A dual stage adaptive thresholding (DuSAT) for automatic mass detection in mammograms. (January 2017)

• Record Type: Journal Article
• Authors: Anitha, J.; Dinesh Peter, J.; Immanuel Alex Pandian, S.
• Is Part Of: Computer methods and programs in biomedicine. Volume 138(2017)
• Page Start: 93
• Page End: 104
• Publication Date: 2017-01
• Subjects: Computer aided detection -- Breast cancer -- Histogram peak analysis -- Adaptive thresholding -- Between-class standard deviation; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2016.10.026
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: 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. Abstract: Background and Objective: Early detection and diagnosis of breast cancer through mammography screening reduces breast cancer mortality by around 20%. However it is often a complex process to differentiate abnormalities due to the ill-defined margins and subtle appearances. Method: This paper investigates a new computer aided approach to detect the abnormalities in the digital mammograms using a Dual Stage Adaptive Thresholding (DuSAT). The suspicious mass region is identified using global histogram and local window thresholding method. The global thresholding is done based on the Histogram Peak Analysis (HPA) of the entire image and the threshold is obtained by maximizing the proposed threshold selection criteria. The local thresholding is carried out for each pixel in a defined neighborhood window that provides precise segmentation results. Results: The algorithm is verified with 300 images in the DDSM database and 170 images in the mini-MIAS database. Experimental results show that the proposed algorithm achieves an average sensitivity of 92.5% with 1.06 FP/image for DDSM database and an average sensitivity of 93.5% with 0.62 FP/image for mini-MIAS database. Conclusion: The achieved results depict that the proposed approach provides better results compared to other state-of-art methods for mass detection that helps the radiologists in diagnosis of breast cancer at early stage.