
Proceedings Paper
Multi-probe-based resonance-frequency electrical impedance spectroscopy for detection of suspicious breast lesions: improving performance using partial ROC optimizationFormat | Member Price | Non-Member Price |
---|---|---|
$17.00 | $21.00 |
Paper Abstract
We have developed a multi-probe resonance-frequency electrical impedance spectroscope (REIS) system to detect breast
abnormalities. Based on assessing asymmetry in REIS signals acquired between left and right breasts, we developed
several machine learning classifiers to classify younger women (i.e., under 50YO) into two groups of having high and
low risk for developing breast cancer. In this study, we investigated a new method to optimize performance based on the
area under a selected partial receiver operating characteristic (ROC) curve when optimizing an artificial neural network
(ANN), and tested whether it could improve classification performance. From an ongoing prospective study, we selected
a dataset of 174 cases for whom we have both REIS signals and diagnostic status verification. The dataset includes 66
"positive" cases recommended for biopsy due to detection of highly suspicious breast lesions and 108 "negative" cases
determined by imaging based examinations. A set of REIS-based feature differences, extracted from the two breasts
using a mirror-matched approach, was computed and constituted an initial feature pool. Using a leave-one-case-out
cross-validation method, we applied a genetic algorithm (GA) to train the ANN with an optimal subset of features. Two
optimization criteria were separately used in GA optimization, namely the area under the entire ROC curve (AUC) and
the partial area under the ROC curve, up to a predetermined threshold (i.e., 90% specificity). The results showed that
although the ANN optimized using the entire AUC yielded higher overall performance (AUC = 0.83 versus 0.76), the
ANN optimized using the partial ROC area criterion achieved substantially higher operational performance (i.e.,
increasing sensitivity level from 28% to 48% at 95% specificity and/ or from 48% to 58% at 90% specificity).
Paper Details
Date Published: 9 March 2011
PDF: 8 pages
Proc. SPIE 7963, Medical Imaging 2011: Computer-Aided Diagnosis, 79631Z (9 March 2011); doi: 10.1117/12.877380
Published in SPIE Proceedings Vol. 7963:
Medical Imaging 2011: Computer-Aided Diagnosis
Ronald M. Summers M.D.; Bram van Ginneken, Editor(s)
PDF: 8 pages
Proc. SPIE 7963, Medical Imaging 2011: Computer-Aided Diagnosis, 79631Z (9 March 2011); doi: 10.1117/12.877380
Show Author Affiliations
Dror Lederman, Univ. of Pittsburgh Medical Ctr. (United States)
Bin Zheng, Univ. of Pittsburgh Medical Ctr. (United States)
Xingwei Wang, Univ. of Pittsburgh Medical Ctr. (United States)
Bin Zheng, Univ. of Pittsburgh Medical Ctr. (United States)
Xingwei Wang, Univ. of Pittsburgh Medical Ctr. (United States)
Xiao Hui Wang, Univ. of Pittsburgh Medical Ctr. (United States)
David Gur, Univ. of Pittsburgh Medical Ctr. (United States)
David Gur, Univ. of Pittsburgh Medical Ctr. (United States)
Published in SPIE Proceedings Vol. 7963:
Medical Imaging 2011: Computer-Aided Diagnosis
Ronald M. Summers M.D.; Bram van Ginneken, Editor(s)
© SPIE. Terms of Use
