Development and Evaluation of Advanced Image Analysis Techniques for Pediatric Deep Vein Thrombosis Imaging Scans

Deep vein thrombosis (DVT) is a condition, which results from atherosclerosis and the possible formation of a blood clot (thrombus) in a deep vein leading to obstruction of blood flow. DVT is considered a major cardiovascular health risk and its early detection is considered crucial to patient survival and well-being. The present work describes the development and evaluation of two image analysis techniques for the identification of DVT in children. The first technique is based on entropy thresholding and the second on active contours. The robustness and sensitivity of these techniques have been evaluated both quantitatively as well as qualitatively. Towards that purpose error parameters were calculated using phantom and real patient images. The usefulness of our techniques was evaluated by specialist radiologists. The suggested algorithms were developed with the Matlab (R) simulation environment. Thus the present work has been implemented towards the improvement of pediatric patients' well-being and at the same time achieve early DVT prognosis.