Abstract
Using abdominal ultrasonographic data and laboratory tests, radiologists often find differential diagnoses of hepatic masses difficult. A computerized second opinion would be especially helpful for clinicians in diagnosing liver cancer because of the difficulty of such diagnoses. A back-propagation neural network was designed to diagnose five classifications of hepatic masses: hepatoma, metastic carcinoma, abscess, cavernous hemangioma, and cirrhosis. The network input consisted of 35 numbers per patient case that represented ultrasonographic data and laboratory tests. The network architecture had 35 elements in the input layer, two hidden layers of 35 elements each, and 5 elements in the output layer. After being trained to a learning tolerance of 1%, the network classified hepatic masses correctly in 48 of 64 cases. An accuracy of 75% is higher than the 50% scored by the average radiology resident in training but lower than the 90% scored by the typical board-certified radiologist. When sufficiently sophisticated, a neural network may significantly improve the analysis of hepatic-mass radiographs.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bryan, P.J., Dinn, W.M., Grossman, Z.D., Wistow, B.W., McAfee, J.G., Kieffer, S.A., Correlation of computed tomography, gray scale ultrasonography, and radionuclide imaging of the liver in detecting space-occupying processes.Radiology 124:387–393, 1977.
Nelson, M.M., and Illingworth, W.T.,A Practical Guide to Neural Nets. Reading, MA: Addison-Wesley, 1991.
Sugarbaker, P.H., and Kemeny, N., Management of metastatic liver cancer.Adv. Surgery 22:1–55, 1988.
Sugarbaker, P.H., Surgical decision making for large bowel cancer metastatic to the liver.Radiology 174:621–626, 1990.
Adson, M.A., Van Heerden, J.A., Adson, M.H., Wayner, J.S., Ilstrup, D.M., Resection of hepatic metastases from colorectal cancer.Arch. Surgery 119:647–651, 1984.
Malt, R.A., Current concepts: Surgery for hepatic neoplasms.New Eng. J. Med. 313:1591–1596, 1985.
Ferrucci, J.T., Liver tumor imaging: current concepts.Amer. J.l Radiol. 155:473–484, 1990.
Boone, J.M., Gross, G.W., and Greco-Hunt, V., Neural networks in radiologic diagnosis.Invest. Radiol. 25:1012–1016, 1990.
Gross, G.W., Boone, J.M., Greco-Hunt, V., and Greenberg, B., Neural networks in radiologic diagnosis. II. Interpretation of neonatal chest radiographs.Invest. Radiol. 25:1017–1023, 1990.
Maclin, P.S., Dempsey, J., Brooks, J., and Rand, J., using neural networks to diagnose renal cancer.J. Med. Syst. (U.S.), 15(1):11–19, 1991.
Mulsant, B.H., A neural network as an approach to clinical diagnosis.MD Comp 7(1):25–36, 1990.
Frenger, P., The silicon synapse or neural net computing.Biomed. Sci. Instrum. 25:267–73, 1989.
Braham, R., and Hamblen, J.O., On the behavior of some associative neural networks.Biol. Cybernetics (West Germany), 2:145–151, 1988.
Crick, F., Neural networks and REM sleep.Biosci. Rep. (England) 8(6):531–535, 1988.
Shadmehr, R., and D'Argenio, D.Z., A neural network for nonlinear Bayesian estimation in drug therapy.Neural Comput. 2:216–225, 1990.
Lippmann, R.P., Review of neural networks for speech recognition.Neural Comput. 1:1–38, 1989.
Elman, J.L., and Zipser, D., Learning the hidden structure of speech.J. Acoustical Soc. Amer. 83(4):1615–26, 1988.
Poli, R., Cagnoni, S., Livi, R., Coppini, G., Valli, G., A neural network expert system for diagnosing and treating hypertension.Computer 24:3, 64–71, 1991.
Piraino, D.W., Amartur, S.C., Richmond, B.J., Schils, J.P., Thome, J.M., Belhobek, G.H., and Schlucter, M.D., Application of an artificial neural network in radiographic diagnosis.J. Digital Imaging 4(4):226–232, 1991.
Borman, S., Neural network applications in chemistry begin to appear.Chem Engineering News 67:24–28, 1989.
Simpson, P.K.,Artificial Neural Systems. New York: Pergamon Press, 1990.
Dyke, R., NeuralWorks Professional II review.Neural Network News. Atlanta: AIWeek Inc., 1(3), 5, 1989.
Blum, Adam, Bidirectional Associative Memory Systems in C + +.Dr. Dobb's J. 15(4), 16–26, 1990.
Bounds, David G., and Lloyd, Paul J. A mltilayer perception network for the diagnosis of low back pain.Proceedings of the IEEE International Conference on Neural Networks Vol. II. 483–489, 1988.
Guha, A., Using small multilayer networks to search real hyperspaces. Neural Networks Supplement:INNS Abstracts, 1:337, 1988.
BrainMaker Users Guide and Reference Manual (4th edition), Sierra Madre, CA: California Scientific Software, 1990.
Rumelhart, D.E., McClelland, J.L., and PDP Research Group,Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Vols. 1, 2. Cambridge, MA, MIT Press, 1986.
McClelland, J.L., and Rumelhart, D.E.,Explorations in Parallel Distributed Processing Cambridge, MA: MIT Press, 1988.
Wasserman, P.D.,Neural Computing: Theory Pract. New York: Van Nostrand Reinhold, 1989.
Neurocomputers 4(4):5, 1990. (Newsletter published monthly by Gallifrey Publishing, P.O. Box 155, Vicksburg, MI 49097. Name later changed toSixth Generation Systems newsletter.)
Asad, N., Doi, K., MacMahon, H.,et al. Potential usefulness of an artificial neural network for differential diagnosis of interstitial lung disease: pilot study.Radiology 177:857–860, 1990.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Maclin, P.S., Dempsey, J. Using an artificial neural network to diagnose hepatic masses. J Med Syst 16, 215–225 (1992). https://doi.org/10.1007/BF01000274
Issue Date:
DOI: https://doi.org/10.1007/BF01000274