Diagnosis of osteoporosis from dental panoramic radiographs using the support vector machine method in a computer-aided system

BackgroundEarly diagnosis of osteoporosis can potentially decrease the risk of fractures and improve the quality of life. Detection of thin inferior cortices of the mandible on dental panoramic radiographs could be useful for identifying postmenopausal women with low bone mineral density (BMD) or osteoporosis. The aim of our study was to assess the diagnostic efficacy of using kernel-based support vector machine (SVM) learning regarding the cortical width of the mandible on dental panoramic radiographs to identify postmenopausal women with low BMD.MethodsWe employed our newly adopted SVM method for continuous measurement of the cortical width of the mandible on dental panoramic radiographs to identify women with low BMD or osteoporosis. The original X-ray image was enhanced, cortical boundaries were determined, distances among the upper and lower boundaries were evaluated and discrimination was performed by a radial basis function. We evaluated the diagnostic efficacy of this newly developed method for identifying women with low BMD (BMD T-score of -1.0 or less) at the lumbar spine and femoral neck in 100 postmenopausal women (≥50 years old) with no previous diagnosis of osteoporosis. Sixty women were used for system training, and 40 were used in testing.ResultsThe sensitivity and specificity using RBF kernel-SVM method for identifying women with low BMD were 90.9% [95% confidence interval (CI), 85.3-96.5] and 83.8% (95% CI, 76.6-91.0), respectively at the lumbar spine and 90.0% (95% CI, 84.1-95.9) and 69.1% (95% CI, 60.1-78.6), respectively at the femoral neck. The sensitivity and specificity for identifying women with low BMD at either the lumbar spine or femoral neck were 90.6% (95% CI, 92.0-100) and 80.9% (95% CI, 71.0-86.9), respectively.ConclusionOur results suggest that the newly developed system with the SVM method would be useful for identifying postmenopausal women with low skeletal BMD.

[1]  Stuart C. White,et al.  Clinical and panoramic predictors of femur bone mineral density , 2005, Osteoporosis International.

[2]  The radiographic trabecular bone pattern during menopause. , 1993, Bone.

[3]  A. Taguchi,et al.  Relationship between the mandibular and lumbar vertebral bone mineral density at different postmenopausal stages. , 1996, Dento maxillo facial radiology.

[4]  S. Majumdar,et al.  Morphometric texture analysis of spinal trabecular bone structure assessed using orthogonal radiographic projections. , 1998, Medical physics.

[5]  X Ouyang,et al.  Texture analysis of direct magnification radiographs of vertebral specimens: correlation with bone mineral density and biomechanical properties. , 1997, Academic radiology.

[6]  S. Kawasaki,et al.  Springer Verlag, Berlin, Heidelberg, New York (1995) , 1996 .

[7]  H. Devlin,et al.  The relationships between two indices of mandibular bone quality and bone mineral density measured by dual energy X-ray absorptiometry. , 1998, Dento maxillo facial radiology.

[8]  H. Devlin,et al.  Diagnosis of osteoporosis in oral health care. , 2007, Journal of oral rehabilitation.

[9]  Tin Wee Tan,et al.  SVM-based prediction of caspase substrate cleavage sites , 2006, BMC Bioinformatics.

[10]  H. Devlin,et al.  Mandibular Radiomorphometric Indices in the Diagnosis of Reduced Skeletal Bone Mineral Density , 2002, Osteoporosis International.

[11]  Susan R. Johnson,et al.  Osteoporosis prevention, diagnosis, and therapy. , 2001, JAMA.

[12]  Jun Cai,et al.  Classification of Nuclear Receptor Subfamilies with RBF Kernel in Support Vector Machine , 2005, ISNN.

[13]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[14]  T. Tomomitsu,et al.  Diagnostic criteria for primary osteoporosis: year 2012 revision , 2013, Journal of Bone and Mineral Metabolism.

[15]  Vladimir Naumovich Vapni.  The Nature of Statistical Learning Theory , 1995 .

[16]  W. Leow,et al.  DETECTION OF FEMUR AND RADIUS FRACTURES IN X-RAY IMAGES , 2004 .

[17]  A. Asano,et al.  Continuous Measurement of the Mandibular Cortical Bone in Dental Panoramic Radiographs for the Diagnosis of Osteoporosis using a Clustering Algorithm on Histograms , 2010 .

[18]  K Horner,et al.  The relationship between mandibular bone mineral density and panoramic radiographic measurements. , 1998, Journal of dentistry.

[19]  Akira Asano,et al.  Computer-aided measurement of mandibular cortical width on dental panoramic radiographs for identifying osteoporosis. , 2012, Journal of investigative and clinical dentistry.

[20]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[21]  R Jacobs,et al.  Automated osteoporosis risk assessment by dentists: a new pathway to diagnosis. , 2007, Bone.

[22]  A. Asano,et al.  Computer-aided system for measuring the mandibular cortical width on dental panoramic radiographs in identifying postmenopausal women with low bone mineral density , 2006, Osteoporosis International.

[23]  A. Taguchi,et al.  Triage screening for osteoporosis in dental clinics using panoramic radiographs. , 2010, Oral diseases.

[24]  G. Hawker,et al.  The validity of decision rules for selecting women with primary osteoporosis for bone mineral density testing , 2004, Osteoporosis International.

[25]  H. Kröger,et al.  Pantomography in assessment of the osteoporosis risk group. , 1994, Scandinavian journal of dental research.

[26]  M. Giger,et al.  Multifractal radiographic analysis of osteoporosis. , 1994, Medical physics.

[27]  M. Fukunaga,et al.  Fracture Prediction From Bone Mineral Density in Japanese Men and Women , 2003, Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research.

[28]  Hajime Orimo,et al.  Diagnostic criteria for primary osteoporosis: year 2000 revision , 2001, Journal of Bone and Mineral Metabolism.