IMAGE-PROCESSING ASSESSMENT OF FEMORAL OSTEOPENIA

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 deve loped algorithms to make automatic assessment of osteopenia from clini cal radiographs. Texture Analysis Models (TA) commonly used in image a nalysis were investigated as measures of osteopenia. Unlike densitomet ric methods, TA characterizes properties of the structure of the image lie, trabecular patterns). A group of women were analyzed whose subje cts ranged from those at risk of osteoporosis (n = 24) to normal (n = 40). Using an IBM PC, frame-grabber, camera, and light-box, we apprais ed five statistical TA algorithms for assessment of the femoral neck i n standard pelvic radiographs: (1) Fractal Signature (FS) describes th e image's fractal nature. (2) Auto-Correlation of unaltered and Sobel Edge Transformed images (ACSE) measures image spatial self-similarity. (3) Go-occurrence Matrices (CM) gives the joint probability of greyle vels with distance/direction and describes statistical relationships o f image variation. (4) Textural Spectrum (TS) neighborhood pixel relat ionships measure regional directional and pixel-inversion properties. (5) Eular Numbers (EN) describe texture by properties (such as connect ivity) of binary images. Good reproducibility from repeated analysis o f radiographs was shown using both paired t-tests and Altman-Bland's m ethods. We have shown a correlation between femoral neck bone mineral density (BMD-the ''gold standard'' of osteoporosis assessment) and tex tural measures for all five algorithms. Significant measures of osteop enia 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 i n osteoporosis. Technology based on these ideas may have a place along side BMD measurements in the assessment of this condition. Copyright ( C) 1997 by W.B. Saunders Company.