Training Strategy for Performance Improvement in Computer-Assisted Detection of Lesions: Based on Multi-institutional Study in Teleradiology Environment

The performance of computer-assisted detection (CAD) software depends on quality and quantity of the dataset used for supervised learning. If the data characteristics in development and practical use are different, the performance of CAD software will be degraded. Therefore, it is necessary to continuously collect data for supervised learning in practical use, and to improve CAD software by retraining with the collected data. For this purpose, we developed a web-based CAD software processing and evaluation platform (CIRCUS CS), which provides on-line processing of CAD software and interfaces to evaluate the results obtained from CAD software. For a multi-institutional study, we implemented CIRCUS CS into a teleradiology environment, which has been in practical use since September 2011. In this study, we investigated the performance improvement of CAD software for each institution based on retraining through a simulation-based study. According to the results, the performance of CAD software for each institution was improved by retraining.