SMOTE algorithm with local linear imbedding

Abstract

A data classification method. The method includes: providing data mapped in a first space; mapping the data into a second space using locally linear embedding to generate mapped data; applying a synthetic minority over-sampling technique (SMOTE) to the mapped data to generate new data; and mapping the new data into the first space.

Description

technical field [0001] The invention generally relates to the field of digital medical image processing, and in particular to computer-aided detection. More specifically, the present invention relates to the application of synthetic minority class oversampling algorithms for computer aided detection (CAD). Background technique [0002] Computer-aided detection (CAD) systems have found application in the medical field, for example, in mammography to aid in the detection of breast cancer. The Kodak Mammography CAD System is an example of such a system. US Published Patent Application No. 2004 / 0024292 (Menhardt) relates to a system and method for assigning computer aided inspection applications to digital images. [0003] Medical CAD systems automatically identify candidates for objects of interest in images given known properties of abnormal shape (e.g., polyps, masses, needles); obtain features for each candidate; classify candidates ; and to display candidates to radiolog...

AI Technical Summary

Problems solved by technology

That is, the resulting decision boundary is heavily biased for the minority class, and may lead to poor performance according to ROC curve analysis (receiver operating characteristic analysis)

Images