Machine learning approach for automatic brain tumour detection using patch-based feature extraction and classification
by T. Kalaiselvi; P. Kumarashankar; P. Sriramakrishnan
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 39, No. 4, 2022

Abstract: Manual selection of tumorous slices from MRI volume is a time expensive process. In the proposed work, we have developed an automatic method for tumorous slice classification from MRI head volume. The proposed method is named as patch-based classification (PBC). PBC uses 8 × 8 patch-based feature extraction and SVM-based classification. Optimal features selection has been done by infinite feature selection (IFS) method. The optimal features are extracted from patches and used to train the SVM classifier to construct the tumour prediction model (TPM). TPM helps to identify the tumorous patches in the testing phase. Accuracy is measured using sensitivity, specificity and accuracy, error rates are calculated using false alarm (FA) and missed alarm (MA). Training and testing patches are chosen from whole brain atlas (WBA) and BraTS datasets. Results of PBC are compared with several existing methods. PBC will be more helpful to physicians who currently undergo a tedious and time consuming process of manually selecting the tumorous slices from the MRI volumes.

Online publication date: Fri, 05-Aug-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Biomedical Engineering and Technology (IJBET):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email