Submitted by Celso Magalhaes (celsomagalhaes@ufrrj.br) on 2017-07-28T16:35:42Z
No. of bitstreams: 1
2016 - Rupila Rami da Silva Goda.pdf: 2862869 bytes, checksum: 8c9a253d8a926ba04221e5ffb1311b81 (MD5) / Made available in DSpace on 2017-07-28T16:35:42Z (GMT). No. of bitstreams: 1
2016 - Rupila Rami da Silva Goda.pdf: 2862869 bytes, checksum: 8c9a253d8a926ba04221e5ffb1311b81 (MD5)
Previous issue date: 2016-08-30 / Breast cancer is the second most common cancer worldwide. According to the National Cancer Institute (INCA) in 2014 were diagnosed 52,680 new cases in Brazil, a number that corresponds to a 22% increase over the year 2013. Being responsible for approximately 39% of women's deaths cancer patients. Despite the high incidence rate, mortality from this cancer has declined since the late eighties, thanks to advances in research on methods for early diagnosis. However, correctly diagnosing cancer is a complex and difficult process as a result of the different variables involved. For an accurate diagnosis, a lot of experience and especially it is required, that the classification of clinical staging of tumor (cancer stage) is correct. The conditions used traditional classification systems are complex and often offer limitations. As is the case of mammography technique, widely used, it is not as effective for women with dense breasts, surgically altered, or under 40 years. Thus, it becomes necessary to develop integrated systems that combined with the professionals in the field experience, allows performing accurate diagnosis in detecting breast cancer. The objective of this study is to apply the technique SVM (Support Vector Machine), so as to assist in the diagnostic interpretation of microcalcifications detected on screening mammography. The data set used consisted of 961 samples of mammograms, obtained from the Radiology Institute of the University of Erlangen Nuremberg. In this set we have information on the age of the patient, BI-RADS (Breast Imaging Reporting and Data System), shape, mass, density and severity (benign | malignant) of microcalcifications. The SVM was developed implemented using the R software (R Development Core Team; http: // www.R-project.org/). The data were divided into two groups: the training set consisting of 80% of the samples of mammographic, used to estimate the model parameters and the independent test set, with 20% of the remaining samples, used to measure the performance of SVM . To evaluate the performance of proposed computational model we used the value of the Total Precision or Accuracy (ACC), sensitivity (S) and specificity (E). The results presented by SVM in identifying malignant lesions in patients with calcifications remained between 72.7% and 100%, which shows that they achieved a satisfactory level in relation to other literatures applied / O c?ncer de mama ? a segunda neoplasia mais frequente no mundo. Segundo dados do Instituto Nacional de C?ncer (INCA), no ano de 2014 foram diagnosticados 52.680 novos casos no Brasil, n?mero este que corresponde a um aumento de 22% em rela??o ao ano de 2013. Sendo respons?vel por aproximadamente 39% dos ?bitos das mulheres portadores de c?ncer. Apesar da elevada taxa de incid?ncia, a mortalidade causada por esta neoplasia tem diminu?do desde o final dos anos oitenta, gra?as ao avan?o das pesquisas em m?todos para o diagn?stico precoce. No entanto, diagnosticar corretamente o c?ncer ? um processo complexo e muito dif?cil em consequ?ncia das diversas vari?veis envolvidas. Para um diagn?stico preciso, exige-se muita experi?ncia e, principalmente, que a classifica??o do estadiamento cl?nico do tumor (est?gio do c?ncer) esteja correta. Os tradicionais sistemas de classifica??o de patologias utilizados s?o complexos e em muitas vezes oferecem limita??es. Como ? o caso da t?cnica de mamografia, que amplamente utilizada, n?o ? t?o eficaz para mulheres com mamas densas, cirurgicamente alteradas ou com menos de 40 anos. Desta forma, torna-se necess?rio o desenvolvimento de sistemas integrados que combinados com a experi?ncia dos profissionais da ?rea, possibilite realizar o diagn?stico preciso na detec??o do c?ncer de mama. O objetivo do presente trabalho ? aplicar a t?cnica SVM (M?quina de Vetor de Suporte), de sorte a auxiliar na interpreta??o diagn?stica das microcalcifica??es detectadas em mamografia de rastreamento. O conjunto de dados utilizado consistiu de 961 amostras de exames mamogr?ficos, obtidos junto ao Instituto de Radiologia da Universidade de Erlangen- Nuremberg. Neste conjunto possu?mos informa??es referentes a idade da paciente, classifica??o BI-RADS ( Breast Imaging Reporting and Data System), forma, massa, densidade e severidade (benigno|maligno) das microcalcifica??o. A SVM desenvolvida foi implementada utilizando-se o software R (R Development Core Team; http:// www.R-project.org/ ) . Os dados foram divididos em dois grupos: o conjunto de treinamento composto por 80% das amostras de exames mamogr?ficos, usado para estimar os par?metros do modelo e o conjunto de teste independente, com 20% das amostras restantes, utilizado para mensurar a performance da SVM. Para avaliar o desempenho do modelo computacional proposto foram utilizados o valor da Precis?o Total ou Acur?cia (ACC), Sensibilidade (S) e Especificidade(E). Os resultados apresentados pela SVM na identifica??o das les?es malignas em pacientes portadores de microcalcifica??es se mantiveram entre 72,7% e 100% o que demonstram que os mesmos alcan?aram um grau satisfat?rio em rela??o com outras literaturas aplicadas
| Identifer | oai:union.ndltd.org:IBICT/oai:localhost:jspui/1930 |
| Date | 30 August 2016 |
| Creators | G?da, R?pila Rami da Silva |
| Contributors | Silva, Robson Mariano da, Delgado, Angel Ramom Sanchez, Oliveira, Raquel Lima |
| Publisher | Universidade Federal Rural do Rio de Janeiro, Programa de P?s-Gradua??o em Modelagem Matem?tica e Computacional, UFRRJ, Brasil, Instituto de Ci?ncias Exatas |
| Source Sets | IBICT Brazilian ETDs |
| Language | Portuguese |
| Detected Language | English |
| Type | info:eu-repo/semantics/publishedVersion, info:eu-repo/semantics/masterThesis |
| Format | application/pdf |
| Source | reponame:Biblioteca Digital de Teses e Dissertações da UFRRJ, instname:Universidade Federal Rural do Rio de Janeiro, instacron:UFRRJ |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | ABCMED, 2013. Bi?psia. Dispon?vel em: <http://www.abc.med.br/p/exames-e-procedimentos/513419/biopsia-o-que-e-quando-e-indicada-quais-os-tipos-quais-as-possiveis-complicacoes-como-ela-e-realizada.htm>. Aguillar VLN, Bauab SP. Rastreamento mamogr?fico para detec??o precoce do c?ncer de mama. Revista brasileira de mastologia 2003. Andre, T.; Rangayyan, R. M. Classification of tumors and masses in mammograms using neural networks with shape and texture features. 25th Annual International Conference of the IEEE Transactions on Engineering in Medicine and Biology Society. Almeida F. F. M. (2007). Relat?rio t?cnico: Support Vector Machine. Universidade Federal de Campina Grande, Centro de Ci?ncia e Tecnologia. Ara?jo, S. D. T. de. Mortalidade por c?ncer de mama, com idade igual ou superior a 50 anos, estado de S?o Paulo 1979-1997. Tese de mestrado apresentada ? Universidade de S?o Paulo, Dezembro 2000. Braz J?nior, G.; Silva, E. C.; Paiva, A. C.; Silva, A. C.; Gattass, M. Breast Tissues Mammograms Images Classification using Moran s Index, Geary s Coefficient and SVM . In: International Conference on Neural Information Processing, 2007, Kitakyushu. Lecture Notes in Computer Science, LNCS, 2007. Campos, L. F. A., Silva, A. C., Barros, A. K., 2007. Independent Component Analysis and Neural Networks Applied for Classification of Malignant, Benign and Normal Tissue in Digital Mammography . Methods of Information in Medicine, 2007. Chang, C. E Lin, C., 2003. Libsvm ? A Library for Support Vector Machines. Costa, D. D., Barros, A. K., E Silva, A. C., 2007. Independent Component Analysis in Breast Tissues Mammograms Images Classification using LDA and SVM . Information Technology Applications in Biomedicine - ITAB2007 - Tokyo. Conference on 6th International Special Topic . Cristianini, N. E Shawe-Taylor, J. , 2000. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods . Cambridge University Press. C. J. C. Burges. A tutorial on support vector machines for pattern recognition. Know- ledge Discovery and Data Mining, 2(2):1?43, 1998. Chaves, A. C. F., 2006. Extra??o de Regras Fuzzy para M?quinas de Vetor de Suporte (SVM) para Classifica??o em M?ltiplas Classes . PhD Thesis. Pontif?cia Universidade Cat?lica do Rio de Janeiro. DDSM, 2001. The Digital Database for Screening Mammography , Michael Heath, Kevin 53 Bowyer, Daniel Kopans, Richard Moore and W. Philip Kegelmeyer, in Proceedings of the Fifth International Workshop on Digital Mammography, M.J. Yaffe, ed., Medical Physics Publishing. Dispon?vel em http://www.csie.ntu.edu.tw/~cjlin/libsvm/. Fenton, J. J., Taplin, S. H., Carney, P. A., Abraham, L., Sickles, E. A., D'orsi, C., Berns, E. A., Cutter, G., Hendrick, R. E., Barlow, W. E. , ELMORE, J. G., 2007. Influence of Computer-Aided Detection on Performance of Screening Mammography . Breast Diseases: A Year Book Quarterly. Ferrari, R. J.; Rangayan, R. M., Desautels, J. E. L.; Freire, A. F. Analysis of asymmetry in mammograms via directional filtering with gaborwavelets. IEEE Transactions on Medical Imaging, v. 20 , September 2001. Freer, T. W. E Ulissey, M. J., 2001. Screening Mammography with Computer-Aided Detection: Prospective Study of 12,860 Patients in a Community Breast Center . Radiology. Giger, M. L, 2000. Computer-aided diagnosis of breast lesions in medical images. Computing in Science & Engineering. Goldberd, D., 1989. Genetic Algorithms in Search, Optimization, and Machine Learning. EUA: Addison-Wesley. Gon?alves A. R. M?quinas de Vetores suporte, 2010. Gonzalez, R. C. E Woods, R. E., 2007. Digital Image Processing . 3rd Edition. Prentice Hal Gunn S. R. (1998). Support Vector Machine for Classification and Regression. Faculty of Engineering, Science and Mathematics School of Electronics and Computer Science. Halkiotis, S.; Mantas, J.; Botsis, T. Computer-aided detection of clustered microcalcifications in digital mammograms. Special Issue: Proceedings of the fifth European Systems Science Congress, V. 2, October 2002. H. Nassif, D. Page, M. Ayvaci, J. Shavlik, and E. S. Burnside. Uncovering age-specific invasive and dcis breast cancer rules using inductive logic programming . Proceedings of 2010 ACM International Health Informatics Symposium (IHI 2010), ACM Digital Library, 2010. Hansel, D . Fundamentos da Patologia, C?ncer de Mama, p?g. 553 - 557. Rio de Janeiro Guanabara Koogan, 2007. Haykin, S. e Engel, P. M., 2001. Redes Neurais: Principios e Pratica . Bookman. Heath, M., Bowyer, K., Kopans, D., Moore, R., Kegelmeyer, W.P., 1998. Current Status of the Digital Database for Screening Mammography. Digital Mammography . iCad (2008). iCad Solutions. Dispon?vel em: http://www.icadmed.com/. 54 Hermann, G.; Janus, C.; Schwartz, I S.; Krivisky, B.; Bier, S.; Rabinowitz, J.G. Nonpalpable breast lesions: Accuracy of prebiopsy mammographic diagnosis, 1987. INCA, 2015. Instituto Nacional do C?ncer. Estimativas 2008: Incid?ncia de C?ncer no Brasil . Available at http://www.inca.gov.br. Instituto Nacional de C?ncer (Brasil). Estimativas 2010. Incid?ncia de c?ncer no Brasil. Rio de Janeiro: INCA; 2009. INTEL, 2008. Opencv, Open Computer Vision Library . Intel Technology and Research. Dispon?vel em http://sourceforge.net/projects/opencvlibrary/. J. A. Baranauskas and M. C. Monard. Reviewing some machine learning concepts and methods. Technical Report 102, Instituto de Ci?ncias Matem?ticas e de Computa??o, Universidade de S?o Paulo, S?o Carlos. Dispon?vel em: ftp://ftp.icmc.usp. br/pub/BIBLIOTECA/rel_tec/RT_102.ps.zip, Fevereiro 2000. Jacobson, H. G.; Edeiken, J. Biopsy of occult breast lesions: Analysis of 1261 abnormalities. J. Am. Math. Assoc., 1990. J. L. Castro, L. D. Flores-Hidalgo, C. J. Mantas, and J. M. Puche. Extraction of fuzzy rules from support vector machines. Fuzzy Sets and Systems archive, 2007. Jain, A. K., Duin, R. P. W., Mao , J., 2000. Statistical pattern recognition: A review . IEEE Transactions on Pattern Analysis e Machine Intelligence. Karatzoglou, A., Smola, A., Hornik, K., & Karatzoglou, M. A. (2016). Package ?kernlab?.R Core Team (2014). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. Kestelman FP, Sousa GA, Thuler LC, Martins G, Freitas VAR, Canella EO. Breast Imaging Reporting and Data System - BI-RADS?: valor preditivo positivo das Categorias 3, 4 e 5. Revis?o sistem?tica da literatura. Radiologia brasileira 2007. Kopans, DB. Imagem da mama. 2? ed. Rio de Janeiro: Revinter Medsi; 2000. Liberman L, Abramson AF, Squires FB, Glassman JR, Morris EA, Dershaw DD. The Breast imaging report and data system: positive predict value of mammographic features and final assement categories. AJR 1998. Lorena A. C. e Carvalho, A. C. P. L. F. (2007) Uma Introdu??o ?s Support Vector Machines. M. A. Hearst, B. Sch?lkopf, S. Dumais, E. Osuna, and J. Platt. Trends and controversies - support vector machines. IEEE Intelligent System , 1998. M. C. Monard and J. A. Baranauskas. Conceitos de aprendizado de m?quina. In S. O. Rezende, editor, Sistemas Inteligentes - Fundamentos e Aplica??es. Editora Manole, 2003. 55 M. C. P. Souto, A. C. Lorena, A. C. B. Delbem, and A. C. P. L. F. Carvalho. T?cnicas de Aprendizado de M?quina para problemas de Biologia Molecular, pages 103?152. Minicursos de Intelig?ncia Artificial, Jornada de Atualiza??o Cient?fica em Intelig?ncia Artificial, XXIII Congresso da Sociedade Brasileira de Computa??o, 2003. Martins, L. O., 2007. Detec??o de Massas em Imagens Mamogr?ficas Atrav?s do Algoritmo Growing Neural Gas e da Fun??o K De Ripley. Disserta??o de mestrado. Universidade Federal do Maranh?o, Departamento de Engenharia de Eletricidade, Programa de P?s-Gradua??o em Engenharia de Eletricidade. S?o Lu?s, 2007. Minist?rio da Sa?de, 2002 . Falando Sobre C?ncer de Mama. Instituto Nacional de C?ncer, Coordena??o de Preven??o e Vigil?ncia. Rio de Janeiro. Minist?rio da Sa?de (BR). Pol?tica Nacional de C?ncer de Mama. Bras?lia: Minist?rio da Sa?de; 2008. Moayedi, F., Boostani, R. Azimifar, Z. Katebi, S., 2007. A Support Vector Based Fuzzy Neural Network Approach for Mass Classification in 81 Mammography . Digital Signal Processing, 2007. 15th International Conference. Mudigonda, N. R; Rangayyan, R. M; Desautels, J. E. L. Detection of the Breast Masses in Mammograms by Density Slicing and Texture Flow-Field Analysis. IEEE Transaction on Medical Imaging, 2001. Obenauer, S.; Hermann, K. P.; Grabbe, E. Applicatios and and literature review of the BI-RADS classification. European Radiology, 2005. Osta, H., Qahwaji, R. E Ipson, S., 2008. Wavelet-based Feature Extraction and Classification for Mammogram Images using RBF and SVM. In Proceedings of International Conference on Visualization, Imaging, and Image Processing (VIIP). Palma de Mallorca, Spain. Padwal, M., 2007. Elements of breasting imaging basics . Disponivel em: http://www.gehealthcare.com/usen/ultrasound/education/products/cme_breast.html. Parkin DM, Bray FI, Devesa SS. Cancer burden in the year 2000. The global picture. Eur J Cancer. 2001 Oct. Queiroz RY, Hummel AC. O valor das microcalcifica??es agrupadas no diagn?stico precoce do c?ncer de mama. Revista brasileira de cancerologia 1995. R. Herbrich. Learning Kernel Classifiers: Theory and Algorithms. MIT Press, 2001. R. Woods, L. Oliphant, K. Shinki, D. Page, J. Shavlik, and E. Burnside. Validation of results from knowledge discovery: Mass density as a predictor of breast cancer . J Digit Imaging, 2009. Ryan Woods and Elizabeth Burnside. The mammographic density of a mass is a significant predictor of breast cancer . Radiology, USA, 2010. 56 S. Haykin. Neural Networks - A Compreensive Foundation. Prentice-Hall, New Jersey, 2nd edition, 1999. Sampat, M. P., Markey, M. K., Bovik, A. C., 2005. Computer-Aided Detection and Diagnosis in Mammography . Handbook of Image and V?deo Processing. Santos, V. T. Segmenta??o de imagens mamogr?ficas para detec??o de n?dulos em mamas densas. Tese de mestrado apresentada na Universidade de S?o Paulo, novembro de 2002. Shanthu S, Bhaskaran AV. A Novel Approach for detecting and Classifying Breast Cancer. In: International Journal of Intelligent Information Technologies, 2013. Shen, L.; Rangayyan, R. M.; Desautels, J. E. L.; Frere, A. F. Application of shape analysis to mammographic calcifications . IEEE Transactions on Medical Imaging v. 13. Sickles EA. Breast calcifications: mammographic evaluation. Radiology 1986. Sousa, J. R., Silva, A. C., Paiva, A. C., 2007. Lung Structures Classification Using 3D Geometric Measurements and SVM . In: 12th Iberoamerican Congress on Pattern Recognition - CIARP 2007, Valparaiso. Lecture Notes Computer Science - LNCS. Berlin: Springer-Verla. T. Mitchell. Machine Learning. McGraw Hill, 1997. T. Ayer, O. Alagoz, J. Chhatwal, J. W. Shavlik, C. E. J. Kahn, and E. S. Burnside. Breast cancer risk estimation with artificial neural networks revisited: discrimination and calibration . Vol. Cancer. 2010. Tse GM, Tan PH, Cheung HS, Chu WCW, Lam WWM. Intermediate to highly suspicious calcification in breast lesions: a radio-pathologic correlation. Breast Cancer Res Treat 2008. V. N. Vapnik and A. Y. Chervonenkis. On the uniform convergence of relative fre- quencies of events to their probabilities. Theory of Probability and its Applications, 1971. V. N. Vapnik. Statistical Learning Theory. John Wiley and Sons, 1998. Vianna AD, Marchiori E. Calcifica??es malignas da mama: correla??o mamografia anatomia patol?gica. Radiologia brasileira 2002. Zhang, P. e Kumar, K., 2006. Analyzing Feature Significance from Various Systems for Mass Diagnosis . Proceedings of the International Conference 83 on Computational Inteligence for Modelling Control and Automation and International Conference on Intelligent Agents Web Technologies and International Commerce. Zurrida, S. et al. A dissec??o axilar no carcinoma de mama. In: VERONESI, U. et al. Mastologia Oncol?gica . Rio de Janeiro: MEDSI, 2002. Yu, S.; Guan, L. A cad system for the automatic detection of clustered microcalcifications in digitized mammogram films. IEEE Transaction on the Medical Imaging , v 20. |
Page generated in 0.0027 seconds