| Home | Organizers | Proceedings Editors | Proceedings Contributors | Search | | ||
|
|
|||
|
||||
|
|
||||
| Title: | COMPUTER AIDED DIAGNOSIS IN DIGITAL MAMMOGRAMS: HYBRID META-HEURISTIC ALGORITHMS FOR DETECTION OF MICROCALCIFICATIONS | |
| DOI No: | 10.1142/9781860948534_0017 | |
| Source: | INNOVATIVE APPLICATIONS OF INFORMATION TECHNOLOGY FOR THE DEVELOPING WORLD (pp 104-119) | |
| Author(s): | K. THANGAVEL
Department of Mathematics, GRI-Deemed University, Gandhigram -624302, Tamil Nadu, India M. KARNAN Fax: 91-4551-227229. Dept. of Computer Science, Gandhigram Rural Institute-Deemed University, Gandhigram-624302, Tamil Nadu, India R. SIVAKUMAR Department of CSE, R.V.S. College of Engg. & Tech., Dindigul, Tamil Nadu, India A. KAJA MOHIDEEN Department of CSE, R.V.S. College of Engg. & Tech., Dindigul, Tamil Nadu, India |
|
| Abstract: | Mammography is currently the best method for early detection of breast cancer. In this paper, Simulated Annealing (SA), Tabu Search (TS), Genetic Algorithm (GA), and Ant Colony Optimization (ACO) and three novel hybrid combinations of TS and ACO such as Sequential TS–ACO, a Hybrid ACO/TS, and a Sequential ACO–TS are proposed for mammogram segmentation. Initially the mammogram images are enhanced and Markov Random Field (MRF) is applied to label the image pixels. The meta-heuristic algorithms are applied to found out the optimum label for segmentation. The Free-response Receiver Operating Characteristic (FROC) analysis was performed to compare the segmentation performance of the proposed algorithms. Statistical comparative analysis conclude that all of the three proposed novel techniques are significantly better than each of their non-hybrid competitors, and furthermore the Sequential ACO–TS provides the superior solution of all. | |
| Full Text: | View full text in PDF format (759KB) | |
| TOC: | Back to Table of Contents | |
|
||