Radiology
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
QUICK SEARCH:   [advanced]


     

DOI: 10.1148/radiol.2403051096
This Article
Right arrow Abstract Freely available
Right arrow Full Text
Right arrow Full Text (PDF)
Right arrow Submit a response
Right arrow Alert me when this article is cited
Right arrow Alert me when eLetters are posted
Right arrow Alert me if a correction is posted
Right arrow Citation Map
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via HighWire
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Burnside, E. S.
Right arrow Articles by Leung, W. K.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Burnside, E. S.
Right arrow Articles by Leung, W. K.

Bayesian Network to Predict Breast Cancer Risk of Mammographic Microcalcifications and Reduce Number of Benign Biopsy Results: Initial Experience1

Elizabeth S. Burnside, MD, MPH, MS, Daniel L. Rubin, MD, MS, Jason P. Fine, PhD, Ross D. Shachter, PhD, Gale A. Sisney, MD and Winifred K. Leung, MD

1 From the Department of Radiology, University of Wisconsin Medical School, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (E.S.B., G.A.S., W.K.L.); Section on Medical Informatics, Stanford University, Stanford, Calif (D.L.R.); Department of Statistics and Department of Biostatistics and Medical Informatics, University of Wisconsin, Madison, Madison, Wis (J.P.F.); and Management Science and Engineering, Stanford University, Terman Engineering Center, Stanford, Calif (R.D.S.). Received June 29, 2005; revision requested August 31; revision received September 15; accepted October 4; final version accepted November 23. E.S.B. supported by the GE Research in Radiology Academic Fellowship. Address correspondence to E.S.B. (e-mail: es.burnside{at}hosp.wisc.edu).


Figure 1
View larger version (18K):

[in a new window]
  		Figure 1: Diagnoses in the disease node of the Bayesian network. LC = lobular carcinoma.

 

Figure 2
View larger version (27K):

[in a new window]
  		Figure 2: Structure of Bayesian network. Labeled ovals represent nodes; arrows (arcs) represent conditional dependence relationships. Each node is a data structure that contains conditional probability tables to quantify probabilistic relationships between variables. Ca++ = calcifications, FC = fibrocystic change, FHx = family history of breast cancer, HRT = hormone replacement therapy, LN = lymph node, P/A/O = present, absent, or obscured.

 

Figure 3
View larger version (16K):

[in a new window]
  		Figure 3: Graph shows ROC curves constructed from the probabilities of the radiologist alone and the Bayesian network (BN) alone and from the average of the probabilities for the radiologist and the Bayesian network. FPF = false-positive fraction (1 – specificity), TPF = true-positive fraction (sensitivity).

 




HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
RADIOLOGY RADIOGRAPHICS RSNA JOURNALS ONLINE
Copyright © 2006 by the Radiological Society of North America.