Scott J A, Fisher R E, Palmer E L
Department of Radiology, Massachusetts General Hospital, Boston 02114, USA.
Radiology. 1996 Mar;198(3):707-13. doi: 10.1148/radiology.198.3.8628858.
To evaluate the usefulness of a neural network developed by one physician and used by another.
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.
Network training was optimized by using input parameters that demonstrated both individually high correlations with pulmonary embolism and good reproducibility in multiple interpretations.
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.
评估由一位医生开发并由另一位医生使用的神经网络的实用性。
分析了通气灌注（V-P）扫描图像分类中的观察者内和观察者间变异性。该信息用于估计未训练该网络的医生使用该网络时的网络性能。
通过使用与肺栓塞个体相关性高且在多次解读中具有良好可重复性的输入参数，优化了网络训练。
当不同医生为网络提供输入数据时，网络性能存在潜在变异性。网络的临床实用性在很大程度上取决于网络训练者和使用者之间解释风格的相似性。
