NOTICE: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or further copied without the explicit permission of the copyright holder.

All documents are in pdf format, and may require Adobe's Acrobat Reader to view.

Estimation of linear observer templates in the presence of multi-peaked Gaussian noise through 2AFC experiments (597K)
Medical Imaging 2000: Image Perception and Performance (Elizabeth A. Krupinski, ed.), vol. 3981, pp. 86-96, Proc. SPIE 2000.
(© 2000, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

Using a Bayesian Neural Network to Optimally Eliminate False-Positive Microcalcification Detections in a CAD Scheme (38K)
IWDM 2000: 5th International Workshop on Digital Mammography (M. J. Yaffe, ed.), Proceedings of the Workshop, (Madison, Wisconsin), pp. 168-173, Medical Physics Publishing, 2001.
(© 2001, Medical Physics)

Eliminating false-positive microcalcification clusters in a mammography CAD scheme using a Bayesian neural network (171K)
Medical Imaging 2001: Image Processing (Milan Sonka and Kenneth Hanson, eds.), vol. 4322, pp. 1954-1960, Proc. SPIE 2001.
(© 2001, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

Ideal Observer Estimation Methods for Computer-Aided Diagnosis (571K)
A Ph.D. Dissertation Proposal Submitted to the Faculty of the Graduate Programs in Medical Physics.
(© 2001, Darrin C. Edwards)

Estimation of three-class ideal observer decision functions with a Bayesian artificial neural network (537K)
Medical Imaging 2002: Image Perception, Observer Performance, and Technology Assessment (Dev P. Chakraborty and Elizabeth A. Krupinski, eds.), vol. 4686, pp. 1-12, Proc. SPIE 2002.
(© 2002, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

Maximum likelihood fitting of FROC curves under an initial-detection-and-candidate-analysis model (228K)
Med. Phys. 29 (12), December 2002.
(© 2002, AAPM)
(This is a preprint of the article as submitted to Medical Physics, and therefore does not correspond exactly in format to the published version, which may require subscription for viewing.)

Bayesian ANN estimates of three-class ideal observer decision variables for classification of mammographic masses (112K)
Medical Imaging 2003: Image Perception, Observer Performance, and Technology Assessment (Dev P. Chakraborty and Elizabeth A. Krupinski, eds.), vol. 5034, pp. 474-482, Proc. SPIE 2003.
(© 2003, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

Ideal Observer Estimation and Generalized ROC Analysis for Computer-Aided Diagnosis (1092K)
[Abstract, 14K] [Plain text abstract, 2K]
A Dissertation Submitted to the Faculty of the Division of the Biological Sciences and the Pritzker School of Medicine in Candidacy for the Degree of Doctor of Philosophy: Committee on Medical Physics.
(© 2003, Darrin C. Edwards)
Defended, 14 Nov. 2003.
Approved by the University of Chicago Dissertation Office, 21 Nov. 2003.

Estimating three-class ideal observer decision variables for computerized detection and classification of mammographic mass lesions (189K)
Med. Phys. 31 (1), January 2004.
(© 2004, AAPM)
(This is a preprint of the article as submitted to Medical Physics, and therefore does not correspond exactly in format to the published version, which may require subscription for viewing.)

Hypervolume under the ROC hypersurface of a "near-guessing" ideal observer in a three-class classification task (122K)
Medical Imaging 2004: Image Perception, Observer Performance, and Technology Assessment (Dev P. Chakraborty and Miguel P. Eckstein, eds.), vol. 5372, pp. 128-137, Proc. SPIE 2004.
(© 2004, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

Ideal Observers and Optimal ROC Hypersurfaces in N-class Classification (87K)
IEEE Trans. Med. Imag. 23 (7), July 2004.
(© 2004, IEEE)
(This is a preprint of the article as submitted to IEEE TMI, and therefore does not correspond exactly in format to the published version, which may require subscription for viewing.)

Review of several proposed three-class classification decision rules and their relation to the ideal observer decision rule (122K)
Medical Imaging 2005: Image Perception, Observer Performance, and Technology Assessment (Miguel P. Eckstein and Yulei Jiang, eds.), vol. 5749, pp. 128-137, Proc. SPIE 2005.
(© 2005, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

Evaluating Bayesian ANN estimates of ideal observer decision variables by comparison with identity functions (297K)
Medical Imaging 2005: Image Perception, Observer Performance, and Technology Assessment (Miguel P. Eckstein and Yulei Jiang, eds.), vol. 5749, pp. 174-182, Proc. SPIE 2005.
(© 2005, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

The Hypervolume under the ROC Hypersurface of "Near-Guessing" and "Near-Perfect" Observers in N-Class Classification Tasks (1003K)
IEEE Trans. Med. Imag. 24(3), March 2005.
(© 2005, IEEE)
(This is a preprint of the article as submitted to IEEE TMI, and therefore does not correspond exactly in format to the published version, which may require subscription for viewing.)

Restrictions on the Three-Class Ideal Observer's Decision Boundary Lines (139K)
IEEE Trans. Med. Imag. 24(12), December 2005.
(© 2005, IEEE)
(This is a preprint of the article as submitted to IEEE TMI, and therefore does not correspond exactly in format to the published version, which may require subscription for viewing.)

Optimization of an ROC hypersurface constructed only from an observer's within-class sensitivities (119K)
Medical Imaging 2006: Image Perception, Observer Performance, and Technology Assessment (Yulei Jiang and Miguel P. Eckstein, eds.), vol. 6146, pp. 61460A1-61460A7, Proc. SPIE 2006.
(© 2006, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

A utility-based performance metric for ROC analysis of N-class classification tasks (273K)
Medical Imaging 2007: Image Perception, Observer Performance, and Technology Assessment (Yulei Jiang and Berkman Sahiner, eds.), vol. 6515, pp. 6515031-65150310, Proc. SPIE 2007.
(© 2007, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

Optimization of Restricted ROC Surfaces in Three-Class Classification Tasks (177K)
IEEE Trans. Med. Imag. 26(10), October 2007.
(© 2007, IEEE)
(This is a preprint of the article as submitted to IEEE TMI, and therefore does not correspond exactly in format to the published version, which may require subscription for viewing.)

Optimality of a utility-based performance metric for ROC analysis (148K)
Medical Imaging 2008: Image Perception, Observer Performance, and Technology Assessment (Berkman Sahiner and David J. Manning, eds.), vol. 6917, pp. 69170F1-68170F6, Proc. SPIE 2008.
(© 2008, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

Comparing the performance of two observers using a novel utility-based performance metric for ROC analysis (148K)
Medical Imaging 2009: Image Perception, Observer Performance, and Technology Assessment (Berkman Sahiner and David J. Manning, eds.), vol. 7263, pp. 72630W1-72630W7, Proc. SPIE 2009.
(© 2009, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)

Behavior of the decision variables of the three-class ideal observer for univariate trinormal data (454K)
Medical Imaging 2010: Image Perception, Observer Performance, and Technology Assessment (David J. Manning and Craig K. Abbey, eds.), vol. 7627, pp. 76270Y1-76270Y11, Proc. SPIE 2010.
(© 2010, SPIE)
(This paper is made available as an electronic preprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.)