Abstract
Visual assessment of femoral osteopenia (the radiographic presentation of osteoporosis) is unreliable. Many of the short-comings of observer grading can be overcome by digital image analysis. Our group has developed algorithms to make automatic assessment of osteopenia from clinical radiographs. Texture Analysis Models (TA) commonly used in image analysis were investigated as measures of osteopenia. Unlike densitometric methods, TA characterizes properties of thestructure of the image (ie, trabecular patterns). A group of women were analyzed whose subjects ranged from those at risk of osteoporosis (n=24) to normal (n=40). Using an IBM PC, frame-grabber, camera, and light-box, we appraised five statistical TA algorithms for assessment of the femoral neck in standard pelvic radiographs: (1)Fractal Signature (FS) describes the image’s fractal nature. (2)Auto-Correlation of unaltered and Sobel Edge Transformed images (ACSE) measures image spatial self-similarity. (3)Co-occurrence Matrices (CM) gives the joint probability of greylevels with distance/direction and describes statistical relationships of image variation. (4)Textural Spectrum (TS) neighborhood pixel relationships measure regional directional and pixel-inversion properties. (5)Eular Numbers (EN) describe texture by properties (such as connectivity) of binary images. Good reproducibility from repeated analysis of radiographs was shown using both pairedt-tests and Altman-Bland’s methods. We have shown a correlation between femoral neck bone mineral density (BMD—the “gold standard” of osteoporosis assessment) and textural measures for all five algorithms. Significant measures of osteopenia were: ACSE (r=0.6,P < .001), CM (r=−0.69,P < .001), FS (r=0.35,P < .01), TS (r=0.52,P < .001) and EN (r=−0.39,P < .01). Relationships were also found between textural characteristics and age/weight. TA techniques characterize the radiographic changes of bone in osteoporosis. Technology based on these ideas may have a place alongside BMD measurements in the assessment of this condition.
Key Words: osteoporosis, femoral radiographs, digital image processing, texture analysis
Full Text
The Full Text of this article is available as a PDF (968.4 KB).
Footnotes
Supported by SmithKline Beecham Pharmaceuticals, New Frontiers Science Park, Harlow, Essex, UK, PhD Studentship.
References
- 1.Wallach S, Feinblatt JD, Avioli LV. The Bone “Quality” Problem. Calcif Tissue Int. 1992;51:169–172. doi: 10.1007/BF00334542. [DOI] [PubMed] [Google Scholar]
- 2.Singh M, Nagrath AR, Maini PS. Changes in the trabecular pattern of the upper end of the femur as an index of osteoporosis. J Bone Joint Surg. 1970;52-A:457–467. [PubMed] [Google Scholar]
- 3.Zucker SW, Terzopoulos D. Finding structure in cooccurrence matrices for texture analysis. Computer Graphics and Image Processing. 1980;12:286–308. doi: 10.1016/0146-664X(80)90016-7. [DOI] [Google Scholar]
- 4.Sonka M, Hlavac V, Boyle R. Texture. In: Sonka M, Hlavac V, Boyle R, editors. Image Processing, Analysis and Machine Vision. London, UK: Chapman and Hall; 1993. pp. 480–485. [Google Scholar]
- 5.Dong-Chen H, Li W. Texture features based on texture spectrum. Pattern Recognition. 1991;24:391–399. doi: 10.1016/0031-3203(91)90052-7. [DOI] [Google Scholar]
- 6.Gonzalez RC, Woods RE. Image segmentation. In: Gonzalez RC, Woods RE, editors. Digital Image Processing. New York, NY: Addison Wesley; 1992. pp. 416–429. [Google Scholar]
- 7.Gonzalez RC, Woods RE. Image Enhancement. In: Gonzalez RC, Woods RE, editors. Digital Image Processing. New York, NY: Addison Wesley; 1992. pp. 209–213. [Google Scholar]
- 8.Rosenfeld A, Kak AC. Enhancement. In: Rosenfeld A, Kak AC, editors. Digital Picture Processing. New York, NY: Academic; 1976. pp. 173–175. [Google Scholar]
- 9.Lynch JA, Hawkes DJ, Buckland-Wright JC. A robust and accurate method for calculating the fractal signature of texture in macroradiographs of osteoarthritic knees. Med Inform. 1991;16:241–251. doi: 10.3109/14639239109012130. [DOI] [PubMed] [Google Scholar]
- 10.Geraets WGM, Stelt PF, Netelenbos CJ, et al. A new method for automatic recognition of the radiographic trabecular pattern. J Bone Miner Res. 1990;5:227–233. doi: 10.1002/jbmr.5650050305. [DOI] [PubMed] [Google Scholar]
- 11.Gonzalez RC, Woods RE. Representation and Description. In: Gonzalez RC, Woods RE, editors. Digital Image Processing. New York, NY: Addison Wesley; 1992. pp. 548–560. [Google Scholar]
- 12.Altman DG, Bland JM. Measurements in medicine: The analysis of method comparison studies. The Statistician. 1983;32:307–317. doi: 10.2307/2987937. [DOI] [Google Scholar]
- 13.Bland M. Clinical measurement. In: Bland M, editor. An Introduction to Medical Statistics. Oxford, UK: Oxford Medical Publications; 1995. pp. 266–269. [Google Scholar]