A Bayesian Belief Network Model for Breast Cancer Diagnosis

S. Wongthanavasu ()
Additional contact information
S. Wongthanavasu: Khon Kaen University

A chapter in Operations Research Proceedings 2010, 2011, pp 3-8 from Springer

Abstract: Abstract A statistical influence diagram, called Bayesian Belief Network (BBN), is investigated in modeling the medical breast cancer diagnosis. The proposed BBN is constructed under supervision by medical experts. Four types of datasets, namely, historic biodata, physical findings, indirect and direct mammographic findings are taken into consideration for modeling the BBN. Biodata are comprised of age, number of relatives having breast cancer, age at first live birth and age at menarche. Physical findings consist of pain, axilla, inflame and nipple discharge. Indirect mammo-graphic data are breast composition. Direct mammographic findings are information obtained by mammogram image processing using the proposed cellular automata algorithms. A dataset is collected in real case of the breast cancer patients who come to get serviced at Srinakarind Hospital, Khon Kaen University, Thailand. A dataset of 500 cases is used throughout for model’s performance evaluation. In this regard, an 80 % of data is used for training the model, while the rest of 20 % is utilized for testing. The trained BBN model is tested on 100 patients consisting of 50, 25 and 25 for normal, benign and malignant patients, respectively. The proposed BBN provides the promising results reporting the 96.5 % of accuracy in the diagnosis. In addition, 5-fold and 10-fold cross-validation approach are implemented, the proposed BBN reports the promising results. It provides 96.2 and 97.4 percentages of accuracy, respectively.

Keywords: Breast Cancer; Support Vector Machine; Bayesian Network; Breast Cancer Diagnosis; Cellular Automaton (search for similar items in EconPapers)
Date: 2011
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:oprchp:978-3-642-20009-0_1

Ordering information: This item can be ordered from
http://www.springer.com/9783642200090

DOI: 10.1007/978-3-642-20009-0_1

Access Statistics for this chapter

More chapters in Operations Research Proceedings from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().