Dr. Darrin C. Edwards Profile

Dr. Darrin C. Edwards

at Univ of Chicago

SPIE Involvement:

Author

Publications (18)

Proceedings Article | 29 February 2012 Paper

A new parametrization for the three-class ideal observer's decision rule

Darrin Edwards

Proceedings Volume 8318, 83180E (2012) https://doi.org/10.1117/12.913350

KEYWORDS: Receivers, Medical imaging, Space operations, Algorithm development, Medicine, Image compression, Current controlled current source, Electronic filtering

Read Abstract +

Proceedings Article | 9 March 2011 Paper

Comparison of two-class and three-class Bayesian artificial neural networks in estimation of observations drawn from simulated bivariate normal distributions

Neha Bhooshan, Darrin Edwards, Maryellen Giger

Proceedings Volume 7963, 796325 (2011) https://doi.org/10.1117/12.878074

KEYWORDS: Computer simulations, Statistical analysis, Computer aided diagnosis and therapy, Artificial neural networks, Matrices, Radiology, Binary data, Breast, Medical imaging, Current controlled current source

Read Abstract +

Proceedings Article | 3 March 2011 Paper

Support of the decision variable densities of the three-class ideal observer for bivariate trinormal data

Darrin Edwards

Proceedings Volume 7966, 79660I (2011) https://doi.org/10.1117/12.877902

KEYWORDS: Data modeling, Matrices, Medical imaging, Receivers, Performance modeling, Numerical analysis, Statistical analysis, Solid modeling, Image classification, Radiology

Read Abstract +

Proceedings Article | 27 February 2010 Paper

Behavior of the decision variables of the three-class ideal observer for univariate trinormal data

Darrin Edwards, Charles Metz

Proceedings Volume 7627, 76270Y (2010) https://doi.org/10.1117/12.843942

KEYWORDS: Data modeling, Image segmentation, Statistical analysis, Space operations, Lawrencium, Receivers, Analytical research, Medical imaging, Algorithm development, Radiology

Read Abstract +

Proceedings Article | 13 March 2009 Paper

Comparing the performance of two observers using a novel utility-based performance metric for ROC analysis

Darrin Edwards, Charles Metz

Proceedings Volume 7263, 72630W (2009) https://doi.org/10.1117/12.810778

KEYWORDS: Data modeling, Performance modeling, Statistical modeling, Medical imaging, Radiology, Receivers, Tissues, Error analysis, Electronic filtering, 3D image processing

Read Abstract +

Proceedings Article | 3 March 2009 Paper

Using three-class BANN classifier in the automated analysis of breast cancer lesions in DCE-MRI

Neha Bhooshan, Maryellen Giger, Darrin Edwards, Karen Drukker, Sanaz Jansen, Hui Li, Li Lan, Gillian Newstead

Proceedings Volume 7260, 72600J (2009) https://doi.org/10.1117/12.813507

KEYWORDS: Breast, Computer aided diagnosis and therapy, Magnetic resonance imaging, Feature selection, Lawrencium, Breast cancer, Databases, Artificial neural networks, Image segmentation, Statistical analysis

Read Abstract +

Proceedings Article | 6 March 2008 Paper

Optimality of a utility-based performance metric for ROC analysis

Darrin Edwards, Charles Metz

Proceedings Volume 6917, 69170F (2008) https://doi.org/10.1117/12.773052

KEYWORDS: Data modeling, Medical imaging, Performance modeling, Electronic filtering, Statistical analysis, Radiology, Receivers, Tissues, Error analysis, 3D image processing

Read Abstract +

Proceedings Article | 20 March 2007 Paper

A utility-based performance metric for ROC analysis of N-class classification tasks

Darrin Edwards, Charles Metz

Proceedings Volume 6515, 651503 (2007) https://doi.org/10.1117/12.710083

KEYWORDS: Electronic filtering, Data modeling, Medical imaging, Solids, Decision support systems, Performance modeling, Space operations, Radiology, Receivers, Tissues

Read Abstract +

Proceedings Article | 20 March 2007 Paper

Evaluation of the channelized Hotelling observer for signal detection in 2D tomographic imaging

Samuel LaRoque, Emil Sidky, Darrin Edwards, Xiaochuan Pan

Proceedings Volume 6515, 651514 (2007) https://doi.org/10.1117/12.710112

KEYWORDS: Signal to noise ratio, Reconstruction algorithms, Image restoration, Signal detection, Tomography, CT reconstruction, Detection and tracking algorithms, Data modeling, Systems modeling, Computed tomography

Read Abstract +

Proceedings Article | 17 March 2006 Paper

Optimization of an ROC hypersurface constructed only from an observer's within-class sensitivities

Darrin Edwards, Charles Metz

Proceedings Volume 6146, 61460A (2006) https://doi.org/10.1117/12.654026

KEYWORDS: Lawrencium, 3D modeling, Receivers, Medical imaging, Performance modeling, Error analysis, Tumor growth modeling, Radiology, Tissues, Analytical research

Read Abstract +

Proceedings Article | 6 April 2005 Paper

Review of several proposed three-class classification decision rules and their relation to the ideal observer decision rule

Darrin Edwards, Charles Metz

Proceedings Volume 5749, (2005) https://doi.org/10.1117/12.595674

KEYWORDS: Lawrencium, Performance modeling, Data modeling, Computer aided diagnosis and therapy, Computer aided design, Analytical research, Statistical modeling, Mammography, Medical imaging, Tumor growth modeling

Read Abstract +

Proceedings Article | 6 April 2005 Paper

Evaluating Bayesian ANN estimates of ideal observer decision variables by comparison with identity functions

Darrin Edwards, Charles Metz

Proceedings Volume 5749, (2005) https://doi.org/10.1117/12.595716

KEYWORDS: Lawrencium, Error analysis, Artificial neural networks, Computer aided diagnosis and therapy, Statistical analysis, Receivers, Analytical research, Medical imaging, Radiology, Medical research

Read Abstract +

Proceedings Article | 12 May 2004 Paper

Computerized detection and 3-way classification of breast lesions on ultrasound images

Karen Drukker, Darrin Edwards, Maryellen Giger, Robert Nishikawa, Charles Metz

Proceedings Volume 5370, (2004) https://doi.org/10.1117/12.534339

KEYWORDS: Cancer, Breast, Ultrasonography, Databases, Mammography, Image classification, Breast cancer, Computer aided diagnosis and therapy, Error analysis, Neural networks

Read Abstract +

Computer-aided diagnosis has great potential to improve performance of the detection and classification of abnormalities on breast ultrasound. Our goal is to develop a computerized tool that detects suspicious areas and distinguishes among false-positive detections, benign lesions, and malignancies. One-step classification into 3 categories is a largely unexplored territory with many possibilities. The computerized scheme first identifies potential lesions based on expected lesion shape and margin characteristics. Our main focus here, however, is the subsequent classification of the potential lesions into 3 categories. For this purpose, we use a 3-way Bayesian neural net (BNN) based on extracted image features of the lesion candidates. The method was tested on a database of 858 cases (1832 images) consisting of complex and simple cysts, benign solid lesions, and malignant lesions. In order to verify whether performance conforms to expectations, the output of a 3-way classifier ("A" vs. "B" vs. "C") can be projected onto that of two 2-way classifiers ("A" vs. "B or C", and "A or B" vs. "C"). We compared the projected performance of the 3-way classifier to two specifically trained 2-way classifiers. The first task was to distinguish cancer from all other lesion candidates, and the second was to distinguish actual lesions from false-positive detections. For these tasks, the performance of the 2-way classifiers and the projected performance of the 3-way classifier were indistinguishable based on calculated means and standard deviations of ROC area (Az). For example, in round robin analysis the average Az values obtained with both approaches were 0.92 and 0.83, for the two tasks, with standard deviations of 0.006 and 0.010, respectively. The potential of 3-way classification is illustrated graphically through the estimated probability density functions of the three truth categories. We have implemented a promising computerized scheme for detection and subsequent one-step 3-way classification of breast lesions on ultrasound images. The method was tested on an extensive database. The main challenge is the development of an objective evaluation method of performance such as the equivalent of ROC analysis for the 2-class problem.

Proceedings Article | 4 May 2004 Paper

Hypervolume under the ROC hypersurface of a near-guessing ideal observer in a three-class classification task

Darrin Edwards, Charles Metz, Robert Nishikawa

Proceedings Volume 5372, (2004) https://doi.org/10.1117/12.536068

KEYWORDS: Space operations, Receivers, Computer aided diagnosis and therapy, Electronic filtering, Mammography, Medical imaging, Radiology, Computer aided design, Breast, Artificial neural networks

Read Abstract +

Proceedings Article | 22 May 2003 Paper

Bayesian ANN estimates of three-class ideal observer decision variables for classification of mammographic masses

Darrin Edwards, Li Lan, Charles Metz, Maryellen Giger, Robert Nishikawa

Proceedings Volume 5034, (2003) https://doi.org/10.1117/12.480343

KEYWORDS: Image classification, Breast, Electronic filtering, Artificial neural networks, Mammography, Image segmentation, Tissues, Medical imaging, Computer aided diagnosis and therapy, Neural networks

Read Abstract +

Proceedings Article | 12 April 2002 Paper

Estimation of three-class ideal observer decision functions with a Bayesian artificial neural network

Darrin Edwards, Charles Metz, Robert Nishikawa

Proceedings Volume 4686, (2002) https://doi.org/10.1117/12.462662

KEYWORDS: Error analysis, Probability theory, Statistical analysis, Artificial neural networks, Neural networks, Computer aided diagnosis and therapy, Data modeling, Signal detection, Mammography, Medical imaging

Read Abstract +

Proceedings Article | 3 July 2001 Paper

Eliminating false-positive microcalcification clusters in a mammography CAD scheme using a Bayesian neural network

Darrin Edwards, John Papaioannou, Yulei Jiang, Matthew Kupinski, Robert Nishikawa

Proceedings Volume 4322, (2001) https://doi.org/10.1117/12.431089

KEYWORDS: Signal detection, Mammography, Computer aided diagnosis and therapy, Neural networks, Feature extraction, Electronic filtering, Analytical research, Databases, Artificial neural networks, Data modeling

Read Abstract +

Proceedings Article | 14 April 2000 Paper

Estimation of linear observer templates in the presence of multi-peaked gaussian noise through 2AFC experiments

Darrin Edwards, Matthew Kupinski, Robert Nishikawa, Charles Metz

Proceedings Volume 3981, (2000) https://doi.org/10.1117/12.383094

KEYWORDS: Matrices, Statistical analysis, Interference (communication), Signal detection, Computer aided diagnosis and therapy, Medical imaging, Image quality, Error analysis, Solid modeling, Computer aided design

Read Abstract +

Showing 5 of 18 publications

Conference Committee Involvement (5)