Using Radon transform of standard radiographs of the hip to differentiate between post-menopausal women with and without fracture of the proximal femur

• Published in: Osteoporosis international Vol. 20; no. 2; pp. 323 - 333
• Main Authors: Boehm, H. F, Lutz, J, Körner, M, Mutschler, W, Reiser, M, Pfeifer, K.-J
• Format: Journal Article
• Language: English
• Published: London London : Springer-Verlag 01.02.2009; Springer-Verlag; Springer; Springer Nature B.V
• Subjects: Aged; Aged, 80 and over; Area Under Curve; Biological and medical sciences; Bone Density; Case-Control Studies; Diagnosis, Differential; Discriminant Analysis; Diseases of the osteoarticular system; Endocrinology; Female; Femur; Femur - diagnostic imaging; Femur - physiopathology; Fracture risk; Fractures; Fractures, Spontaneous; Fractures, Spontaneous - diagnostic imaging; Fractures, Spontaneous - physiopathology; Hip; Hip - diagnostic imaging; Hip Fractures; Hip Fractures - diagnostic imaging; Hip Fractures - physiopathology; Hip joint; Humans; In vivo; Injuries of the limb. Injuries of the spine; Legs; Lumbar Vertebrae; Lumbar Vertebrae - physiopathology; Medical sciences; Medicine; Medicine & Public Health; methods; Older people; Original Article; Orthopedics; Osteoporosis; Osteoporosis. Osteomalacia. Paget disease; physiopathology; Proximal femur; Radiographic texture analysis; Radiography; Radon transform; Rheumatology; Risk Assessment; Risk Assessment - methods; Risk factors; Sensitivity and Specificity; Traumas. Diseases due to physical agents; Womens health; Radon transform; In vivo; Osteoporosis; Radiographic texture analysis; Fracture risk; Proximal femur; Human; Proximal; Femur; Radiodiagnosis; Radon; Diseases of the osteoarticular system; Rheumatology; Exploration; Fracture; Trauma; Texture; Hip; Radiography; Risk factor; Woman
• ISSN: 0937-941X; 1433-2965; 1433-2965
• DOI: 10.1007/s00198-008-0663-6

Summary Texture features based on the Radon transform were extracted from clinical radiographs of the hip in post-menopausal women. The novel algorithm allowed us to identify patients with fracture of the proximal femur and may provide an alternative to measuring bone mineral density in predicting the fracture-risk in osteoporosis, especially where densitometry is regionally unavailable. Introduction The aim of this study is to introduce an algorithm for differentiation between patients with and without fracture of the hip using parameters based on the Radon transform (RT) and applied to standard radiographs of the proximal femur and to compare the results with bone mineral density (BMD). Methods The study comprised 50 post-menopausal women (78.6 ± 11.5 years of age), including 25 patients with hip fracture and 25 age-matched controls. We obtained lumbar and femoral BMD and standard femoral radiographs. In the radiographs we analysed trabecular patterns of the hip in a region-of-interest of 57 x 29 mm using the RT. From the histogram-representation of the RT, we extracted several characteristic parameters. By ROC and discriminant-analysis, we assessed the statistical power of both methods. Results For correct differentiation between fracture and non-fracture cases by femoral BMD, area-under-the-curve (AUC) was 0.78; AUC for the RT-based parameters ranged from 0.73 to 0.8. By combination of densitometric and textural information in a multivariate model the fracture status of 84% of subjects was predicted correctly, identification of fracture cases rose to 88%. Conclusion Identification of fracture patients by RT applied to femoral radiographs was feasible and seemed to have a discriminative potential comparable to that of standard densitometry. In the future, the new method may provide an alternative to DXA or in conjunction with conventional densitometry may enhance the detection of patients with elevated risk of hip fracture.