"The Reliability Issue of Computer-Aided Breast Cancer Diagnosis,"
Computers and Biomedical Research,
Vol. 33, No. 4 (August 2000), pp. 296-313, 2000.
B. Kovalerchuk, E. Triantaphyllou, J.F. Ruiz, V.I. Torvik, and E. Vityaev
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 on
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.
Neural networks, machine learning, discriminant analysis, data
monotonicity, computer-aided diagnostic systems, reliability of
diagnosis, representation/narrow vicinity hypothesis.