Detecção de agrupamento de microcalcificações em imagens de mamogramas digitalizados usando a transformada wavelet complexa de árvore dupla

• Ano de defesa: 2016
• Autor(a) principal: Sá, Amandia de Oliveira
• Orientador(a): Ferrari, Ricardo José
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de São Carlos; Câmpus São Carlos
• Programa de Pós-Graduação: Programa de Pós-Graduação em Ciência da Computação - PPGCC
• Palavras-chave em Português: Detecção de agrupamentos de microcalcificações; DT-CWT; Câncer de mama; Mamograma
• Palavras-chave em Inglês: Detection of clustered microcalcifications; DT-CWT; Breast cancer; Mammogram
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA
• Link de acesso: https://repositorio.ufscar.br/handle/20.500.14289/7845

Mammography is considered the “gold standard"in the early detection of breast cancer, being this disease one of the greatest health problems of women worldwide. Clustered microcalcifications detected on mammograms are very important findings in asymptomatic patients with early breast cancer and may be considered one of the first signs of malignancy. However, due to the small size of these structures, associated with the visual fatigue of radiologists resulting from the analysis of a large volume of images, clinical studies indicate that from 10 to 30% of microcalcifications presented in mammograms are lost during diagnosis. Within this scenario, this master thesis aims to develop an automatic system for the detection of clustered microcalcifications in digitized mammography images. To solve this problem, we use the transformed dua-three complex wavelet to detect the microcalsifications since this technique has some important characteristics for the signal analysis, for instance, good directional selectivity, approximate shift invariance and it provides both information - magnitude and phase. After the detection of isolated microcalcifications, a post-processing step is used to automatically demarcate regions containing clusters of microcalcifications. Furthermore, three techniques were investigated for the analysis of each clustered detection in order to identify false-positive clusters, such as: the Hessian matrix, the groups exclusion and the gray level co-occurrence matrix technique and SVM classifiers. For the development and testing of the algorithms one digitized mammogram database were used. The analysis of the results were performed by using ROC and FROC curves. The method achieved good results when compared to the mark made by experts.