Mammographic CAD Systems Evaluation

• Autor(a) principal: Perre, Ana C.
• Data de Publicação: 2021
• Outros Autores: Freire, Luís C.
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: https://doi.org/10.46885/roentgen.v2i2.58
• topic: Mammography; Breast Cancer; Computer-Aided Diagnosis (CAD); Fractal Dimension; Convolutional Neural Network (CNN); Transfer Learning; Support Vector Machine (SVM); Deep Learning; Mamografia; Cancro de mama; Diagnóstico Assistido por Computador (CAD); Dimensão Fractal; Redes Neuronais de Convolução (CNN); Transfer Learning; Deep Learning; Support Vector Machine (SVM)

Computer‑Aided Systems can improve the performance of breast cancer diagnosis, helping the differentiation and classification of breast benign and malignant lesions. Breast lesions are strongly correlated with their shape, therefore, in this work, firstly, were used quantitative measures based on fractal dimension, which can help characterizing the smoothness or the roughness of mammographic lesion shape, being calculated through the box‑counting method, directly from manually segmented lesions, and after applying a region growing/erosion algorithm. Then, Convolutional neural networks (CNN), which recently have been successfully used in the medical field to detect and classify pathologies in different imaging modalities, were applied in mammographic images. Since the mammographic databases have a restricted number of samples, one way to solve this problem is using a transfer learning approach, in which a CNN, previously pre-trained with a large amount of labelled non-medical data, is subsequently finetuned using a smaller dataset of mammographic images. In this study were applied three different pre-trained networks and were made an evaluation if their performance to classify lesions in mammograms is affected by the use, or not, of normalized images. Was also evaluated the performance of a support vector machine fed with features extracted from the CNN and the combined use of handcrafted features to complement the CNN-extracted features. The obtained results are encouraging and reveal that both use of fractal dimension and CNN can help to improve computer-aided diagnostic of mammographic lesions, with AUC values around 81.3%.