Performance Evaluation of Parallel Genetic Algorithm for Brain MRI Segmentation in Hadoop and Spark

Objectives: The radical growth of brain MRI data demands faster and accurate processing. To meet these demands, it is necessary to develop a design in cloud platform using distributed platforms. Methods/Analysis: In this paper, we introduce an architecture developed for the cloud using Apache Hadoop to segment the brain MRI images. The scanned MRI images are uploaded through either through web interface or mobile app to the system in the public cloud. The Parallel Genetic Algorithm (PGA) in the cloud system enabled with Hadoop or Spark is used to segment the given MRI images. Findings: The processing time taken for different size of data varying from 2GB to 10GB in a different number of clusters varying from one to five are denoted. This process has been implemented in both Apache Hadoop and Apache Spark. The time ranges from 12 to 24 secs approximately in Hadoop whereas the processing time has come down from 4 to 7 secs in Spark. First of all, the results prove that the network based applications for Medical Image Processing are outperformed by the cloud platform applications. Novelty/Improvement: Distributed Platforms have been used in Cloud environment for Brain MRI segmentation using Parallel Genetic Algorithm.