A dual stage adaptive thresholding (DuSAT) for automatic mass detection in mammograms

详细信息    查看全文

• 作者：J. Anitha^a ; ^{anitha_j@karunya.edu} ; J. Dinesh Peter^b ; S. Immanuel Alex Pandian^c
• 关键词：Computer aided detection ; Breast cancer ; Histogram peak analysis ; Adaptive thresholding ; Between-class standard deviation
• 刊名：Computer Methods and Programs in Biomedicine
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：138
• 期：Complete
• 页码：93-104
• 全文大小：2083 K
• 卷排序：138

文摘

Pre-processing using thresholding and region growing methods. An optimal adaptive global threshold selection by maximizing between-class standard deviation through histogram peak analysis to obtain a coarse segmentation. A window based adaptive local thresholding to obtain the fine segmentation of mass. Proposed approach yields most satisfactory results to ground-truth segments. The comparison is carried out in terms of TPF and FP/I to show the effectiveness.