Breast Cancer Classification and Precise Diagnosis using Breast MRI Data
Author(s):
Vidya K, Dr. M. Z. Kurian
Keywords:
Magnetic Resonance Imaging, Classifier Malignant/Benign tumor, Breast cancer
Abstract
Precise diagnosis of the Breast cancer plays a pivotal role in deciding the treatment whether it is surgery or neo adjuvent chemotherapy. Accurate detection will avoid the unnecessary procedure and the removal of the breast. High resolution Magnetic Resonance Imaging (MRI) has been strongly incorporated as the imaging modality to measure the size of the tumor and hence the staging of the cancer in order to choose the best treatment for the patient. Therefore Detection of the tumor from the breast MRI and its classification performed by Computer Aided Diagnosis (CAD) based techniques has been a helping hand to the radiologist in taking the decision about the tumor. The aim of the proposed work is to segment and detect the tumor section from the MRI slices. This is done by initial thresholding followed by filtering and then extraction of foreground and background objects assisting in reliable classification. A statistical based approach is used for extracting the feature set followed by supervised learning classification. The detected tumor is extracted and compared with the data which is marked by the radiologist (ground truth data). Performance parameters such as sensitivity, specificity, accuracy and F values are calculated. Tumor is extracted from all the MRI slices of a patient and then its dimension is calculated at its widest part to know the stage for further treatment. Spearman correlation coefficient of 0.7079 is obtained by comparing the extracted tumor with radiologist data. Study outcome is also compared with the existing classification.
Article Details
Unique Paper ID: 156662

Publication Volume & Issue: Volume 9, Issue 4

Page(s): 466 - 473
Article Preview & Download


Share This Article

Join our RMS



Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Latest Publication

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers