Segmentation and classification of the abnormalities on the brain are necessary to save one's life;hence the data acquired by magnetic resonance imaging (MR imaging) scan have to be processed. Handling massive MR ...
详细信息
Segmentation and classification of the abnormalities on the brain are necessary to save one's life;hence the data acquired by magnetic resonance imaging (MR imaging) scan have to be processed. Handling massive MR imaging data for high accuracy and precision is a major concern for any framework. Big data and image processing are integrated for brain tumor classification and segmentation in this work. The Hadoop system on matlab performs the big data analysis of the brain tumor image. The BraTS dataset is provided to the Hadoop and matlab distributed computing server (MDCS) system for processing, processed by the single master node and four slave nodes (multimode) on the MDCS configuration. The data from this analysis is decomposed by the novel dual-tree complex Gabor wavelet transform (DTCGWT). The resulting feature vectors are classified as malignant and benign brain tumors based on the deep convolutional neural network (DCNN). If a malignant brain tumor is classified, then the fuzzy level set method based on the manta ray foraging algorithm (FLSM-MRF) will segment the portions of the brain tumor. The model is implemented in the matlab platform and has yield minimum of 56.8 min for processing similar to 30GB of data, while on image processing, 99.1234% and 99.15% accurate result for classification and segmentation respectively is obtained. The parameters like accuracy, sensitivity, specificity, dice, and Jaccard similarity indexes are compared with the existing methods.
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,...
详细信息
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.
Parallel computing System (PCS) is currently used widely in many applications of complex problems involving high computations. This is because it has the capability to process computations efficiently using a parallel...
详细信息
ISBN:
(纸本)9783642217289
Parallel computing System (PCS) is currently used widely in many applications of complex problems involving high computations. This is because it has the capability to process computations efficiently using a parallel scheme. ARS cluster is a low-cost PCS developed to implement processing of full-field digital mammograms. In this system eight processors are used to communicate via the Ethernet network using LINUX which is Fedora 7 as the operating system and matlab distributed computing server (MDCS) as a platform to process the digital mammograms. In this paper the Wavelet Transforms Modulus Maxima (WTMM) method is used to detect the edge of tumor in digital mammogram implemented on the ARS cluster. The study involved 80 digitized mammographic images obtained from the Malaysian National Cancer Center (NCC). The performance of the PCS in detecting the edge of tumors in digital mammograms using WTMM on the ARS cluster is reported. The experimental results showed that the speedup of the PCS improves when the number of processors is increased.
暂无评论