Lesion detection using segmentation and classification of mammograms

Authors:
L. Vibha;G. M. Harshavardhan;K. Pranaw;P. Deepa Shenoy;K. R. Venugopal;L. M. Patnaik
Affiliations:
Dept. of CSE, University Visvesvaraya College of Engineering, Bangalore University, Bangalore, India;Dept. of CSE, University Visvesvaraya College of Engineering, Bangalore University, Bangalore, India;Dept. of CSE, University Visvesvaraya College of Engineering, Bangalore University, Bangalore, India;Dept. of CSE, University Visvesvaraya College of Engineering, Bangalore University, Bangalore, India;Dept. of CSE, University Visvesvaraya College of Engineering, Bangalore University, Bangalore, India;Microprocessor Applications Laboratory, Indian Institute of Science, Bangalore, India
Venue:
AIAP'07 Proceedings of the 25th conference on Proceedings of the 25th IASTED International Multi-Conference: artificial intelligence and applications
Year:
2007

Citing 3
Cited 2

Data mining: concepts and techniques

Data mining: concepts and techniques
Digital Image Processing

Digital Image Processing
Dynamic Association Rule Mining using Genetic Algorithms

Intelligent Data Analysis

Computer-Based Identification of Breast Cancer Using Digitized Mammograms

Journal of Medical Systems
Random Forest Classification for Automatic Delineation of Myocardium in Real-Time 3D Echocardiography

FIMH '09 Proceedings of the 5th International Conference on Functional Imaging and Modeling of the Heart

Quantified Score

Hi-index	0.00

Visualization

Abstract

The national cancer institute (NCI) estimates that 1 in 8 women in USA (12.6%) develop breast cancer, during their life time. Mammography is a medical imaging technique that combines, low-dose radiation and high-contrast, high-resolution film for examination of the breast and screening for breast cancer. The aim of a screening mammogram is to detect a tumor that cannot be physically detected. This paper proposes a method for detection of tumor using Watershed Algorithm, and further classifies it as benign or malignant using Watershed Decision Classifier (WDC). The technique consists of four phases namely, the pre-processing of image, detecting the presence of tumor, creation of the data base and finally classifying and categorizing them into two groups such as Cancerous or Benign. Experimental results show that this method performs well with the classification accuracy reaching nearly 88.38%.