Related Experiment Videos
Focal liver disease: neural network-aided diagnosis based on clinical and laboratory data
K Rudzki1, M Hartleb, T Sadowski
1Department of Nuclear Medicine, Technical University of Silesia, Katowice, Pologne.
Objectives:
The purpose of this study was to evaluate the use of clinical and laboratory data in the diagnosis of benign or malignant focal liver disease.
Methods:
Diagnosis was made by artificial neural network (NN), a system of simple computing units connected in a specific structural network. Seven clinical and laboratory variables were retrospectively studied in 172 patients with a liver mass (93 benign, 79 malignant) detected with ultrasound. The diagnostic efficacy of NN was compared with a score based on the logistic regression model (Beaujon score).
Results:
Although the sensitivity of the Beaujon score and the neural network was similar (4 malignant tumors inversely classified), neural network-aided diagnosis was characterized by higher specificity and accuracy (respectively 98.9% vs 82.5%, P < 0.001, and 97.1% vs 88.4%, P < 0.002).
Conclusion:
In patients with a hepatic mass, neural network is a valuable method for differentiating malignant and benign tumors.