Construction of a Bayesian network for mammographic diagnosis of breast cancer

被引:109
作者
Kahn, CE [1 ]
Roberts, LM [1 ]
Shaffer, KA [1 ]
Haddawy, P [1 ]
机构
[1] UNIV WISCONSIN, DEPT ELECT ENGN & COMP SCI, MILWAUKEE, WI 53201 USA
关键词
Bayesian networks; artificial intelligence; breast cancer; mammography; computer-aided diagnosis; expert systems;
D O I
10.1016/S0010-4825(96)00039-X
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Bayesian networks use the techniques of probability theory to reason under uncertainty, and have become an important formalism for medical decision support systems. We describe the development and validation of a Bayesian network (MammoNet) to assist in mammographic diagnosis of breast cancer. MammoNet integrates five patient-history features, two physical findings, and 15 mammographic features extracted by experienced radiologists to determine the probability of malignancy. We outline the methods and issues in the system's design, implementation, and evaluation. Bayesian networks provide a potentially useful tool for mammographic decision support. (C) 1997 Elsevier Science Ltd.
引用
收藏
页码:19 / 29
页数:11
相关论文
共 59 条
[1]  
*AM COLL RAD, 1993, BREAST IM REP DAT SY
[2]  
ANDREASSEN M, 1987, P INT JOINT C ART IN, P366
[3]   MEDICAL EXPERT SYSTEMS BASED ON CAUSAL PROBABILISTIC NETWORKS [J].
ANDREASSEN, S ;
JENSEN, FV ;
OLESEN, KG .
INTERNATIONAL JOURNAL OF BIO-MEDICAL COMPUTING, 1991, 28 (1-2) :1-30
[4]  
Andreassen S., 1992, Artificial Intelligence in Medicine, V4, P227, DOI 10.1016/0933-3657(92)90029-O
[5]  
[Anonymous], 11 INT JOINT C ART I
[6]   BREAST-CANCER - PREDICTION WITH ARTIFICIAL NEURAL-NETWORK-BASED ON BI-RADS STANDARDIZED LEXICON [J].
BAKER, JA ;
KORNGUTH, PJ ;
LO, JY ;
WILLIFORD, ME ;
FLOYD, CE .
RADIOLOGY, 1995, 196 (03) :817-822
[7]   Artificial neural network: Improving the quality of breast biopsy recommendations [J].
Baker, JA ;
Kornguth, PJ ;
Lo, JY ;
Floyd, CE .
RADIOLOGY, 1996, 198 (01) :131-135
[8]  
BASSETT LW, 1992, RADIOL CLIN N AM, V30, P93
[9]   Variability in the interpretation of screening mammograms by US radiologists - Findings from a national sample [J].
Beam, CA ;
Layde, PM ;
Sullivan, DC .
ARCHIVES OF INTERNAL MEDICINE, 1996, 156 (02) :209-213
[10]   FAMILY HISTORY, AGE, AND RISK OF BREAST-CANCER - PROSPECTIVE DATA FROM THE NURSES HEALTH STUDY [J].
COLDITZ, GA ;
WILLETT, WC ;
HUNTER, DJ ;
STAMPFER, MJ ;
MANSON, JE ;
HENNEKENS, CH ;
ROSNER, BA ;
SPEIZER, FE .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 1993, 270 (03) :338-343