Finding the optimal picture archving and communciation system (PACS) architecture: A comparison of three PACS designs

Purpose: At present, there are two basic picture archiving and communicatio n system (PACS) architectures: centralized with a central cache and control ler, and distributed with a distributed cache and central controller. A thi rd architecture proposed here is an autonomous one with a distributed cache end no controller. This report will investigate the performance las measur ed be central processing unit [CPU] and network load, scalability, and exam ination retrieval and display latency) of these three types. Methods: The d istributed PACS architecture will be simulated using an IMPAX R3.5 (AGFA, R idgefield Park, NJ) PACS, while the centralized design will be simulated us ing an IMPAX R4 (AGFA) PACS. The autonomous system will be designed and imp lemented in-house. The autonomous system consists of two types of entities: basic components such as acquisition gateways, display stations, and long- term archives, and registry servers, which store global state information a bout the individual PACS components. The key feature of the autonomous syst em will be the replacement of the central PACS controller by the registry s ervers. In this scenario the registry servers monitor the interactions betw een the components, but do not directly govern them. Instead each component will contain the application logic it requires and will use the state info rmation from the registry servers to take the appropriate action, such as r outing images, prefetching studies, and expiring images from near line cach e. In addition the routing of examinations will be optimized to reduce the duplication of image data. Display stations will be categorized by specialt y (neuroradiology, pediatrics, chest, etc) and will retrieve studies for di splay on demand from intermediate servers dedicated to the corresponding sp ecialty. Studies will be routed only to the intermediate servers and not to display stations. Results: By distributing the application logic, an auton omous PACS architecture can provide increased fault tolerance and therefore increased uptime. In addition, the lack of a central controller and the us e of intermediate servers improve the scalability of the system, as well as reduce CPU and network loads. Copyright (C) 2001 by W.B. Saunders Company