数字化牙科全景X线片下颌骨皮质骨纹理分析用于韩国女性骨质疏松症的诊断
Texture analysis of mandibular cortical bone on digital dental panoramic radiographs for the diagnosis of osteoporosis in Korean women.
作者信息
Kavitha Muthu Subash, An Seo-Young, An Chang-Hyeon, Huh Kyung-Hoe, Yi Won-Jin, Heo Min-Suk, Lee Sam-Sun, Choi Soon-Chul
机构信息
Department of Oral and Maxillofacial Radiology and Dental Research Institute, School of Dentistry, Seoul National University, Seoul, Korea.
Department of Oral and Maxillofacial Radiology, School of Dentistry, Kyungpook National University, Daegu, Korea.
出版信息
Oral Surg Oral Med Oral Pathol Oral Radiol. 2015 Mar;119(3):346-56. doi: 10.1016/j.oooo.2014.11.009. Epub 2014 Dec 5.
OBJECTIVE
To determine whether individual measurements or a combination of textural features and mandibular cortical width (MCW) derived from digital dental panoramic radiographs (DPRs) are more useful in assessment of osteoporosis.
STUDY DESIGN
Textural features were obtained by using fractal dimension (FD) and gray-level co-occurrence matrix (GLCM). Digital DPRs and bone mineral densities (BMDs) of the lumbar spine and the femoral neck were obtained from 141 female patients. A naïve Bayes classifier, a k-nearest neighbor (k-NN) algorithm, and a support vector machine were assessed for classifying osteoporosis.
RESULTS
The combinations of FD plus MCW (95.3%, 92.1%, 96.8%) and GLCM plus MCW (93.7%, 89.5%, 94.2%) for femoral neck BMD showed the highest diagnostic accuracy with the use of the naïve Bayes, k-NN, and support vector machine classifiers, respectively.
CONCLUSIONS
The combination of textural features and MCW contributed a better assessment of osteoporosis compared with the use of only individual measurements.
目的
确定从数字化牙科全景X线片（DPR）获得的个体测量值或纹理特征与下颌骨皮质宽度（MCW）的组合在骨质疏松症评估中是否更有用。
研究设计
通过使用分形维数（FD）和灰度共生矩阵（GLCM）获得纹理特征。从141名女性患者中获取腰椎和股骨颈的数字化DPR及骨密度（BMD）。评估朴素贝叶斯分类器、k近邻（k-NN）算法和支持向量机对骨质疏松症进行分类的情况。
结果
对于股骨颈BMD，FD加MCW（95.3%，92.1%，96.8%）和GLCM加MCW（93.7%，89.5%，94.2%）的组合分别使用朴素贝叶斯、k-NN和支持向量机分类器时显示出最高的诊断准确性。
结论
与仅使用个体测量值相比，纹理特征和MCW的组合有助于更好地评估骨质疏松症。
Zotero 插件