Abstract
While artificial brains are in the realm of science fiction, artificial neural networks (ANNs) are scientific facts. An artificial neural network is a computational structure modeled somewhat on the neural structure of the brain; both have many highly interconnected processing elements. These biologically inspired processing elements are taught by feeding examples until the results are acceptable. In the past 5 years, neural networks have become successful in providing meaningful second opinions in clinical diagnosis. In our research, a prototype artificial neural network was trained on numeral ultrasound data of 52 actual cases and then correctly identified renal cell carcinoma from renal cysts and other conditions without diagnostic errors. Our nonlinear artificial neural network was trained on software using the standard backpropagation paradigm on a 80386 microcomputer. Our ANN learned from ultrasound data in 52 cases (17 malignant, 30 cysts, and 5 other) at a Memphis hospital. The trained prototype performed without error on 47 cases which were not in the data used for training. This prototype must be validated by extending this study to more cases.
Similar content being viewed by others
References
Wild, J.J., The use of ultrasonic pulses for the measurement of biologic tissues and the detection of tissue density chances.Surgery 27:183, 1950.
Amendola, M.A., Bree, R., Pollack, H.,et al. Small renal cell carcinomas: Resolving a diagnostic dilemma.Radiology 166(3):637–641, 1988.
Talamo, T.S., and Shonnard, J.W., Small renal adenocarcinomas with metastases.J. Urol. 124:132–134, 1980.
Walter, T.A., Berger, C.S., and Sandberg, A., The cytogenetics of renal tumors. Where do we stand, where do we go?Cancer Genet. Cytogenet. 43(1):15–34, 1989.
Fallon, B., Renal cancer associated with acquired cystic disease of the kidney and chronic renal failure.Semin. Urol. 7(4):228–36, 1989.
Clayman, R.V., Surya, V., Mill, R.,et al. Pursuit of the renal mass: Is ultrasound enough?Am. J. Med. 77:218–223, 1984.
intec Customer Support Newsletter: December 1989,intec, P.O. Box 27561, Tempe AZ 85285.
Roth, A., Interview with Igor Aleksander.Neural Network News. AIWeek Inc., Atlanta, November 1(3):6, 1989.
DeRoach, J.N., Neural networks—An artificial intelligence approach to the analysis of clinical data.Austr. Phys. Eng. Sci. Med. 12(2):100–106, 1989.
Mathew, B., Norris, D., Hendry, D., and Waddell, G., Artificial intelligence in the diagnosis of low back pain and sciatica.Spine 1991, In press.
Bounds, D.G., and Lloyd, P.J., A multilayer perceptron network for the diagnosis of low back pain.Proceedings of the IEEE International Conference on Neural Networks Vol. II, 1988, pp. 483–489.
McGregor, M.J., Flores, T.P., and Sternberg, M.J., Prediction of beta-turns in proteins using neural networks.Protein Eng. (England) (7):521–6, 1989.
Holley, L.H., and Karplus, M., Protein secondary structure prediction with a neural network.Proc. Natl. Acad. Sci. USA 86(1):152–156, 1989.
Bohr, H., Bohr, J., Brunak, S.,et al. Protein secondary structure and homology by neural networks.FEBS (Netherlands) 241:223–8, 1988.
Qia, N., and Sejnowski, T.J., Predicting the secondary structure of globular proteins using neural network models.J. Mol. Biol. 202(4):865–84, 1988.
Kuperstein, M., Neural model of adaptive hand-eye coordination for single postures.Science 239(4845):1308–11, 1988.
Elman, J.L., and Zipser, D., Learning the hidden structure of speech.J. Acoust. Soc. Am. 83(4):1615–26, 1988.
Mulsant, B.H., A neural network as an approach to clinical diagnosis.MD Comput. 7(1):25–36, 1990.
LeCun, Y., Modèle connexionistes de l'apprentissage: Thèse de doctorat. Universite' de Paris, Paris, 1987.
Baxt, W.G., Use of an artificial neural network for data analysis in clinical decision-making: The diagnosis of acute coronary occlusion.Neur. Comput. 2:480–489, 1990.
Weiss, S.M., and Kulikowski, C.A.,Computer Systems That Learn Morgan Kaufmann, Palo Alto, Calif., 1991, pp. 99–102.
Hartzberg, J., Stanley, J., and Lawrence, M.,BrainMaker Users' Guide and Reference Manual (fourth edition), Sierra Madre, Calif., California Scientific Software, Sierra Madre, Calif, 1990. Chapter 4: Designing Neural Networks, pp. 79–108.
Daniels, W.W., Hartman, G.W., Witten, D.M., Farrow, G.M., and Kelalis, P.P., Calcified renal masses: a review of ten years experience at the Mayo Clinic.Radiology 103:503–508, 1972.
Neurocomputers newsletter. Gallifrey Publishing, Vicksburg, Michigan, 4(4):5, 1990.
Baum, E., and Wilczek, F., Supervised learning of probability distributions by neural networks.Proceedings of the 1987 IEEE Conference on Neural Information Processing Systems—Natural and Synthetic American Institute of Physics, New York, 52–61, 1988.
Dietz, W., Kiech, E., and Ali, M., Pattern-based fault-diagnosis using neural networks.First International Conference on Industrial and Engineering Applications of AI and Expert Systems University of Tennessee Space Institute, Chattanooga, Tenn., 13–23, 1988.
Guha, A., Using small multilayer networks to search real hyperspaces. Neural Networks Supplement.INNS Abstracts 1:337, 1988.
Rumelhart, D.E., McClelland, J.L., and PDP Research Group:Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vols. 1, 2, MIT Press, Cambridge, 1988.
Nelson, M.M., and Illingworth, W.T.,A Practical Guide to Neural Nets Addison-Wesley, Reading, Mass., 1991.
Wasserman, P.D.,Neural Computing: Theory and Practice Van Nostrand Reinhold, New York, 1989.
Simpson, P.K.,Artificial Neural Systems Pergamon Press, New York, 1990.
Bailey, D., and Thompson, D., How to develop neural-network applications.AI Expert 5(6):38–47, 1990.
Stanley, J.,Introduction to Neural Networks. California Scientific Software, Sierra Madre, Calif., 1989.
Morse, K.G., In an upscale world.Byte 14(8):222–223, 1989.
Makhoul, J., Artificial neural networks.Invest. Radiol. 25:748–750, 1990.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Maclin, P.S., Dempsey, J., Brooks, J. et al. Using neural networks to diagnose cancer. J Med Syst 15, 11–19 (1991). https://doi.org/10.1007/BF00993877
Issue Date:
DOI: https://doi.org/10.1007/BF00993877