Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India

Research Article

MRI-Based Brain Tumor detection and classification using Artificial Neural Network

Download47 downloads
  • @INPROCEEDINGS{10.4108/eai.23-11-2023.2343221,
        author={Chithra  PL and Yegammai  T},
        title={MRI-Based Brain Tumor detection and classification using Artificial Neural Network},
        proceedings={Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India},
        publisher={EAI},
        proceedings_a={IACIDS},
        year={2024},
        month={3},
        keywords={brain tumor classification segmentation artificial neural network tumor detection},
        doi={10.4108/eai.23-11-2023.2343221}
    }
    
  • Chithra PL
    Yegammai T
    Year: 2024
    MRI-Based Brain Tumor detection and classification using Artificial Neural Network
    IACIDS
    EAI
    DOI: 10.4108/eai.23-11-2023.2343221
Chithra PL1,*, Yegammai T2
  • 1: Department of Computer Science, University of Madras, Chennai, Tamil Nadu, India
  • 2: Department of Computer Science, Shri Shankarlal Sundarbai Shasun Jain College for Women, Chennai, Tamil Nadu, India
*Contact email: chitrasp2001@yahoo.com

Abstract

The process of brain tumor categorization and identification using MRI (magnetic resonance imaging) is one of the challenging domains in medical field. There were numerous malignancies such as glioma tumor, no tumor (benign), pituitary tumor and meningioma tumor.In this paper, an efficient automated methodhas been proposedto identify and classify tumor image from the MRI images.This proposed methodology includes three processing steps, including pre-processing, segmentation and feature classification from MRI images. In this,the Otsu thresholding technique is first applied to separate tumor from input brain image. Then then combination of three methods, namelyDWT(Discrete wavelet transform), PCA (Principal Component Analysis) and GLCM (Gray level co-occurrence matrix) to extract image attributes from the fragmented MRI data. Further, the extracted feature images are applied to the classifiers namely Naive Bayes (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and Decision Tree (DT). Analysing the results of above machine learning classifiers, the Artificial Neural Network (ANN) model obtains a 97.6% accuracy rate and the minimum loss rate of 0.028817. It is evident from the experimental result, the proposed method has a great chance of detecting tumor efficiently.