Skip to main content

Estimating three-class ideal observer decision variables for computerized detection and classification of mammographic mass lesions.

Publication ,  Journal Article
Edwards, DC; Lan, L; Metz, CE; Giger, ML; Nishikawa, RM
Published in: Med Phys
January 2004

We are using Bayesian artificial neural networks (BANNs) to classify mammographic masses in schemes for computer-aided diagnosis, and we are extending this methodology to a three-class classification task. We investigated whether a BANN can estimate ideal observer decision variables to distinguish malignant, benign, and false-positive computer detections. Five features were calculated for 63 malignant and 29 benign computer-detected mass lesions, and for 1049 false-positive computer detections, in 440 mammograms randomly divided into a training and testing set. A BANN was trained on the training set features and applied to the testing set features. We then used a known relation between three-class ideal observer decision variables and that used by a two-class ideal observer when two of three classes are grouped into one class, giving one decision variable for distinguishing malignant from nonmalignant detections, and a second for distinguishing true-positive from false-positive computer detections. For comparison, we grouped the training data into two classes in the same two ways and trained two-class BANNs for these two tasks. The three-class BANN decision variables were essentially identical in performance to the specifically trained two-class BANNs, with the average difference in area under the ROC curves being less than 0.0035 and no differences in area being statistically significant. Thus, the BANN outputs obey the same theoretical relationship as do the three-class and two-class ideal observer decision variables, which is consistent with the claim that the three-class BANN output can provide good estimates of the decision variables used by a three-class ideal observer.

Duke Scholars

Published In

Med Phys

DOI

ISSN

0094-2405

Publication Date

January 2004

Volume

31

Issue

1

Start / End Page

81 / 90

Location

United States

Related Subject Headings

  • Reproducibility of Results
  • Radiographic Image Interpretation, Computer-Assisted
  • Observer Variation
  • Nuclear Medicine & Medical Imaging
  • Neural Networks, Computer
  • Mammography
  • Humans
  • Female
  • Breast Neoplasms
  • 1112 Oncology and Carcinogenesis
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Edwards, D. C., Lan, L., Metz, C. E., Giger, M. L., & Nishikawa, R. M. (2004). Estimating three-class ideal observer decision variables for computerized detection and classification of mammographic mass lesions. Med Phys, 31(1), 81–90. https://doi.org/10.1118/1.1631912
Edwards, Darrin C., Li Lan, Charles E. Metz, Maryellen L. Giger, and Robert M. Nishikawa. “Estimating three-class ideal observer decision variables for computerized detection and classification of mammographic mass lesions.Med Phys 31, no. 1 (January 2004): 81–90. https://doi.org/10.1118/1.1631912.
Edwards, Darrin C., et al. “Estimating three-class ideal observer decision variables for computerized detection and classification of mammographic mass lesions.Med Phys, vol. 31, no. 1, Jan. 2004, pp. 81–90. Pubmed, doi:10.1118/1.1631912.

Published In

Med Phys

DOI

ISSN

0094-2405

Publication Date

January 2004

Volume

31

Issue

1

Start / End Page

81 / 90

Location

United States

Related Subject Headings

  • Reproducibility of Results
  • Radiographic Image Interpretation, Computer-Assisted
  • Observer Variation
  • Nuclear Medicine & Medical Imaging
  • Neural Networks, Computer
  • Mammography
  • Humans
  • Female
  • Breast Neoplasms
  • 1112 Oncology and Carcinogenesis