Back to search

South Dakota State University

Fourier Irregularity Index: A New Approach to Measure Irregularity of Breast Masses in Mammograms

Abstract

dc:description.abstract

Shape is one of typical descriptions of a mammographically detected breast mass. The morphol ogical appearance is also used as a malignancy diagnosis factor. It is believed that masses appearing with very irregular shapes are highly suspicious for breast cancer, while a purely round or oval mass is likely benign. Thus, an effective irregularity measure could aid medical doctors in diagnosing. In this paper, Fourier Irregularity Index (Fu), Compactness Index (Cl), Fractal Dimension (FD) and Fourier Factor (FF) were investigated and assessed by applying them with 1304 mammograms. The result shows Fu outperforms the other methods. Furthermore, in order to achieve a higher performance, combined measures of these four methods are studied. Radial Basis Function Neural Network is employed to build classifiers that use different combinations of measures. The results show the classifier using all four measures, including F11, outperforms those classifiers using a single measure or other combinations of measures.

Degree

thesis:*
Name thesis:degree_name
Master of Science (MS)
Level thesis:degree_level
Thesis - University Access Only
Discipline thesis:degree_discipline
Electrical Engineering and Computer Science

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zhang, Gensheng
Contributors dc:contributor
  • Sung Y. Shin

Rights

dc:rights

Identifiers

dc:identifier.*
Repository record dc:identifier
https://openprairie.sdstate.edu/etd2/1969

Chain of custody

source
Harvested from
South Dakota State University
Base URL
openprairie.sdstate.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Zhang, Gensheng. Fourier Irregularity Index: A New Approach to Measure Irregularity of Breast Masses in Mammograms. Thesis - University Access Only thesis, https://openprairie.sdstate.edu/etd2/1969