Incorporation of a Laguerre–Gauss Channelized Hotelling Observer for False-Positive Reduction in a Mammographic Mass CAD System
Abstract
Previously, we developed a simple Laguerre–Gauss (LG) channelized Hotelling observer (CHO) for incorporation into our mass computer-aided detection (CAD) system. This LG-CHO was trained using initial detection suspicious region data and was empirically optimized for free parameters. For the study presented in this paper, we wish to create a more optimal mass detection observer based on a novel combination of LG channels. A large set of LG channels with differing free parameters was created. Each of these channels was applied to the suspicious regions, and an output test statistic was determined. A stepwise feature selection algorithm was used to determine which LG channels would combine best to detect masses. These channels were combined using a HO to create a single template for the mass CAD system. Results from free-response receiver operating characteristic curves demonstrated that the incorporation of the novel LG-CHO into the CAD system slightly improved performance in high-sensitivity regions.
Key words
CAD mass detection classification image processing breast cancerNotes
Acknowledgments
We would like to gratefully acknowledge the support for this research from the DOD Breast Cancer Research Program, DAMD17-02-1-0367.
References
- 1.ACS, American Cancer Society: Cancer Facts and Figures 2002. Atlanta, GA: American Cancer Society 2002, 2002Google Scholar
- 2.Freer TW, Ulissey MJ: Screening mammography with computer-aided detection: Prospective study of 12,860 patients in a community breast center. Radiology 220:781–786, 2001PubMedCrossRefGoogle Scholar
- 3.Castellino RA, Roehrig J, Zhang W: Improved Computer-aided Detection (CAD) Algorithms for Screening Mammography in Radiology. 2000, p 400Google Scholar
- 4.Catarious DM, Baydush AH, Floyd Jr, CE: Incorporation of an iterative, linear segmentation routine into a mammographic mass CAD system. Med Phys 31:1512–1520, 2004PubMedCrossRefGoogle Scholar
- 5.Catarious DM, Baydush AH, Lo JY, Floyd Jr, CE: Characterization of difference of Gaussian filters in the detection of mammographic regions. Med Phys 33:4104–4114, 2006PubMedCrossRefGoogle Scholar
- 6.Baydush AH, Catarious DM, Floyd Jr, CE: Incorporation of Laguerre–Gauss channelized Hotelling observer into a mammographic mass CAD system. In: International Workshop on Digital Mammography, 2004Google Scholar
- 7.Heath M, Bowyer KW, Kopans D: Current status of the digital database for screening mammography. In: Karssemeijer N, Thijssen M, Hendriks J Eds. Digital Mammography. The Netherlands: Kluwer Academic Publishers, 1998, pp 457–460Google Scholar
- 8.Eckstein M, Abbey C, Whiting J: Human vs model observers in anatomic backgrounds. In: Proceedings of SPIE: Image Perception, 1998, vol 3340, pp 16–26Google Scholar
- 9.Fiete RD, Barrett HH, Smith WE, Myers KJ: Psychophysical study to test the ability of the Hotelling trace criterion to predict human-performance. J Opt Soc Am A–Opt Image Sci Vis 3:P126, 1986Google Scholar
- 10.Fiete RD, Barrett HH, Smith WE, Myers KJ: Hotelling trace criterion and its correlation with human-observer performance. J Opt Soc Am A–Opt Image Sci Vis 4:945–953, 1987Google Scholar
- 11.Gifford HC, King MA, de Vries DJ, Soares EJ: Channelized Hotelling and human observer correlation for lesion detection in hepatic SPECT imaging. J Nucl Med 39:771, 1998Google Scholar
- 12.Gifford HC, Wells RG, King MA: A comparison of human observer LROC and numerical observer ROC for tumor detection in SPECT images. IEEE Trans Nucl Sci 46:1032–1037, 1999CrossRefGoogle Scholar
- 13.Gifford HC, King MA, de Vries DJ, Soares EJ: Channelized Hotelling and human observer correlation for lesion detection in hepatic SPECT imaging. J Nucl Med 41:514–521, 2000PubMedGoogle Scholar
- 14.Wollenweber SD, Tsui BMW, Lalush DS, Frey EC, LaCroix KJ, Gullberg GT: Comparison of Hotelling observer models and human observers in defect detection from myocardial SPECT imaging. IEEE Trans Nucl Sci 46:2098–2103, 1999CrossRefGoogle Scholar
- 15.Metz C: Evaluation of CAD methods. In: Doi K, MacMahon H, Giger ML, Hoffmann KR Eds. Computer-Aided Diagnosis in Medical Imaging. Amsterdam: Elsevier Science, 1998, pp 543–554Google Scholar
- 16.Metz CE: Basic principles of ROC analysis. Semin Nuc Med 8:283–298, 1978Google Scholar
- 17.Metz CE: ROC methodology in radiologic imaging. Invest Radiol 21:720–733, 1986PubMedCrossRefGoogle Scholar
- 18.Barrett HH, Abbey CK, Gallas BG: Stabilized estimates of Hotelling-observer detection performance in patient-structured noise. In: Proceedings of SPIE: Image Perception, 1998, vol 3340, pp 27–43Google Scholar
- 19.Myers KJ, Barrett HH: Addition of a channel mechanism to the ideal-observer model. J Opt Soc Am A–Opt Image Sci Vis 4:2447–2457, 1987CrossRefGoogle Scholar