Alveolar bone-loss area localization in periodontitis radiographs based on threshold segmentation with a hybrid feature fused of intensity and the H-value of fractional Brownian motion model. Issue 3 (October 2015)

• Record Type: Journal Article
• Authors: Lin, P.L.; Huang, P.W.; Huang, P.Y.; Hsu, H.C.
• Is Part Of: Computer methods and programs in biomedicine. Volume 121:Issue 3(2015)
• Page Start: 117
• Page End: 126
• Publication Date: 2015-10
• Subjects: 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.2015.05.004
• Languages: English
• ISSNs: 0169-2607

Abstract

<abstract abstract-type="author-highlights" id="abs0005"> <title id="sect0005">Highlights</title> <sec> <p id="spar0005"> <list id="lis0005"> <list-item id="lsti0005"> <label></label> <p id="par0005">Present an effective threshold segmentation method for localizing alveolar bone-loss areas in periodontitis images using a hybrid feature = 0.15 fBm-H + 0.85 (1 − <italic>I</italic>), both fBm-H and <italic>I</italic> are normalized.</p> </list-item> <list-item id="lsti0010"> <label></label> <p id="par0010">(TPF, FPF) of 31 tested radiograph images (used and unused in weight training) ∼ (92.5%, 14%).</p> </list-item> <list-item id="lsti0015"> <label></label> <p id="par0015">∼14% lower FPF than level set, Bayesian, KNN, SVM classification using the same two features.</p> </list-item> <list-item id="lsti0020"> <label></label> <p id="par0020">The method would be useful for dentists in evaluating degree of bone-loss for periodontitis patients.</p> </list-item> </list> </p> </sec> </abstract>