Skip to main content

Prediction of breast biopsy outcome using a likelihood ratio classifier and biopsy cases from two medical centers

Publication ,  Journal Article
Bilska-Wolak, AO; Floyd, CE; Lo, JY
Published in: Proceedings of SPIE - The International Society for Optical Engineering
September 15, 2003

Potential malignancy of a mammographie lesion can be assessed using the mathematically optimal likelihood ratio (LR) from signal detection theory. We developed a LR classifier for prediction of breast biopsy outcome of mammographie masses from BI-RADS findings. We used cases from Duke University Medical Center (645 total, 232 malignant) and University of Pennsylvania (496, 200). The LR was trained and tested alternatively on both subsets. Leave-one-out sampling was used when training and testing was performed on the same data set. When tested on the Duke set, the LR achieved a Received Operating Characteristic (ROC) area of 0.91 ± 0.01, regardless of whether Duke or Pennsylvania set was used for training. The LR achieved a ROC area of 0.85 ± 0.02 for the Pennsylvania set, again regardless of which set was used for training. When using actual case data for training, the LR's procedure is equivalent to case-based reasoning, and can explain the classifier's decisions in terms of similarity to other cases. These preliminary results suggest that the LR is a robust classifier for prediction of biopsy outcome using biopsy cases from different medical centers.

Duke Scholars

Published In

Proceedings of SPIE - The International Society for Optical Engineering

DOI

ISSN

0277-786X

Publication Date

September 15, 2003

Volume

5032 III

Start / End Page

1386 / 1391

Related Subject Headings

  • 5102 Atomic, molecular and optical physics
  • 4009 Electronics, sensors and digital hardware
  • 4006 Communications engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Bilska-Wolak, A. O., Floyd, C. E., & Lo, J. Y. (2003). Prediction of breast biopsy outcome using a likelihood ratio classifier and biopsy cases from two medical centers. Proceedings of SPIE - The International Society for Optical Engineering, 5032 III, 1386–1391. https://doi.org/10.1117/12.481349
Bilska-Wolak, A. O., C. E. Floyd, and J. Y. Lo. “Prediction of breast biopsy outcome using a likelihood ratio classifier and biopsy cases from two medical centers.” Proceedings of SPIE - The International Society for Optical Engineering 5032 III (September 15, 2003): 1386–91. https://doi.org/10.1117/12.481349.
Bilska-Wolak AO, Floyd CE, Lo JY. Prediction of breast biopsy outcome using a likelihood ratio classifier and biopsy cases from two medical centers. Proceedings of SPIE - The International Society for Optical Engineering. 2003 Sep 15;5032 III:1386–91.
Bilska-Wolak, A. O., et al. “Prediction of breast biopsy outcome using a likelihood ratio classifier and biopsy cases from two medical centers.” Proceedings of SPIE - The International Society for Optical Engineering, vol. 5032 III, Sept. 2003, pp. 1386–91. Scopus, doi:10.1117/12.481349.
Bilska-Wolak AO, Floyd CE, Lo JY. Prediction of breast biopsy outcome using a likelihood ratio classifier and biopsy cases from two medical centers. Proceedings of SPIE - The International Society for Optical Engineering. 2003 Sep 15;5032 III:1386–1391.

Published In

Proceedings of SPIE - The International Society for Optical Engineering

DOI

ISSN

0277-786X

Publication Date

September 15, 2003

Volume

5032 III

Start / End Page

1386 / 1391

Related Subject Headings

  • 5102 Atomic, molecular and optical physics
  • 4009 Electronics, sensors and digital hardware
  • 4006 Communications engineering