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

Augustine, D. Peter; Raj, Pethuru

doi:10.17485/ijst/2016/v9i48/91373

Cited by 5 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…24,25 In 2016, MR brain tumor segmentation is evaluated using parallel genetic approach (PGA) in Hadoop and Spark tools for varying data sizes. 26 The novel approach is in the cloud environment; therefore, an effective lossless compression methodology for transferring of brain data is used to have communication with the cloud. For the experimentation Connectome project data set is taken of sizes ranging from 2 to 10 GB which are processed through 1 to 5 cluster nodes.…”

Section: Related Workmentioning

confidence: 99%

An efficient Hadoop‐based brain tumor detection framework using big data analytic

Chahal

Pandey

2020

Softw Pract Exp

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

An efficient Hadoop‐based brain tumor detection framework using big data analytic

Chahal

Pandey

2020

Softw Pract Exp

View full text Add to dashboard Cite

show abstract

“…Clustering in a multi-core architecture starts with dividing the image data into regions in a grid pattern, and then parallelizes the segmentation over the regions. Parallel file system approach with Hadoop, MarReduce, and Spark (Augustine and Raj, 2016;Li et al, 2016;Cao et al, 2018;Liu et al, 2019;Wang X. et al, 2020) is built for high resolution image segmentation. All of the above approaches allow increasing the performance of the algorithm.…”

Section: Introductionmentioning

confidence: 99%

A proposed scenario to improve the Ncut algorithm in segmentation

Tran

Hieu²,

Bao³

2023

Front. Big Data

View full text Add to dashboard Cite

In image segmentation, there are many methods to accomplish the result of segmenting an image into k clusters. However, the number of clusters k is always defined before running the process. It is defined by some observation or knowledge based on the application. In this paper, we propose a new scenario in order to define the value k clusters automatically using histogram information. This scenario is applied to Ncut algorithm and speeds up the running time by using CUDA language to parallel computing in GPU. The Ncut is improved in four steps: determination of number of clusters in segmentation, computing the similarity matrix W, computing the similarity matrix's eigenvalues, and grouping on the Fuzzy C-Means (FCM) clustering algorithm. Some experimental results are shown to prove that our scenario is 20 times faster than the Ncut algorithm while keeping the same accuracy.

show abstract

“…In addition, some studies are trying to handle the real application concurrently in big data analytics [9,10]. A brain tumor segmentation technique is validated by the use of a parallel genetic approach (PGA) in Hadoop and Spark environments under distinct sizes of data [11]. An effective model in the cloud platform called a proficient lossless compression technique is designed to transfer the brain imaging in the cloud setting is employed.…”

Section: Introductionmentioning

confidence: 99%

Metaheuristic Optimization Based Multi-Key Enabled Encryption With Image Classification for Big Data Environment in Healthcare Sector

Kumar¹,

Mohan²,

Nagesh³

2021

INDJCSE

View full text Add to dashboard Cite

In recent times, medical imaging domain undergoes significant development with respect to innovations, market growth, and exploitation with the rise in the generation of massive data quantity poses diagnostic imaging in the context of Big data. At the same time, securing medical images is needed and it remains a crucial process on the shared communication model. Encryption is considered an effective way of securing the data transmission process in big data environment. Besides, the computer aided diagnosis also provides a second opinion to professionals to manage parallelism. So, it becomes essential to design digital environments and applications which offer effective handling of medical images such as Big data. This paper presents a new Metaheuristic Optimization based Multi-Key Enabled Encryption with Image Classification (MOMEE-IC) for Big Data Environment in Healthcare Sector. The proposed model involves two major operations as encryption and image classification. Firstly, the encryption process involves Multiple key based Homomorphic Encryption (MHE) with lion optimization algorithm (LOA) based optimal key generation process, called MHE-LOA. Besides, Stacked Denoise Autoencoder with Logistic Regression (SDAE-LR) based image classification process is employed for diagnosing the images in the cloud platform. To ensure the superior results of the presented model, a wide set of simulations were performed and the results are examined under distinct aspects.

show abstract

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

Cited by 5 publications

References 0 publications

An efficient Hadoop‐based brain tumor detection framework using big data analytic

An efficient Hadoop‐based brain tumor detection framework using big data analytic

A proposed scenario to improve the Ncut algorithm in segmentation

Metaheuristic Optimization Based Multi-Key Enabled Encryption With Image Classification for Big Data Environment in Healthcare Sector

Contact Info

Product

Resources

About