基于云计算的医学图像检索系统

Distributed medical image retrieval system based on cloud computing

为了提高海量医学图像检索效率,提出一种基于云计算的医学图像检索系统。采用Brushlet变换和LBP算法提取医学示例图像的频域和空域特征,采用具有分布式、并行处理能力云计算将任务分配到各个工作节点共同完成医学图像检索,采用仿真实验对系统的性能进行测试。结果表明,相对于B/S单节点的医学图像检索系统,云计算的医学图像检索系统提高了图像检索速度和效率,尤其对于大规模医学图像检索优势更加明显。

In order to improve retrieval efficiency of medical image, this paper proposes a medical image retrieval system based on cloud computing. Domain and frequency domain features of medical image are extracted using Brushlet transform and LBP algorithm, and then the cloud computing which has distributed, parallel processing ability is used to assign tasks to each node to obtain retrieval results of medical image. Performance is tested and analyzed. The test results show that, compared with the single node of B/S medical image retrieval system, the proposed system has reduced the image store and retrieval time, and has improved the image retrieval speed. Especially it has more obvious advantages for the large scale medical image.