Comparative study of different machine learning classifiers for mammograms and brain MRI images
by Poonam Sonar; Udhav Bhosle; Chandrajit Choudhury
International Journal of Image Mining (IJIM), Vol. 3, No. 2, 2018

Abstract: Today, breast cancer in women has become the leading cause of cancer deaths. Mammography has been the most reliable and accurate technique for early and accurate detection of breast cancer. This paper presents machine learning based mammogram classification techniques. The authors propose an improved hybrid KNN-SVM classifier to improve the performance of the expert system. It is based on mapping feature points to kernel space and finds the K nearest neighbours for a given test data point among the training dataset. This narrow down search for support vectors to the more relevant data points. The proposed algorithm is tested on standard MIAS and DDSM mammograms databases and brain MRI database. The results are compared with different machine learning classifiers such as SVM, KNN, Random Forest, C4.5, Logistic Regression, Fisher Discriminant analysis, Naïve Bayesian classifiers. The results show that the performance of the proposed classifier is better compared to the other classifiers.

Online publication date: Thu, 22-Nov-2018

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 Image Mining (IJIM):
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