Computer-aided detection and characterization of hyperparathyroidism in digital hand radiographs

A computer algorithm has been developed to detect and possibly stage subperiosteal resorption from digitized hand radiographs for patients with primary or secondary hyperparathyroidism. The method can quantify the severity of bony resorption by analyzing the roughness of the radial phalangeal margins as projected on the hand radiographs. This margin is detected by a model-guided boundary-tracking scheme and its roughness is quantified by the mean-square variation and the first moment of the power spectrum. The preliminary results indicate that the computer-aided diagnosis system if accurately trained, may assist radiologists in detection and staging of hyperparathyroidism by providing reproducible and consistent analysis of bony erosion.<>