Abstract-This paper presents applications of entropic spanning graphs to imaging and feature clustering applications. Entropic spanning graphs span a set of feature vectors in such a way that the normalized spanning length of the graph converges to the entropy of the feature distribution as the number of random feature vectors increases. This property makes these graphs naturally suited to applications where entropy and information divergence are used as discriminants including: texture classification; feature clustering; image indexing; and image registration. Among other areas, these problems arise in geographical information systems, digital libraries, medical information processing, video indexing, multi-sensor fusion, and content-based retrieval.
The accuracy of magnetic resonance imaging of the hip was prospectively evaluated in 19 military subjects engaged in endurance training. These patients had hip pain, negative radiographs, and radionuclide bone scans consistent with femoral neck stress fracture. Twenty-two hips were identified as positive for femoral neck stress fracture by bone scan. Each patient underwent magnetic resonance imaging and 6-week follow-up plain radiographs of the hips. Magnetic resonance imaging studies differentiated femoral neck stress fractures from a synovial pit, iliopsoas muscle tear, iliopsoas tendinitis, obturator externus tendinitis, avascular necrosis of the femoral head, and a unicameral bone cyst. The follow-up radiographs were used to verify the diagnosis of stress fracture. The radiographs showed healing callus in patients with stress fractures. Patients with diagnoses other than stress fractures had no changes on follow-up radiographs. Magnetic resonance imaging studies were as sensitive and much more specific than bone scan in determining the cause of hip pain. Radionuclide bone scan had an accuracy of 68% for femoral neck stress fractures with 32% false-positive results; MRI was 100% accurate. Magnetic resonance imaging proved to be superior to radionuclide bone scanning in providing an early and accurate diagnostic tool that aided in the differential diagnosis of hip pain in the young endurance athlete.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.