Improved Radiography Image

About

Track Code CWRU004 ​Abstract Cardiovascular disease is the leading cause of death in the United States, responsible for approximately 500,000 deaths per year. More than one million Americans have heart attacks or angina every year. The increasing incidence of cardiovascular disease makes accurate and noninvasive imaging of early cardiovascular disease increasing important. Recently, digital radiography (DR) has markedly improved imaging of cardiac and lung diseases. Digital technology has enabled the use of dual-energy techniques in digital radiography systems. With recent advancements in digital radiography and flat-panel technology, dual-energy subtraction techniques can produce a high-energy image and a low-energy image. Post-processing of these two images results in the following images: a standard high-energy image, a subtracted soft-tissues image that removes the overlying bone from the underlying lung and mediastinum, and a low-energy bone image that optionally displays bone and calcified thoracic structure. Thus, dual-energy digital radiography could be a cost-effective screening tool for cardiac and lung diseases. However, cardiac and/or lung motion causes artifacts on the subtracted images, resulting in inconsistent detection and diagnosis of cardiac and lung diseases. Though the high-energy and low-energy images are taken within a very short period of time, they still represent different phases of cardiac and respiration motion cycles. Because the two images may not be perfectly aligned, subtracting one image from the other will generate motion artifacts and reduce the image quality. Researchers at Case Western Reserve University have developed deformable registration algorithms for this application. These registration techniques include new methods for feature extraction, similarity optimization, and non-rigid transformation. The registration techniques can improve the image quality of dual-energy digital radiography and reduce motion artifacts on the subtracted images. Thus, the techniques can increase the accuracy of detection and diagnosis of cardiac and lung diseases. This method has been tested on clinical patient data and the software can be used as standalone or embedded into existing manufacturer's software. This technology was developed in part using funding from the Coulter-Case Translational Research Partnership.