Open AccessThis article is
- freely available
Image Similarity to Improve the Classification of Breast Cancer Images
US Army Research Laboratory, 2800 Powder Mill Rd, Adelphi, MD 20783, USA
Received: 12 October 2009; in revised form: 20 November 2009 / Accepted: 25 November 2009 / Published: 1 December 2009
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.
Keywords: cancer; similarity; classification
Citations to this Article
Cite This Article
MDPI and ACS Style
Tahmoush, D. Image Similarity to Improve the Classification of Breast Cancer Images. Algorithms 2009, 2, 1503-1525.
Tahmoush D. Image Similarity to Improve the Classification of Breast Cancer Images. Algorithms. 2009; 2(4):1503-1525.
Tahmoush, Dave. 2009. "Image Similarity to Improve the Classification of Breast Cancer Images." Algorithms 2, no. 4: 1503-1525.