A Bayesian nonparametric approach to tumor detection using UWB imaging

We develop a tumor detection and discrimination algorithm for Ultra-Wideband (UWB) microwave imaging of breast cancer based on a Bayesian nonparametric approach. We model the UWB backscattered signal as a mixture of distinct scatterer contributions, and use a Dirichlet Process mixture model (DPMM) t...

Full description

Saved in:
Bibliographic Details
Main Authors: Nijsure, Yogesh, Tay, Wee Peng, Gunawan, Erry, Yue, Joshua Lai Chong
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2013
Online Access:https://hdl.handle.net/10356/99490
http://hdl.handle.net/10220/12892
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-99490
record_format dspace
spelling sg-ntu-dr.10356-994902020-03-07T13:24:49Z A Bayesian nonparametric approach to tumor detection using UWB imaging Nijsure, Yogesh Tay, Wee Peng Gunawan, Erry Yue, Joshua Lai Chong School of Electrical and Electronic Engineering IEEE International Conference on Ultra-Wideband (2012 : Syracuse, New York, US) We develop a tumor detection and discrimination algorithm for Ultra-Wideband (UWB) microwave imaging of breast cancer based on a Bayesian nonparametric approach. We model the UWB backscattered signal as a mixture of distinct scatterer contributions, and use a Dirichlet Process mixture model (DPMM) to describe the amplitudes and delays of the backscattered returns. Because of the unbounded complexity afforded by the DPMM, model under-fitting is avoided and parameters like the clutter covariance matrix in other commonly used approaches, need not be estimated. The DPMM allows us to perform discrimination when there are multiple tumor and clutter sources that present as extended radar targets. After performing discrimination, we distinguish the tumor sources from other clutter sources using a generalized likelihood ratio test (GLRT). We perform experiments on a breast phantom with realistic dielectric contrast ratios, and compare the performance of our algorithm with a direct GLRT approach. Our numerical results show performance improvement in terms of tumor detection probability and Signal to Interference and Noise Ratio (SINR) gain of approximately 2.2 dB at a probability of detection of 0.9 over the GLRT method. 2013-08-02T04:40:47Z 2019-12-06T20:08:02Z 2013-08-02T04:40:47Z 2019-12-06T20:08:02Z 2012 2012 Conference Paper https://hdl.handle.net/10356/99490 http://hdl.handle.net/10220/12892 10.1109/ICUWB.2012.6340410 en
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
description We develop a tumor detection and discrimination algorithm for Ultra-Wideband (UWB) microwave imaging of breast cancer based on a Bayesian nonparametric approach. We model the UWB backscattered signal as a mixture of distinct scatterer contributions, and use a Dirichlet Process mixture model (DPMM) to describe the amplitudes and delays of the backscattered returns. Because of the unbounded complexity afforded by the DPMM, model under-fitting is avoided and parameters like the clutter covariance matrix in other commonly used approaches, need not be estimated. The DPMM allows us to perform discrimination when there are multiple tumor and clutter sources that present as extended radar targets. After performing discrimination, we distinguish the tumor sources from other clutter sources using a generalized likelihood ratio test (GLRT). We perform experiments on a breast phantom with realistic dielectric contrast ratios, and compare the performance of our algorithm with a direct GLRT approach. Our numerical results show performance improvement in terms of tumor detection probability and Signal to Interference and Noise Ratio (SINR) gain of approximately 2.2 dB at a probability of detection of 0.9 over the GLRT method.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Nijsure, Yogesh
Tay, Wee Peng
Gunawan, Erry
Yue, Joshua Lai Chong
format Conference or Workshop Item
author Nijsure, Yogesh
Tay, Wee Peng
Gunawan, Erry
Yue, Joshua Lai Chong
spellingShingle Nijsure, Yogesh
Tay, Wee Peng
Gunawan, Erry
Yue, Joshua Lai Chong
A Bayesian nonparametric approach to tumor detection using UWB imaging
author_sort Nijsure, Yogesh
title A Bayesian nonparametric approach to tumor detection using UWB imaging
title_short A Bayesian nonparametric approach to tumor detection using UWB imaging
title_full A Bayesian nonparametric approach to tumor detection using UWB imaging
title_fullStr A Bayesian nonparametric approach to tumor detection using UWB imaging
title_full_unstemmed A Bayesian nonparametric approach to tumor detection using UWB imaging
title_sort bayesian nonparametric approach to tumor detection using uwb imaging
publishDate 2013
url https://hdl.handle.net/10356/99490
http://hdl.handle.net/10220/12892
_version_ 1681042482843877376