Image Similarity to Improve the Classification of Breast Cancer Images

Abstract

Techniques in image similarity can be used to improve the classification of breast cancer images. Breast cancer images in the mammogram modality have an abundance of non-cancerous structures that are similar to cancer, which make classification of images as containing cancer especially difficult to work with. Only the cancerous part of the image is relevant, so the techniques must learn to recognize cancer in noisy mammograms and extract features from that cancer to appropriately classify images. There are also many types or classes of cancer with different characteristics over which the system must work. Mammograms come in sets of four, two images of each breast, which enables comparison of the left and right breast images to help determine relevant features and remove irrelevant features. In this work, image feature clustering is done to reduce the noise and the feature space, and the results are used in a distance function that uses a learned threshold in order to produce a classification. The threshold parameter of the distance function is learned simultaneously with the underlying clustering and then integrated to produce an agglomeration that is relevant to the images. This technique can diagnose breast cancer more accurately than commercial systems and other published results

Positive predictive values by mammographic density and screening mode in the Norwegian Breast Cancer Screening Program

“…Image Similarity to Improve the Classification of Breast Cancer Images. Algorithms 2009;2(4): 1503-1525)(138).The 5 th edition of the BI-RADS density classification scale has gradually been implemented in the program from 2016 onward. The 5 th edition of the BI-RADS density classification includes four categories; a) almost entirely fatty, b) scattered areas of fibroglandular density, c) heterogeneously dense, which can obscure small masses, and d) extremely dense, which lowers the sensitivity of mammography (93).…”

Seleção supervisionada de características por ranking para processar consultas por similaridade em imagens médicas

“…A Figura 2.4 mostra algumas amostras do banco de filtros gerados pela Equação 2.2. O Banco de Filtros de Gabor tem sido usado em muitas aplicações na área médica, em (Buciu and Gacsadi, 2009) Gabor é usado para a detecção de tumores malignos e benignos em mamografias, em (Tahmoush, 2009) é utilizada para a detecção de câncer de mama. Além disso, os filtros de Gabor também são usados em aplicações de reconhecimento de padrões (Wang et al, 2005b).…”