RESUMO
Abstract Introduction Breast cancer is the first leading cause of death for women in Brazil as well as in most countries in the world. Due to the relation between the breast density and the risk of breast cancer, in medical practice, the breast density classification is merely visual and dependent on professional experience, making this task very subjective. The purpose of this paper is to investigate image features based on histograms and Haralick texture descriptors so as to separate mammographic images into categories of breast density using an Artificial Neural Network. Methods We used 307 mammographic images from the INbreast digital database, extracting histogram features and texture descriptors of all mammograms and selecting them with the K-means technique. Then, these groups of selected features were used as inputs of an Artificial Neural Network to classify the images automatically into the four categories reported by radiologists. Results An average accuracy of 92.9% was obtained in a few tests using only some of the Haralick texture descriptors. Also, the accuracy rate increased to 98.95% when texture descriptors were mixed with some features based on a histogram. Conclusion Texture descriptors have proven to be better than gray levels features at differentiating the breast densities in mammographic images. From this paper, it was possible to automate the feature selection and the classification with acceptable error rates since the extraction of the features is suitable to the characteristics of the images involving the problem.
RESUMO
OBJETIVO: Avaliar o impacto sobre o treinamento de residentes utilizando uma ferramenta computacional dedicada à avaliação do desempenho da leitura de imagens radiológicas convencionais e digitais. MATERIAIS E MÉTODOS: O treinamento foi realizado no Laboratório de Qualificação de Imagens Médicas (QualIM). Os residentes de radiologia efetuaram cerca de 1.000 leituras de um total de 60 imagens obtidas de um simulador estatístico (Alvim®) que apresenta fibras e microcalcificações de dimensões variadas. O desempenhodos residentes na detecção dessas estruturas foi avaliado por meio de parâmetros estatísticos. RESULTADOS:Os resultados da probabilidade de detectabilidade foram de 0,789 e 0,818 para os sistemas convencional e digital, respectivamente. As taxas de falso-positivos foram de 8% e 6% e os valores de verdadeiro- -positivos, de 66% e 70%, respectivamente. O valor de kappa total foi 0,553 para as leituras em negatoscópio e 0,615 em monitor. A área sob a curva ROC foi de 0,716 para leitura em filme e 0,810 para monitor.CONCLUSÃO: O treinamento proposto mostrou ser efetivo e apresentou impacto positivo sobre o desempenhodos residentes, constituindo-se em interessante ferramenta pedagógica. Os resultados sugerem que o método de treinamento baseado na leitura de simuladores pode produzir um melhor desempenho dos profissionais na interpretação das imagens mamográficas.
OBJECTIVE: The present study was aimed at evaluating the performance of residents trained in the reading of conventional and digital mammography images with a specific computational tool. MATERIALS AND METHODS: The training was accomplished in the Laboratory of Medical Images Qualification (QualIM û Laboratório de Qualificação de Imagens Médicas). Residents in radiology performed approximately 1,000 readings of a set of 60 images acquired from a statistical phantom (Alvim®) presenting microcalcifications and fibers with different sizes. The analysis of the residents' performance in the detection of these structures was based on statistical parameters. RESULTS: Values for detection probability were respectively 0.789 and 0.818 for conventional and digital systems. False-positive rates were 8% and 6%, and true-positive rates, 66% and 70% respectively. The total kappa value was 0.553 for readings on the negatoscope (hard-copy readings), and 0.615 on the monitor (soft-copy readings). The area under the ROC curve was 0.716 forhard-copy readings and 0.810 for soft-copy readings. CONCLUSION: The training has showed to be effective,with a positive impact on the residents' performance, representing an interesting educational tool. The resultsof the present study suggest that this method of training based on the reading of images from phantoms can improve the practitioners' performance in the interpretation of mammographic images.