New models for region of interest reader classification analysis in chest radiographs

Authors:
M. S. Pattichis;T. Cacoullos;Peter Soliz
Affiliations:
Department of Electrical and Computer Engineering, The University of New Mexico, Albuquerque, NM 87131-0001, USA;Department of Mathematics, National and Capodistrian University of Athens, Athens Panepistimioupolis, GR-157 84, Athens, Greece;VisionQuest Biomedical, LLC, 4801 Lang NE, Suite 110, Albuquerque, NM 87109, USA
Venue:
Pattern Recognition
Year:
2009

Citing 4
Cited 2

Some representations of the multivariate Bernoulli and binomial distributions

Journal of Multivariate Analysis
Computer-Aided Diagnosis for Pnemoconiosis Using Neural Network

CBMS '01 Proceedings of the Fourteenth IEEE Symposium on Computer-Based Medical Systems
A Screening System for the Assessment of Opacity Profusion in Chest Radiographs of Miners with Pneumoconiosis

SSIAI '02 Proceedings of the Fifth IEEE Southwest Symposium on Image Analysis and Interpretation
Digital Design: Principles and Practices (4th Edition)

Digital Design: Principles and Practices (4th Edition)

Multiscale AM-FM analysis of pneumoconiosis X-ray images

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
An online AUC formulation for binary classification

Pattern Recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

In several computer-aided diagnosis (CAD) applications of image processing, there is no sufficiently sensitive and specific method for determining what constitutes a normal versus an abnormal classification of a chest radiograph. In the case of lung nodule detection or in classifying the perfusion of pneumoconiosis, multiple radiograph readers (radiologists) are asked to examine and score specific regions of interest (ROIs). The readers provide size, shape and perfusion grades for the presence of opacities in each region and then use all the ROI grades to classify the lung as normal or abnormal. The combined grades from all readers are then used to arrive at a consensus normal or abnormal classification. In this paper, using area under the ROC curve, we evaluate new mathematical models that are based on mathematical statistics, logic functions, and several statistical classifiers to analyze reader performance in grading chest radiographs for pneumoconiosis as the first step toward applying this technique to early detection of nodules found in lung cancer. In pneumoconiosis, rounded opacities are on the order of 1-10mm in size, while lung nodules are often not diagnosed until they reach a size on the order of 1cm.