Performance Evaluation of Medical Image Similarity Analysis in a Heterogeneous Architecture

The volume of data has increased fast, particularly medical images, in big hospitals over the last years. This increase imposes a big challenge to medical specialists: the maintenance of high interpretation accuracy of image-based diagnosis. Computer-Aided Diagnosis software allied to the Content-Based Image Retrieval (CBIR) can provide decision support to specialists by allowing them to find images from a database that are similar to a reference image. However, a well known challenge of CBIR is the processing time that it takes to process all comparisons between the reference image and the image database. This paper proposes a performance evaluation of medical Image Similarity Analysis (ISA) in a heterogeneous single-, multi- and many-core architecture using the high performance parallel OpenCL framework. A CBIR algorithm was implemented to validate the proposal. The algorithm used a Lung Cancer image database with 131, 072 Computed Tomography scans, Texture Attributes for image features and Euclidean Distance for image comparison metrics. The results showed that the OpenCL parallelism can increase the performance of ISA, especially using the GPU, with speedups of 3x, 36x and 64x. The results also showed that it is not worth the use of GPU local memory for the Euclidean Distance metrics due to its low performance improvement and high implementation complexity in comparison to the GPU global memory. That being said, GPU is a safer medical CBIR approach than further distributed environments as clusters, cloud and grid computing because GPU usage does not require the patient data to be transfered to other machines.