The reliability issue of computer-aided breast cancer diagnosis
Document Type
Article
Department or Administrative Unit
Computer Science
Publication Date
8-2000
Abstract
This paper introduces a number of reliability criteria for computer-aided diagnostic systems for breast cancer. These criteria are then used to analyze some published neural network systems. It is also shown that the property of monotonicity for the data is rather natural in this medical domain, and it has the potential to significantly improve the reliability of breast cancer diagnosis while maintaining a general representation power. A central part of this paper is devoted to the representation/narrow vicinity hypothesis, upon which existing computer-aided diagnostic methods heavily rely. The paper also develops a framework for determining the validity of this hypothesis. The same framework can be used to construct a diagnostic procedure with improved reliability.
Recommended Citation
Kovalerchuk, B., Triantaphyllou, E., Ruiz, J. F., Torvik, V. I., & Vityaev, E. (2000). The Reliability Issue of Computer-Aided Breast Cancer Diagnosis. Computers and Biomedical Research, 33(4), 296–313. https://doi.org/10.1006/cbmr.2000.1546
Journal
Computers and Biomedical Research
Rights
Copyright © 2000 by Academic Press
Comments
This article was originally published in Computers and Biomedical Research. The full-text article from the publisher can be found here.
Due to copyright restrictions, this article is not available for free download from ScholarWorks @ CWU.