Abstract
This paper presents research into the application of the fuzzy ARTMAP neural network model to the diagnosis of cancer from fine-needle aspirates of the breast. Trained fuzzy ARTMAP networks are differently pruned so as to maximise accuracy, sensitivity and specificity. The differently pruned networks are then employed in a ‘cascade’ of networks intended to separate cases into ‘certain’ and ‘suspicious’ classes. This mimics the predictive behaviour of a human pathologist. The fuzzy ARTMAP model also provides symbolic rule extraction facilities and the validity of the derived rules for this domain is discussed. Additionally, results are provided showing the effects upon network performance of different input features and different observers. The implications of the findings are discussed.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Hayes-Roth F, Waterman DA, Lenat DB. Building Expert Systems. Addison-Wesley, London, 1983
Bounds DG, Lloyd PJ, Mathew BG. A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders. Neural Networks 1990; 3: 583–591
Egmont-Petersen M, Talmon JL, Brender J, McNair P. On the quality of neural network classifiers. Artif Intell in Medicine 1994; 6: 359–381
Harrison RF, Marshall SJ, Kennedy RL. A connectionist aid to the early diagnosis of myocardial infarction. Proc Third Euro Conf Artif Intell in Medicine, Maastricht, 1991: 119–128
Apolloni B, Avanzini G, Cesa-Bianci N, Ronchini G. Diagnosis of epilepsy via backpropagation. Proc Int Joint Conf Neural Networks 1990: 571–574
Pizzi N, Choo LP, Mansfield J, Halliday WC, Mantsch HH, Somorjal RL. Neural network classification of infrared spectra of control and Alzheimer's diseased tissue. Artif Intell in Medicine 1997; 7: 67–79
Cross SS, Harrison RF, Kennedy RL. Introduction to Neural networks. Lancet 1995; 346: 1075–1079
Baxt WG. Application of artificial neural networks to clinical medicine. Lancet 1995; 346: 1135–1138
Dybowski R, Gant V. Artificial neural networks in pathology and medical laboratories. Lancet 1995; 346: 1203–1207
Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature 1986; 323: 533–536
Moody J, Darken C. Fast learning in networks of locally-tuned processing units. Neural Computation 1989; 1: 281–294
Cybenko G. Approximations by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems 1989; 2: 303–314
Park J, Sandberg I. Universal approximation using radial basis function networks. Neural Computation 1991; 3: 246–257
Richard M, Lippman R. Neural network classifiers estimate Bayesian a posteriori probabilities. Neural Computation 1991; 3: 461–483
Carpenter G, Grossberg S. The ART of adaptive pattern recognition by a self-organising neural network. Computer 1988; 21: 77–88
Sharkey NE, Sharkey AJC. An analysis of catastrophic interference. Connection Science 1995; 7: 301–329
Ma Z, Harrison RF. GR2: a hybrid knowledge-based system using general rules. Proc Int Joint Conf Artif Intell, Montreal, 1995: 488–493
Downs J, Harrison RF, Kennedy RL, Cross SS. Application of the fuzzy ARTMAP neural network model to medical pattern classification tasks. Artif Intell in Medicine 1996; 8: 403–428
Carpenter G, Grossberg S, Reynolds J. ARTMAP: Supervised real-time learning and classification of non-stationary data by a self-organizing neural network. Neural Networks 1991; 4: 565–588
Underwood JCE. Tumours: benign and malignant. In: Underwood JCE (ed), General and Systematic Pathology, Churchill Livingstone, Edinburgh, 1992. pp. 223–246
Elston CW, Ellis IO. Pathology and breast screening. Histopathology 1990; 16: 109–118
Wolberg WH, Mangasarian OL. Computer-designed expert systems for breast cytology diagnosis. Analytical and Quantitative Cytology and Histology 1993; 15: 67–74
Start RD, Silcocks PB, Cross SS, Smith JHF. Problems with audit of a new fine-needle aspiration service in a district general hospital. Pathology 1992; 167: 141A
Wells CA, Ellis IO, Zakhour HD, Wilson AR. Guidelines for cytology procedures and reporting on fine needle aspirates of the breast. Cytopathology 1994; 5: 316–334
Heathfield HA, Kirkham N, Ellis IO, Winstanley G. Computer assisted diagnosis of fine needle aspirates of the breast. J Clinical Pathology 1990; 43: 168–170
Hamilton PW, Anderson N, Bartels PH, Thompson D. Expert system support using Bayesian belief networks in the diagnosis of fine needle aspiration biopsy specimens of the breast. J Clinical Pathology 1994; 47: 329–336
Downs J, Harrison RF, Cross SS. A neural network decision support tool for the diagnosis of breast cancer. In: Hallam J (ed), Hybrid Problems, Hybrid Solutions, IOS Press, Amsterdam, 1995, pp. 51–60
Downs J, Harrison RF, Cross SS. Evaluating a neural network decision-support tool for the diagnosis of breast cancer. Proc Fifth Euro Conf Artif Intell in Medicine (AIME-95), Pavia, Italy, 1995: 239–250
Carpenter G, Grossberg S. A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision, Graphics and Image Processing 1987; 37: 54–115
Grossberg S. Competitive learning: from interactive activation to adaptive resonance. Cognitive Sci 1987; 11: 23–63
Carpenter G. Distributed activation, search and learning by ART and ARTMAP neural networks. Research Report CAS/CNS-96-006, University of Boston, Boston, USA, 1996
Carpenter G, Grossberg S, Rosen D. Fuzzy ART: Fast, stable learning and categorisation of analogue patterns by an adaptive resonance system. Neural Networks 1991; 4: 759–771
Carpenter G, Grossberg S, Markuzon S, Reynolds J, Rosen D. Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multi-dimensional maps. IEEE Trans Artif Neural Networks 1992; 3: 698–712
Kasuba T. Simplified fuzzy ARTMAP. AI Expert 1993; 8: 18–25
Marriott S, Harrison RF. A modified fuzzy ARTMAP architecture for the approximation of noisy mappings. Neural Networks 1995; 8: 619–642
Towell GG, Shavlik JW. Extracting refined rules from knowledge-based neural networks. Machine Learning 1993; 13: 71–101
Carpenter G, Tan A-H. Rule extraction, fuzzy ART-MAP and medical databases. Proc World Congress on Neural Networks 1993: 501–506
Downs J, Harrison RF, Kennedy RL. A prototype neural network decision-support tool for the diagnosis of acute myocardial infarction. Proc Fifth Euro Conf Artif Intell in Medicine (AIME-95), Pavia, Italy, 1995: 355–366
Trott PA. Aspiration cytodiagnosis of the breast. Diagnostic Oncology 1991; 1: 79–87
Bottles K, Chan JS, Holly EA, Chiu S, Miller TR. Cytologic criteria for fibroadenoma. Am J Clinical Pathology 1988; 89: 707–713
Quincey C, Raitt N, Bell J, Ellis IO. Intracytoplasmic lumina — a useful diagnostic feature of adenocarcinomas. Histopathology 1991; 19: 83–87
Stork DG. Self-organisation, pattern recognition and adaptive resonance networks. J Neural Network Comput 1989; 1: 26–42
Bland M. An Introduction to Medical Statistics, Oxford University Press, Oxford, 1987
Goodman PH, Kaburlasos VG, Egbert DD, Carpenter G, Grossberg S, Reynolds J, Rosen D et al. Fuzzy ARTMAP neural network compared to linear discriminant analysis prediction of the length of hospital stay in patients with pneumonia. In: Marks RJ (ed), Fuzzy Logic Technology and Applications. IEEE Technical Activities Board, Piscataway, 1994: 424–429
Hamilton PW, Bartels PH, Montironi R, Anderson N, Thompson D. Improved diagnostic decision-making in pathology: do inference networks hold the key? J Pathology 1995; 175: 1–6
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Downs, J., Harrison, R.F. & Cross, S.S. A decision support tool for the diagnosis of breast cancer based upon Fuzzy ARTMAP. Neural Comput & Applic 7, 147–165 (1998). https://doi.org/10.1007/BF01414167
Issue Date:
DOI: https://doi.org/10.1007/BF01414167