Neural networks in ventilation-perfusion imaging: Part II. Effects of interpretive variability

PURPOSE: To evaluate the usefulness of a neural network developed by one physician and used by another. MATERIALS AND METHODS: Intra- and interobserver variability were analyzed in image categorization of ventilation-perfusion (V-P) scans. This information was used to estimate network performance when it was used by a physician who did not train the network. RESULTS: Network training was optimized by using input parameters that demonstrated both individually high correlations with pulmonary embolism and good reproducibility in multiple interpretations. CONCLUSION: Potential variability exists in the performance of a network when it is supplied with input data by different physicians. The clinical usefulness of a network depends heavily on the similarity of interpretive styles between the network trainer and the user.