An efficient Hadoop‐based brain tumor detection framework using big data analytic. (14th September 2020)

• Record Type: Journal Article
• Authors: Kaur Chahal, Prabhjot; Pandey, Shreelekha
• Other Names: Aujla Gagangeet Singh guestEditor.; Prodan Radu guestEditor.; Rawat Danda B. guestEditor.
• Is Part Of: Software, practice & experience. Volume 52:Number 3(2022)
• Page Start: 805
• Page End: 818
• Publication Date: 2020-09-14
• Subjects: brain tumor -- computer aided detection -- Hadoop -- magnetic resonance images -- Matlab distributed computing server -- segmentation; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.2899
• Languages: English
• ISSNs: 0038-0644

Abstract

Abstract: The exponential increase of brain MR image data in the medical imaging field requires faster and accurate segmentation of tumor. The computer aided detection systems acting as a second option to experts, radiologists, and surgeons needs to be swift enough to handle parallelism. However, handling of massive MR data for segmentation with high accuracy and low processing time is significant concern of any framework. In this article, distributed platforms for brain tumor segmentation using hybrid weighted fuzzy approach integrated with Matlab Distributed Computing Server and Hadoop has been proposed. The approach is based on the fuzzification of the pixel values to achieve more meaningful clusters by grouping of large data into similar clusters. The article focuses on analyzing the performance of varying sized data sets using hybrid fuzzy clustering in MapReduce on Hadoop to deal with huge MR brain data cross clusters of commodity computers. For experimentation varying size of DICOM data set is processed through different number of clusters to compare the read, write, and processing time on each node. The read and write operation time elevates as the data size increasing is floated to multinode. However, the processing time of the proposed approach turns to be 35 min on single, whereas 3‐node clusters process the same data set (215 MB) in 3.4 min. Furthermore, increasing the data set to 7.3 GB the 3‐node cluster performs in 235.4 min which is greatly reduced from single node processing time of 2085.2 min.