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

Highlights • 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 − I ), both fBm-H and I are normalized. • (TPF, FPF) of 31 tested radiograph images (used and unused in weight training) ∼ (92...

Full description

Saved in:
Bibliographic Details
Published in:Computer methods and programs in biomedicine 2015-10, Vol.121 (3), p.117-126
Main Authors: Lin, P.L, Huang, P.W, Huang, P.Y, Hsu, H.C
Format: Article
Language:English
Subjects:
Alveolar bone-loss
Alveolar Process - diagnostic imaging
Alveolar Process - pathology
fBm model
Humans
Hybrid feature
Internal Medicine
Leave-one-out cross validation
Models, Anatomic
Other
Periodontitis - diagnostic imaging
Periodontitis - pathology
Periodontitis radiographs
Radiography, Dental
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • 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 − I ), both fBm-H and I are normalized. • (TPF, FPF) of 31 tested radiograph images (used and unused in weight training) ∼ (92.5%, 14%). • ∼14% lower FPF than level set, Bayesian, KNN, SVM classification using the same two features. • The method would be useful for dentists in evaluating degree of bone-loss for periodontitis patients.
ISSN:0169-2607
1872-7565
DOI:10.1016/j.cmpb.2015.05.004