Optical processing of radiographic trabecular pattern versus bone mineral density of proximal femur as measures of bone strength.

The purpose of the present study was to evaluate a noninvasive method that utilizes optical processing to analyze the trabecular pattern on bone radiographs. The trabecular network on proximal femur radiographs of 17 intact cadaveric femora was analyzed by optical Fourier transform, yielding a trabecular bone index (TBI) at several locations. The bone mineral density (BMD) of the proximal femur was measured by dual X-ray absorptiometry. Dimensions of the proximal femur were obtained from the radiograph. The bones were fractured in a "fall configuration" to yield the fracture load. A multiple regression model, combining only radiograph- derived parameters-bone dimensions and the TBI at the intertrochanteric region and at the greater trochanter-yielded a correlation of 0.938 with the fracture load. A model combining the BMD at the greater trochanter and at the neck yielded a correlation of 0.928 with the fracture load. When all the variables were introduced into a combined analysis, the correlation with the fracture load was 0.973. The TBI obtained by optical processing of the trabecular bone pattern on femoral radiographs together with bone dimensions derived from these radiographs may serve as an effective estimate for hip fracture risk.

Analysis of clustered microcalcifications by using a single numeric classifier extracted from mammographic digital images.

RATIONALE AND OBJECTIVES: The authors prospectively tested the performance of a single numeric classifier constructed from a discriminative analysis classification system based on automatic computer-extracted quantitative features of clustered microcalcifications. MATERIALS AND METHODS: Mammographically detected clustered microcalcifications in patients who had been referred for biopsy were digitized at 600 dpi with an 8-bit gray scale. A software program was developed to extract features automatically from digitized images to describe the clustered microcalcifications quantitatively. The significance of these features was evaluated by using the Wilcoxon test, the Welch modified two-sample t test, and the two-sample Kolmogorov-Smirnov test. A discriminant analysis pattern recognition system was constructed to generate a single numeric classifier for each case, based on the extracted features. This system was trained on 137 archival known reference cases and its performance tested on 24 unknown prospective cases. The results were evaluated by using receiver operating characteristic analysis. RESULTS: Thirty-seven extracted parameters demonstrated a statistically significant difference between the values for the benign and for the malignant lesions. Seven independent factors were selected to construct the classifier and to evaluate the unknown prospective cases. The area under the receiver operating characteristic curve for the prospective cases was 0.88. CONCLUSION: A pattern recognition classifier based on quantitative features for clustered microcalcifications at screen-film mammography was found to perform satisfactorily. The software may be of value in the interpretation of mammographically detected microcalcifications.