Classification Performance related to Intrinsic Dimensionality in Mammographic Image Analysis

Harry George Strange, Reyer Zwiggelaar

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)

29 Downloads (Pure)

Abstract

In the problem of mammographic image classification one seeks to classify an image, based on certain aspects or features, into a risk assessment class. The use of breast tissue density features provide a good way of classifying mammographic images into BI-RADS risk assessment classes. However, this approach leads to a high-dimensional problem as many features are extracted from each image. These features may be an over representation of the data and it would be expected that the intrinsic dimensionality would be much lower. We aim to find how running a simple classifier in a reduced dimensional space, in particular the apparent intrinsic dimension, affects classification performance. We perform classification of the data using a simple k-nearest neighbor classifier with data pre-processed using two dimensionality reduction techniques, one linear and one non-linear. The optimum result occurs when using dimensionality reduction in the estimated intrinsic dimensionality. This not only shows that optimum performance occurs when classifying in the intrinsic-dimensional space but also that dimensionality reduction can improve the performance of a simple classifier.
Original languageEnglish
Title of host publicationProceedings of the Thirteenth Annual Conference on Medical Image Understanding and Analysis
Pages219-223
Number of pages5
Publication statusPublished - Jul 2009

Fingerprint

Dive into the research topics of 'Classification Performance related to Intrinsic Dimensionality in Mammographic Image Analysis'. Together they form a unique fingerprint.

Cite this