Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ44928

Unsupervised Classification for predicting Malignant Tumor cells in Brain using FCM Method



Physiological effects has a significant impact on human existence. MRI plays a crucial part in our life. Magnetic resonance imaging (MRI) is a crucial tool for spotting brain tumors. In this proposed research work, we introduce a novel approach for predicting brain tumors. One of the great problems of modern medicine is the identification of human brain tumors. In this study, we present an MRI-based model for detecting human brain tumors using the improved fuzzy C means (FCM) algorithm. The suggested approach determines the best segmentation template to use for a given image by analyzing its grayscale intensity. The flexible C-means (FCM) algorithm uses distances from the cluster centroid to the cluster data points to update membership as it gets closer to the optimal solution, and then the upgraded FCM clustering algorithm is applied to tumor detection. The suggested approach outperforms state-of-the-art methods in simulating human brain images with tiny differences in gray-level intensity, as demonstrated by the simulation results. As an added bonus, our system can detect human brain cancers in a matter of seconds, whereas other algorithms can take up to minutes to do so. Tumor detection and extraction from brain MRI scans are performed with the help of MATLAB. The findings show a level of robustness against the presence of noise. Additionally, in some instances of tumor pathology, the accuracy of segmentation was improved by as much as 10-15% compared to the expert estimate.


Brain Tumor, Fuzzy C-Means, Malignant, Benign, Clustering, Feature Extraction

Full Text