Texture analysis of mandibular cortical bone on digital dental panoramic radiographs for the diagnosis of osteoporosis in Korean women

2015 ◽  
Vol 119 (3) ◽  
pp. 346-356 ◽  
Author(s):  
Muthu Subash Kavitha ◽  
Seo-Young An ◽  
Chang-Hyeon An ◽  
Kyung-Hoe Huh ◽  
Won-Jin Yi ◽  
...  
2009 ◽  
Vol 55 (1) ◽  
pp. 29-33
Author(s):  
Mizuki OHASHI ◽  
Hiroshi NAKAJIMA ◽  
Chieko MASUDA ◽  
Wakako SUMIMOTO ◽  
Yuka NAKAMICHI ◽  
...  

Author(s):  
Laatra Yousfi ◽  
Lotfi Houam ◽  
Abdelhani Boukrouche ◽  
Eric Lespessailles ◽  
Frédéric Ros ◽  
...  

Early diagnosis of osteoporosis can efficiently predict fracture risk. There is a great demand to prevent this disease. The goal of this study was to distinguish osteoporotic cases from healthy controls on 2D bone radiograph images, using texture analysis and genetic algorithms (GAs). Gray Level Co-occurrence Matrix (GLCM), Run length Matrix (RLM) and Binarized Statistical Image Features (BSIF) were used for texture analysis. Features are numerous and parameter-dependent. The related experts can pick out the useful input features for the classifier. It however remains a difficult task and may be inefficient or even harmful as the data pattern is not clear. In this paper, GAs were used to optimize the two parameters of the co-occurrence matrix (distance parameter or pixel separation, orientation or direction) and the number of gray levels used in the preprocessing quantification step. GAs were also used to select the best combination of features extracted from GLCM and RLM matrices. Experiments were conducted on two populations composed of Osteoporotic Patients and Control Subjects. Results show that GAs combined with GLCM and BSIF features can improve the classification rates (ACC = 87.50%) obtained using GLCM (ACC = 77.8%) alone.


2015 ◽  
Vol 119 (5) ◽  
pp. 584-592 ◽  
Author(s):  
Sandra R. Torres ◽  
Curtis S.K. Chen ◽  
Brian G. Leroux ◽  
Peggy P. Lee ◽  
Lars G. Hollender ◽  
...  

2015 ◽  
Author(s):  
Kazuki Horiba ◽  
Chisako Muramatsu ◽  
Tatsuro Hayashi ◽  
Tatsumasa Fukui ◽  
Takeshi Hara ◽  
...  

2016 ◽  
Vol 33 (2) ◽  
pp. 117-123 ◽  
Author(s):  
Yoshiko Ariji ◽  
Akitoshi Katsumata ◽  
Ryota Kubo ◽  
Akira Taguchi ◽  
Hiroshi Fujita ◽  
...  

2017 ◽  
Vol 20 (1) ◽  
pp. 56
Author(s):  
Paula Cristina De Faria ◽  
Maria Fernanda Lima Villaça-Carvalho ◽  
Sérgio Lúcio Pereira de Castro Lopes ◽  
Mari Eli Leonelli De Moraes ◽  
Luiz Roberto Coutinho Manhães Júnior

<p><strong>Objective:</strong> The aim of this study was to evaluate the potential of panoramic radiographs (PR) and their radiomorphometric indices as an auxiliary method for the diagnosis of osteoporosis. <strong>Material and</strong> <strong>Methods:</strong> Twenty five women were selected, who had been prescribed PR for different purposes. The PR were analysed according to the MCI, which evaluates the mandibular cortex below the mental foramen, and then divided into two groups: normal and bone mineral loss. Bone densitometry scans were obtained (DXA) from the lumbar spine and neck of the femur/whole femur, which were used as the gold standard for comparison against the MCI. Kappa test (p&lt;0.05) was used to determine the association between the MCI and bone densitometry readings. <strong>Results:</strong> Regarding the DXA, 7 patients were normal at the lumbar spine or femur, 24 subjects showed osteopenia at the lumbar spine or femur and 9 subjects had osteoporosis at the lumbar spine or femur. Regarding the association between DXA and MCI, 18 subjects showed some degree of bone loss at the spine detected by both DXA and the Klemetti index. <strong>Conclusions:</strong> PR may be useful to assess the risk of such diseases being present.</p>


2016 ◽  
Vol 10 (01) ◽  
pp. 064-068 ◽  
Author(s):  
Saadettin Dagistan ◽  
Ozkan Miloglu ◽  
Fatma Caglayan

ABSTRACT Objective: To compare the existence of gonial cortical bone thickness, antegonial index, mandibular canal bone resorption and gonial angle values and pathologies like ground-glass appearance in jawbones and brown tumor in male patients undergoing dialysis due to chronic renal failure and men from the healthy control group on panoramic radiographs. Materials and Methods: Panoramic radiographs were taken from 80 male individuals in total (40 normal and 40 dialysis patients). Values obtained from the right and left sides of the mandible were summed and their means were calculated. Gonial cortical thickness, antegonial index and gonial angle values were assessed with the Student's t-test, mandibular canal wall resorption with the Chi-square test, and pathologies such as ground-glass appearance and Brown tumor as “available” or “not available.” Results: Statistically significant differences were observed among the antegonial index (P < 0.001), gonial cortical bone thickness (P < 0.001), and gonial angle (P < 0.001) values of study and control groups. Besides, mandibular canal wall resorption (P < 0.001) was also statistically significant. In the study group, pathologies with ground-glass appearance were encountered in mandible, but no radiographic findings were observed similar to brown tumor. Conclusions: Compared to the control group, decreases were found in gonial cortical bone thicknesses, antegonial index values, mandibular canal wall resorption, and gonial angle values of the patients receiving dialysis treatment due to chronic renal failure. Although it is not statistically significant, pathology with ground-glass appearance was detected in a patient, but no pathologies like brown tumor were observed. These findings from patients with chronic renal failure must be evaluated in panoramic radiography.


Sign in / Sign up

Export Citation Format

Share Document