Online ISSN: 2515-8260

Keywords : GLCM


AUTOMATIC SEGMENTATION OF SPINAL CORD IN MRI IMAGES VIA ITERATIVE CUCKOO SEARCH BASED RANDOM WALKER AND ONLINE KERNEL LEARNING (OKL) CLASSIFIER

Dr. D. Brindha; N.R. Deepa; Dr.Y. BabyKalpana; Dr.K. Murugan; Dr.A. Devipriya

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 9, Pages 875-891

Segmentation of Spinal Cord (SC) part has a major role in assessing spinal cord atrophy.
Spinal Cord segmentation is not similar to that of brain segmentation, although Magnetic Resonance
Imaging (MRI) sequence are greatly deployed for spinal cord examination. There is always a great
challenge in spinal cord MRI segmentation which has been investigated by many researches. Also,
considerable accuracy and degree of complexity for segmentation have been presented and elucidated in
prevailing researches. A new approach namely combining Iterative Random-Walk (RW) solver and a
Cuckoo Search Algorithm (CSA) has been suggested, thus facilitating direct homogenous and
heterogeneous SC measurements comparison. An interactive RW solver with CSA is greatly utilized for
complete cascaded pipelining in automatic manner. The initialization of automatic segmentation pipeline is
done through powerful voxelwise classification via Online Kernel Learning (OKL) classifier. Therefore,
SC topology refinement is done iteratively along with cascading of RW-CSA solvers for attaining proper
segmentation outcomes in less iteration, even for cases including bone fractures and lesions. The
segmentation experimental outcome mainly relies on MRI images indicating achievement of improved
accuracy when compared with prevailing approaches

An Efficient Brain Tumor Classification And Detection Using Evolutionary Approach For Healthcare System

Vinoth Kumar. V; Dr. Paluchamy. B

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 3, Pages 658-670

The growth of irregular cells within the brain region with the prearrangement of tissues is characterized as a Brain Tumor that leads death to people. Comparing to other categories of cancers, a brain tumor is the most deadly disease that has to be detected and treated in the previous stage. Due to cells' complex formation, the tumor detection process is complicated with simple image processing methodologies. Moreover, for providing proper and efficient treatment to the patients, an exact cancer segmentation and classification technique must process the input of brain images as Magnetic Resonance Imaging (MRI) scans. Based on that, this paper develops a novel approach called Soft Computing based Brain Tumor Detection and Classification (SC-BTDC) with the obtained MRI. In the present scenario of tumor detection from image processing, soft computing techniques play a significant role. Hence, it is adopted in this work. The method contains phases such as pre-processing, Fuzzy c-Means clustering-based segmentation, feature extraction, and image classification. The median pre-processing filter and edge detection methods are incorporated for noise removal and clearly define the image in the stage of the median pre-processing filter. Further, FCM based clustering is performed for the image segmentation process, following, factors of Gray Level Co-Occurrence Matrix (GLCM) found feature extraction is established. The final phase includes the classification process using the soft computing technique called Artificial Neural Network (ANN) classification. The proposed system acquires a higher accuracy rate and is compared with various existing algorithms for proving the efficiency and minimum loss of the proposed algorithm.