As decisions in cardiology increasingly rely on non-invasive methods, fast and precise image analysis tools have become a crucial component of the clinical workflow. Especially when dealing with complex cardiovascular disorders, such as valvular heart disease, advanced imaging techniques have the potential to significantly improve treatment outcome as well as to reduce procedure risks and correlated costs.
This thesis concentrates on three aspects: physiological heart valve modeling, algorithms for patient-specific parameter estimation from multimodal images and advanced applications for clinical management of heart valve disease. In particular, a novel physiological model of the complete valvular apparatus is introduced, which captures a large spectrum of morphologic, dynamic and pathologic variations. A robust learning-based framework is proposed to estimate the patient-specific model parameters from cardiac medical scans, mainly transesophageal echocardiography, cardiac computed tomography and cardiac magnetic resonance imaging.
This original model-driven approach enables a multitude of advanced clinical applications including quantitative valvular analysis, shape-based diagnosis and patient selection as well as computational decision support for valve replacement and repair procedures. In comparison to the gold standard methods, which manually process 2D images, the automatic 4D model-based concept provides fast, precise, reproducible and comprehensive valve quantification. Moreover, in case of emerging percutaneous and minimal invasive valve interventions, cardiac surgeons and interventional cardiologists can substantially benefit from the automated patient selection and virtual valve implantation approaches presented in this thesis. The algorithms proposed in this thesis are validated through extensive quantitative and clinical experiments involving over 476 patients treated in leading medical centers around the world.
«
As decisions in cardiology increasingly rely on non-invasive methods, fast and precise image analysis tools have become a crucial component of the clinical workflow. Especially when dealing with complex cardiovascular disorders, such as valvular heart disease, advanced imaging techniques have the potential to significantly improve treatment outcome as well as to reduce procedure risks and correlated costs.
This thesis concentrates on three aspects: physiological heart valve modeling, algori...
»