Abstract
This paper describes the evaluation of an application of the ARTMAP neural network model to the diagnosis of cancer from fine-needle aspirates of the breast. The network has previously demonstrated very high performance when used with high-quality data provided by an expert pathologist. New performance results are provided for its use with “noisy” data provided by an inexperienced pathologist. Additionally, ARTMAP supports the extraction of symbolic rules from a trained network and the validity of these autonomously-acquired rules is discussed. It is concluded that the symbolic rules provide an appropriate mapping of input features to category classes in the domain. However, the network in its present form is only suitable for use as a decision-support tool by a senior pathologist, since its performance deteriorated greatly with poor-quality data provided by a junior pathologist. The implications of the findings are discussed.
Preview
Unable to display preview. Download preview PDF.
References
G.A. Carpenter and S. Grossberg (1987) A Massively Parallel Architecture for a Self-Organizing Neural Pattern Recognition Machine, Computer Vision, Graphics and Image Processing, 37, 54–115.
G.A. Carpenter, S. Grossberg, N. Markuzon, J.H. Reynolds and D.B. Rosen (1992) Fuzzy ARTMAP: A Neural Network Architecture for Incremental Supervised Learning of Analog Multidimensional Maps, IEEE Transactions on Neural Networks, 3(5), 698–712.
G.A. Carpenter, S. Grossberg and J.H. Reynolds (1991) ARTMAP: Supervised Real-Time Learning and Classification of Nonstationary Data by a Self-Organizing Neural Network, Neural Networks, 4(5), 565–588.
G.A. Carpenter and A.H. Tan (1993) Rule Extraction, Fuzzy ARTMAP, and Medical Databases, Proceedings of the World Congress on Neural Networks, Volume I, 501–506.
S.S. Cross, T.J. Stephenson, Y. Diez, R.F. Harrison, J.C.E. Underwood and J. Downs (In Press) Diagnosis of Breast Fine Needle Aspirates Using Human Observations and a Multi-Layer Perceptron Neural Network, to appear in J. Pathol..
G. Cybenko (1989) Approximations by Superpositions of a Sigmoidal Function, Mathematics of Control, Signals and Systems, 2, 303–314.
J. Downs, R.F. Harrison and S.S. Cross (In Press) A Neural Network Decision Support Tool for the Diagnosis of Breast Cancer, to appear in Proceedings of the 10th Conference of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB-95). Amsterdam: IOS Press.
J. Downs, R.F. Harrison and R.L. Kennedy (1995) A Prototype Neural Network Decision Support Tool for the Diagnosis of Acute Myocardial Infarction, this volume.
S.A.C. Dundas, P.R. Sanderson, H. Matta and A.J. Shorthouse (1988) Fine Needle Aspiration of Palpable Breast Lesions: Results Obtained with Cytocentrifuge Preparation of Aspirates, Acta Cytologica, 32, 202–206.
C.W. Elston and I.O. Ellis (1990) Pathology and Breast Screening, Histopathology, 16, 109–118.
P.W. Hamilton, N. Anderson, P.H. Bartels and D. Thompson (1994) Expert System Support Using Bayesian Belief Networks in the Diagnosis of Fine Needle Aspiration Biopsy Specimens of the Breast, J. Clin. Pathol., 47, 329–336.
R.F. Harrison, C.P. Lim and R.L. Kennedy (1994) Autonomously Learning Neural Networks for Clinical Decision Support. In: E.C. Ifeachor and K.G. Rosen, (Eds.) Proceedings of the International Conference on Neural Networks and Expert Systems in Medicine and Healthcare (NNESMED-94), Plymouth, UK, 15–22.
F. Hayes-Roth, D.A. Waterman and D.B. Lenat (1983) Building Expert Systems. London: Addison-Wesley.
H.A. Heathfield, N. Kirkham, I.O. Ellis and G. Winstanley (1990) Computer Assisted Diagnosis of Fine Needle Aspirates of the Breast, J. Clin. Pathol., 43, 168–170.
C.P. Lim and R.F. Harrison (In Press) Modified Fuzzy ARTMAP Approaches Bayes Optimal Classification Rates: An Empirical Demonstration, to appear in Neural Networks.
J. Moody and C. Darken (1989) Fast Learning in Networks of Locally-Tuned Processing Units, Neural Computation, 1, 281–294.
J. Park and I. Sandberg (1991) Universal Approximation Using Radial Basis Function Networks, Neural Computation, 3, 246–257.
J.R. Quinlan (1986) Induction of Decision Trees, Machine Learning, 1, 81–106.
D. Rumelhart, G. Hinton and R. Williams (1986) Learning Representations by Back-Propagating Errors, Nature, 323, 533–536.
P.B. Silcocks (1983) Measuring Repeatability and Validity of Histological Diagnosis-A Brief Review with Some Practical Examples, J. Clin. Pathol., 36, 1269–1275.
R.D. Start, P.B. Silcocks, S.S. Cross and J.H.F. Smith (1992) Problems with Audit of a New Fine-Needle Aspiration Service in a District General Hospital, J. Pathol., 167, 141A.
G.Towell and J.W. Shavlik (1993) Extracting Refined Rules from Knowledge-Based Neural Networks, Machine Learning, 13(1), 71–101.
J.C.E. Underwood (1992) Tumours: Benign and Malignant. In: J.C.E. Underwood, (Ed.) General and Systematic Pathology, 223–246. Edinburgh: Churchill Livingstone.
CA.Wells, I.O. Ellis, H.D. Zakhour and A.R. Wilson (1994) Guidelines for Cytology Procedures and Reporting on Fine Needle Aspirates of the Breast, Cytopathology, 5, 316–334.
W.H. Wolberg and O.L. Mangasarian (1993) Computer-Designed Expert Systems for Breast Cytology Diagnosis, Anal. Quant. Cytol. Histol., 15, 67–74.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Downs, J., Harrison, R.F., Cross, S.S. (1995). Evaluating a neural network decision-support tool for the diagnosis of breast cancer. In: Barahona, P., Stefanelli, M., Wyatt, J. (eds) Artificial Intelligence in Medicine. AIME 1995. Lecture Notes in Computer Science, vol 934. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60025-6_141
Download citation
DOI: https://doi.org/10.1007/3-540-60025-6_141
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60025-1
Online ISBN: 978-3-540-49407-2
eBook Packages: Springer Book Archive