interferometric Images of a Mammary Carcinoma, Brazilian Journal of Biometrics, v.38, n.3, p.324-342, 2020.
MORETTIN, P.A.,Ondas e Ondaletas.Da análise de Fourier `a Análise de Séries Temporais Edusp-Editora da Universidade de São Paulo, 2004. 320p.
NAMAZI, H. and KIMINEZHADMALAIE, M., Diagnosis of Lung Cancer by Fractal Analysis of Damage DNA.Computacional and Mathematical Methods in medicine, 2015.
NICOLIS, O., RAMIREZ-COBO, P. and VIDAKOVIC, B., 2-D wavelet-basedspectra with applications. Computational Statistics and Data Analysis, v.55, p.738-751, 2011.
RAMIREZ-COBO, P. et al., A wavelet-based spectral method for extracting self-similarity measures in time-varying two-dimensional rainfall maps. Journal of TimeSeries, v.32, p.351-363, 2011.
S ́AFADI,T., KANG, M. , LEITE, I.C.C. and VIDAKOVIC, B., Wavelet-based spectral descriptors on detection of damage in sunflower seeds. International Journalof Wavelets, Multiresolution and Information Processing, v.14, n.4, p.1650027 ,2016.
TONER, B. C., A Longitudinal Study of Mammograms Utilizing the Automated Wavelet Transform Modulus Maxima Method. Electronic Theses and Dissertations. 3123, 2019.
RICHARDSON, W. B., Applying wavelets to mammograms. IEEE Engineering in Medicine and Biology Magazinev.14, n.5, p.551-560, 1995.
VEITCH, D; ABRY, P. A wavelet-based joint estimator of the parameters of long-range dependence. [IEEE Transactions on Information Theory], v.45, p.878-97,1999.
VIDAKOVIC, B. Statistical Modeling by Wavelets. John Wiley and Sons. New York,1999.