Abstract

This paper presents a novel methodology for the classification of suspicious areas in digital mammograms. The methodology is based on the fusion of clustered sub classes with various intelligent classifiers. A number of classifiers have been incorporated into the proposed methodology and evaluated on the well known benchmark digital database of screening mammography (DDSM). The results in the form of overall classification accuracies, TP, TN, FP and FN have been analyzed, compared and presented. The results of all four tested classifiers with clustered sub classes on the DDSM benchmark database show that the proposed methodology can significantly improve the accuracy and reduce the false positive rate.

Highlights

  • BREAST cancer affects 10-12% of the world’s females accounting for around 500,000 deaths per year worldwide [1]

  • The research presented in this paper addresses this issue by incorporating clustered sub-classes into the classification process in order to improve classification accuracy and reduce the false positive rate

  • Various methodologies have been proposed to address the issue of variable classification accuracy for the classification of suspicious areas in digital mammograms

Read more

Summary

Introduction

BREAST cancer affects 10-12% of the world’s females accounting for around 500,000 deaths per year worldwide [1]. Chang [19] used a likelihood function to compare the gray level and shape characteristics of a Regions of Interest (ROI) against a database of classified masses. This was used to compute a likelihood measure. The measures took into account AUC and the contrast between the area of the matched region and the background of the similarity map The results of this process were quite successful in that an accuracy of AUC of 0.96 ± 0.05 was achieved. Only 68 mammograms were utilized in this study and the algorithms are very time consuming to come to a classification

Results
Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call