NEURAL NETWORKS AS AN AID IN THE DIAGNOSIS OF LYMPHOCYTE-RICH EFFUSIONS

Neural network (NN) technology was applied to digital image analysis d ata for 112 Papanicolaou-fixed and -stained smears of lymphocyte-rich effusions (LREs). The smears were analyzed with an inexpensive image a nalysis system assembled in our laboratory. Several models were develo ped using backpropagation NN development software in an effort to opti mize classification of the LREs as reactive lymphocytosis or malignant lymphoma and to analyze the effects of various parameters on classifi cation rates. The greatest specificity and sensitivity of LRE classifi cation were achieved with NN models that consisted of 7 input neurons, including 5 morphometric and 2 densitometric variables, 10 hidden-lay er neurons and 1 output neuron. This NN architecture with a sigmoidal transfer function provided a true cross-validation rate of 89.3% of te sting data, with a sensitivity of 76.9%, specificity of 93.0% and shri nkage of 10.7%. The same NN architecture with a step transfer function provided a true cross-validation rate of 95.3%, sensitivity of 85.7%, specificity of 97.6% and shrinkage of 0%. The effects of various para meters, such as network size, shrinkage and ratio of sample size to in put layer size, on NN accuracy are discussed.