Meeting Banner
Abstract #1483

The Use of Texture Analysis in the Grading of Breast Cancer on MR Images: Preliminary Findings

Shelley Waugh1, 2, Richard Lerski1, 2, Luc Bidaut2, Alastair Thompson, 23

1Medical Physics, Ninewells Hospital, Dundee, Angus, United Kingdom; 2University of Dundee, Dundee, United Kingdom; 3Department of Surgery, Ninewells Hospital, Dundee, United Kingdom

This study considers the use of texture analysis in the grading of the two most common types of breast cancer- invasive ductal and infiltrative lobular cancers. It was believed that the underlying histological nature of cancer growth patterns used for staging would also result in textural features on MR imaging that could potentially allow classification between grades using computer-based texture analysis methods.

Keywords

able accounting acquisition affect aided aimed aims alone angular around assisted automatically bandwidth basis benign best breast breasts brightness cancer cancers carcinoma carried cells channel characteristics classification classified coefficient coil combination common complementary complete computer confirmed considered considers consisted contrast corp correlation counting cross currently degree diagnosis differentiate differentiating differentiation drawing dynamic entropy examination excellent feature features findings flash folds formation full grade grades grading hospital identified identify incorrectly individual infiltrative injected injection invasive inverse kingdom laboratories length lesion lesions lobular make malignancy many matrix measurable medical microscopic minute minutes misclassification model models moment nearest negative orientation parallel pathology patient patients physics pixel poorly populated potentially predictive preliminary probability proposed regime regressive repetition reported reports represented respectively routine scanner sensitivity separately shot significantly simplification slice slices sparsely specificity squares stage staged statistical statistically straying studies subtracted suggesting summary table texture thereby transform uptake variable variance varying vectors version volume volumes wavelet