Thumbnail Image
Publication

Shape factors for analysis of breast tumors in mammograms

; 
Rangayyan, Rangaraj
; 
Desautels, J. E. Leo
; 
Alim, Onsy
Citations
Altmetric:
Type
Supervisor
Subject
breast tumors , mammograms , shape factors , malignant breast tumors , benign breast tumors , shape complexity , radiographic definition , compactness , moments , Fourier descriptors , chord length statistics , spiculated mass , circumscribed mass , four-group classification , breast cancer diagnosis
Date
2002-08-06
Collections
ECE - Conference Papers
Show all metadata
Files
Thumbnail Image
MassShapeCCECE1996.pdf
Adobe PDF, 437.77 KB
Research Projects
Organizational Units
Journal Issue
Abstract
Distinguishing between benign and malignant breast tumors requires careful analysis of their shape complexity and radiographic definition. In this paper we examine the usefulness of shape factors such as compactness, moments, Fourier descriptors, and statistics of chord lengths in distinguishing between circumscribed/spiculated and benign/malignant masses. A database of 54 tumors was used in pattern classification experiments. Classification accuracies of 95% for circumscribed/spiculated, 76% for benign/malignant, and 77% for four-group classification were obtained, which indicate the usefulness of the proposed methods in breast cancer diagnosis.
Department
Electrical and Computer Engineering
Publisher
IEEE
Sponsor
Copyright
Book title
Journal title
Open Access
http://hdl.handle.net/20.500.14131/598
DOI
10.1109/CCECE.1996.548110
Embedded videos