Breast cancer diagnosis based on mammary thermography and extreme learning machines

Maíra Araújo de Santana; Jessiane Mônica Silva Pereira; Fabrício Lucimar da Silva; Nigel Mendes de Lima; Felipe Nunes de Sousa; Guilherme Max Silva de Arruda; Rita de Cássia Fernandes de Lima; Washington Wagner Azevedo da Silva; Wellington Pinheiro dos Santos

doi:10.1590/2446-4740.05217

Original Article

Breast cancer diagnosis based on mammary thermography and extreme learning machines

Maíra Araújo de Santana; Jessiane Mônica Silva Pereira; Fabrício Lucimar da Silva; Nigel Mendes de Lima; Felipe Nunes de Sousa; Guilherme Max Silva de Arruda; Rita de Cássia Fernandes de Lima; Washington Wagner Azevedo da Silva; Wellington Pinheiro dos Santos

http://dx.doi.org/10.1590/2446-4740.05217 Res. Biomed. Eng., vol.34, n1, p.45-53, 2018

PDF

Downloads: 0

Abstract

Abstract: Introduction: Breast cancer is the most common cancer in women and one of the major causes of death from cancer among female around the world. The early detection and treatment are the major way to healing. The use of mammary thermography in Mastology is increasing as a complementary imaging technique to early detect lesions. Its use as a screening exam to identify breast disorders has been investigated. The aim of this study is to investigate the behavior of different classification methods while grouping the thermographic images into specific types of lesions.

Methods: To evaluate our proposal, we built classifiers based on artificial neural networks, decision trees, Bayesian classifiers, and Haralick and Zernike attributes. The image database is composed by thermographic images acquired at the University Hospital of the Federal University of Pernambuco. These images are clinically classified into the classes cyst, malignant and benign. Moments of Zernike and Haralick were used as attributes.

Results: Extreme Learning Machines (ELM) and Multilayer Perceptron networks (MLP) proved to be quite efficient classifiers for classification of breast lesions in thermographic images. Using 75% of the database for training, the maximum value obtained for accuracy was 73.38%, with a Kappa index of 0.6007. This result indicated to a sensitivity of 78% and specificity of 88%. The overall efficiency of the system was 83%.

Conclusion: ELM showed to be a promising classifier to be used in the differentiation of breast lesions in thermographic images, due to its low computational cost and robustness.

Keywords

Breast cancer early diagnosis, Thermographic images, Mammary thermography, Artificial neural networks, Extreme learning machines

References

Acharya UR, Ng EYK, Tan JH, Sree SV. Thermography based breast cancer detection using texture features and support vector machine. J Med Syst. 2012; 36(3):1503-10. PMid:20957511. http://dx.doi.org/10.1007/s10916-010-9611-z.

Aguiar PS Jr, Belfort CNS, Silva AC, Diniz PHB, Lima RCF, Conci A, Paiva AC. Detecção de regiões suspeitas de lesão na mama em imagens térmicas utilizando Spatiogram e redes neurais. Cad Pesq. 2013; 20:56-63.

American Cancer Society. Global cancer facts & figures. 3rd ed. Atlanta; 2015.

Araújo MC, Lima RC, Souza RM. Interval symbolic feature extraction for thermography breast cancer detection. Expert Syst Appl. 2014; 41(15):6728-37. http://dx.doi.org/10.1016/j.eswa.2014.04.027.

Belfort CNS, Silva AC, Paiva AC. Detecção de lesões em imagens termográficas da mama utilizando Índice de Similaridade de Jaccard e Artificial Crawlers. In: Anais do XV Workshop de Informática Médica; 2015; Recife. Porto Alegre: Sociedade Brasileira de Computação; 2015.

Bezerra LA, Oliveira MM, Rolim TL, Conci A, Santos FGS, Lyra PRM, Lima RCF. Estimation of breast tumor thermal properties using infrared images. Signal Process. 2013; 93(10):2851-63. http://dx.doi.org/10.1016/j.sigpro.2012.06.002.

Breiman L. Random forests. Mach Learn. 2001; 45(1):5-32. http://dx.doi.org/10.1023/A:1010933404324.

Cheng HD, Shi XJ, Min R, Hu LM, Cai XP, Du HN. Approaches for automated detection and classification of masses in mammograms. Pattern Recognit. 2006; 39(4):646-68. http://dx.doi.org/10.1016/j.patcog.2005.07.006.

Cheng J, Greiner R. Learning Bayesian Belief Network classifiers: algorithms and system. In: Proceedings of 14th Biennial Conference of the Canadian Society for Computacional Studies of Intelligence; 2001; Ottawa, Canada. Berlin: Springer-Verlag; 2001. p. 141-51. Vol. 2056.

Etehadtavakol M, Ng EY. Breast thermography as a potential non-contact method in the early detection of cancer: a review. J Mech Med Biol. 2013; 13(02):1330001. http://dx.doi.org/10.1142/S0219519413300019.

Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Mach Learn. 2006; 63(1):3-42. http://dx.doi.org/10.1007/s10994-006-6226-1.

Gonçalves WN, Machado BB, Bruno OM. Texture descriptor combining fractal dimension and artificial crawlers. Phys A: Stat Mech App. 2014; 395:358-70. http://dx.doi.org/10.1016/j.physa.2013.10.011.

Hankare P, Shah K, Nair D, Nair D. Breast cancer detection using thermography. Int Res J Eng Technol. 2016; 4(3):1061-4.

Haykin S. Redes neurais: princípios e prática. 2nd ed. Porto Alegre: Bookman; 1999.

Huang GB, Zhu QY, Siew CK. Extreme learning machine: theory and applications. Neurocomp. 2006; 70(1-3):489-501. http://dx.doi.org/10.1016/j.neucom.2005.12.126.

Instituto Nacional de Câncer José Alencar Gomes da Silva. Estimativa 2005/2014 [internet]. Rio de Janeiro: INCA; 2015. [cited 2017 July 24]. Available from: https://mortalidade.inca.gov.br/MortalidadeWeb/pages/Modelo02/consultar.xhtml#panelResultado

Jung Y, Hu J. A k-fold averaging cross-validation procedure. J Nonparametr Stat. 2015; 27(2):167-79. PMid:27630515. http://dx.doi.org/10.1080/10485252.2015.1010532.

Klein S, Staring M, Pluim JP. Evaluation of optimization methods for nonrigid medical image registration using mutual information and B-splines. IEEE Trans Image Process. 2007; 16(12):2879-90. PMid:18092588. http://dx.doi.org/10.1109/TIP.2007.909412.

Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977; 33(1):159-74. PMid:843571. http://dx.doi.org/10.2307/2529310.

Librelotto SR. Análise dos algoritmos de mineração J48 e a priori aplicados na detecção de indicadores da qualidade de vida e saúde. RevInt. 2014; 1(1):26-37.

Milosevic M, Jankovic D, Peulic A. Comparative analysis of breast cancer detection in mammograms and thermograms. Biomed Tech. 2015; 60(1):49-56. PMid:25720034. http://dx.doi.org/10.1515/bmt-2014-0047.

Oliveira MM. Desenvolvimento de protocolo e construção de um aparato mecânico para padronização da aquisição de imagens termográficas de mama [dissertation]. Recife: Federal University of Pernambuco; 2012.

Resmini R, Conci A, Borchartt TB, de Lima RDCF, Montenegro AA, Pantaleão CA. Diagnóstico precoce de doenças mamárias usando imagens térmicas e aprendizado de máquina. Reavi. 2012; 1(1):55-67.

Shanthi S, Bhaskaran VM. A novel approach for detecting and classifying breast cancer. Int J Intell Inf Technol. 2013; 9(1):21-39. http://dx.doi.org/10.4018/jiit.2013010102.

Silva ASV. Classificação e segmentação de termogramas de mama para triagem de pacientes residentes em regiões de poucos recursos médicos [dissertation]. Recife: Universidade Federal de Pernambuco; 2015.

Walker D, Kaczor T. Breast thermography: history, theory, and use. Is this screening tool adequate for standalone use? Nat Med J. 2012; 4(7).

Breast cancer diagnosis based on mammary thermography and extreme learning machines

Maíra Araújo de Santana; Jessiane Mônica Silva Pereira; Fabrício Lucimar da Silva; Nigel Mendes de Lima; Felipe Nunes de Sousa; Guilherme Max Silva de Arruda; Rita de Cássia Fernandes de Lima; Washington Wagner Azevedo da Silva; Wellington Pinheiro dos Santos

Abstract

Keywords

References

Links

Share

Res. Biomed. Eng.