Abstract
Bayesian networks use the techniques of probability theory to reason under conditions of uncertainty. We investigated the use of Bayesian networks for radiological decision support. A Bayesian network for the interpretation of mammograms (MammoNet) was developed based on five patient-history features, two physical findings, and 15 mammographic features extracted by experienced radiologists. Conditional-probability data, such as sensitivity and specificity, were derived from peer-reviewed journal articles and from expert opinion. In testing with a set of 77 cases from a mammography atlas and a clinical teaching file, MammoNet performed well in distinguishing between benign and malignant lesions, and yielded a value of 0.881 (+/- 0.045) for the area under the receiver operating characteristic curve. We conclude that Bayesian networks provide a potentially useful tool for mammographic decision support.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Andreassen S., Jensen F. V., Olesen K. G. Medical expert systems based on causal probabilistic networks. Int J Biomed Comput. 1991 May-Jun;28(1-2):1–30. doi: 10.1016/0020-7101(91)90023-8. [DOI] [PubMed] [Google Scholar]
- D'Orsi C. J., Getty D. J., Swets J. A., Pickett R. M., Seltzer S. E., McNeil B. J. Reading and decision aids for improved accuracy and standardization of mammographic diagnosis. Radiology. 1992 Sep;184(3):619–622. doi: 10.1148/radiology.184.3.1509042. [DOI] [PubMed] [Google Scholar]
- D'Orsi C. J., Kopans D. B. Mammographic feature analysis. Semin Roentgenol. 1993 Jul;28(3):204–230. doi: 10.1016/s0037-198x(05)80080-x. [DOI] [PubMed] [Google Scholar]
- Feig S. A. Decreased breast cancer mortality through mammographic screening: results of clinical trials. Radiology. 1988 Jun;167(3):659–665. doi: 10.1148/radiology.167.3.3283836. [DOI] [PubMed] [Google Scholar]
- Getty D. J., Pickett R. M., D'Orsi C. J., Swets J. A. Enhanced interpretation of diagnostic images. Invest Radiol. 1988 Apr;23(4):240–252. doi: 10.1097/00004424-198804000-00002. [DOI] [PubMed] [Google Scholar]
- Haddawy P., Kahn C. E., Jr, Butarbutar M. A Bayesian network model for radiological diagnosis and procedure selection: work-up of suspected gallbladder disease. Med Phys. 1994 Jul;21(7):1185–1192. doi: 10.1118/1.597400. [DOI] [PubMed] [Google Scholar]
- Hall F. M., Storella J. M., Silverstone D. Z., Wyshak G. Nonpalpable breast lesions: recommendations for biopsy based on suspicion of carcinoma at mammography. Radiology. 1988 May;167(2):353–358. doi: 10.1148/radiology.167.2.3282256. [DOI] [PubMed] [Google Scholar]
- Metz C. E. ROC methodology in radiologic imaging. Invest Radiol. 1986 Sep;21(9):720–733. doi: 10.1097/00004424-198609000-00009. [DOI] [PubMed] [Google Scholar]
- Suermondt H. J., Cooper G. F. An evaluation of explanations of probabilistic inference. Comput Biomed Res. 1993 Jun;26(3):242–254. doi: 10.1006/cbmr.1993.1017. [DOI] [PubMed] [Google Scholar]
- Teach R. L., Shortliffe E. H. An analysis of physician attitudes regarding computer-based clinical consultation systems. Comput Biomed Res. 1981 Dec;14(6):542–558. doi: 10.1016/0010-4809(81)90012-4. [DOI] [PubMed] [Google Scholar]
- Tombropoulos R., Shiffman S., Davidson C. A decision aid for diagnosis of liver lesions on MRI. Proc Annu Symp Comput Appl Med Care. 1993:439–443. [PMC free article] [PubMed] [Google Scholar]
- Wingo P. A., Tong T., Bolden S. Cancer statistics, 1995. CA Cancer J Clin. 1995 Jan-Feb;45(1):8–30. doi: 10.3322/canjclin.45.1.8. [DOI] [PubMed] [Google Scholar]
- Wu Y., Giger M. L., Doi K., Vyborny C. J., Schmidt R. A., Metz C. E. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology. 1993 Apr;187(1):81–87. doi: 10.1148/radiology.187.1.8451441. [DOI] [PubMed] [Google Scholar]