Early detection of breast cancer using thermal texture maps

Hairong Qi, Phani Teja Kuruganti, Zhongqi Liu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

33 Scopus citations

Abstract

This paper focuses on the discussion of using thermal infrared imaging (TIR) in early detection of breast cancer. We use the term thermal texture maps to represent the images captured from TIR imaging. Even though the heat emanating onto the surface from the cancerous tissue can be successfully modeled using the Pennes bio-heat equation, the complexity of the boundary conditions associated with the biological body makes it impractical to solve the inverse problem. This paper presents a new method for analyzing a thermal system based on an analogy to electrical circuit theory; referred to as thermal-electric analog. We demonstrate how the analog can be used to estimate the depth of the heat source, and furthermore, help understand the metabolic activities undergoing within the human body. The method has been used in early breast cancer detection and has achieved high sensitivity. Several breast cancer study cases are given to show the effectiveness of the method. On-going clinical study results are provided as well.

Original languageEnglish
Title of host publication2002 IEEE International Symposium on Biomedical Imaging, ISBI 2002 - Proceedings
PublisherIEEE Computer Society
Pages309-312
Number of pages4
ISBN (Electronic)078037584X
DOIs
StatePublished - 2002
Externally publishedYes
EventIEEE International Symposium on Biomedical Imaging, ISBI 2002 - Washington, United States
Duration: Jul 7 2002Jul 10 2002

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2002-January
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

ConferenceIEEE International Symposium on Biomedical Imaging, ISBI 2002
Country/TerritoryUnited States
CityWashington
Period07/7/0207/10/02

Fingerprint

Dive into the research topics of 'Early detection of breast cancer using thermal texture maps'. Together they form a unique fingerprint.

Cite this