Image Texture in Dental Panoramic Radiographs as a Potential Biomarker of Osteoporosis

• Published in: IEEE transactions on biomedical engineering Vol. 60; no. 9; pp. 2384 - 2392
• Main Authors: Roberts, Martin G., Graham, James, Devlin, Hugh
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2013
• Subjects: Area Under Curve; Biomarkers; Biomedical measurement; Bone and Bones - diagnostic imaging; Bone and Bones - pathology; Bone Density; Bones; Cluster Analysis; Co-occurrence matrices; dental panoramic radiograph (DPR); Dentistry; Female; Fractals; Humans; Image texture; Osteoporosis; Osteoporosis - diagnostic imaging; Osteoporosis - epidemiology; Radiographic Image Interpretation, Computer-Assisted - methods; Radiography, Panoramic - methods; random forest classifier; ROC Curve; Vegetation
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2013.2256908

Previous studies have shown an association between osteoporosis and automatic measurements of mandibular cortical width on dental panoramic radiographs (DPRs). In this study, we show that additional image texture features increase this association and propose the combined features as a potential biomarker for osteoporosis. We used an existing dataset of 663 DPRs of female patients with bone mineral density (BMD) measurements. The mandibular cortex was located using a previously described computer algorithm. Texture features, based on co-occurrence matrices and fractal dimension, were measured in the bone within the cortex and also in the superior basal bone above the cortex. These, augmented by cortical width measurements, were used by a random forest classifier to identify osteoporosis at femoral neck, total hip, and lumbar spine. Classification performance was assessed by ROC analysis. Area-under-curve (AUC) values for identifying osteoporosis at femoral neck were 0.830, 0.824, and 0.872 using, respectively, cortical width alone, cortical texture (co-occurrence matrix features) alone, and combined width and texture. At 80% sensitivity, these classifiers produced specificity values of 74.4%, 73.6%, and 80.0%, respectively. Fractal dimension was a less effective texture feature. Prediction of osteoporosis at the lumbar spine was poorer, but a combined width and superior basal bone texture classifier gave a significant improvement in AUC at over the use of width alone.