<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "Prediction of ventricular pressure and diagnosis from cardiac\r\nmagnetic resonance imaging using artificial neural networks"^^ . "Diastolic heart failure is the most common cause of heart insufficiency worldwide. Diagnosis is\r\ntypically established via hemodynamic measurements during invasive cardiac catheterization.\r\nHowever, this is associated with interventional risks for the patient. In this dissertation artificial\r\nintelligence (AI) models are proposed to predict left-ventricular filling pressures based on non-invasive cardiac magnetic resonance imaging (MRI).\r\nA total cohort of 66,936 patients receiving cardiac catheterization, including 11,699 cardiac MRI\r\nexaminations, was investigated. The developed AI model could distinguish between elevated\r\nand normal filling pressures, providing valuable information on the heart’s diastolic function. The\r\nnovel approach was found superior to established echocardiographic biomarkers and human\r\nexperts.\r\nA secondary AI model was developed to automatically diagnose various types of cardiomyopathies from cardiac MRI. The detectable disease patterns were: hypertrophic, dilated and\r\nischemic cardiomyopathy, cardiac amyloidosis and control. The AI only required a single MRI\r\nframe to reach a diagnosis, which could enable less time-intensive MRI protocols in the future.\r\nBoth AI applications were introspected by attention mapping revealing the AI’s approach to\r\nsolve those tasks, thus contributing to explainability. The AI model behind the filling pressure\r\nprediction was validated in three independent hospitals involving multiple MRI manufacturers,\r\nprotocols and models.\r\nIn essence, artificial neural networks can predict filling pressure and diagnosis from cardiac\r\nMRI, representing a highly scalable approach in the face of overburdened health systems,\r\npotentially impacting future diagnosis and treatment strategies."^^ . "2024" . . . . . . . "David Hermann"^^ . "Lehmann"^^ . "David Hermann Lehmann"^^ . . . . . . "Prediction of ventricular pressure and diagnosis from cardiac\r\nmagnetic resonance imaging using artificial neural networks (PDF)"^^ . . . "Doctoral Thesis David Hermann Lehmann.pdf"^^ . . . "Prediction of ventricular pressure and diagnosis from cardiac\r\nmagnetic resonance imaging using artificial neural networks (Other)"^^ . . . . . . "indexcodes.txt"^^ . . . "Prediction of ventricular pressure and diagnosis from cardiac\r\nmagnetic resonance imaging using artificial neural networks (Other)"^^ . . . . . . "lightbox.jpg"^^ . . . "Prediction of ventricular pressure and diagnosis from cardiac\r\nmagnetic resonance imaging using artificial neural networks (Other)"^^ . . . . . . "preview.jpg"^^ . . . "Prediction of ventricular pressure and diagnosis from cardiac\r\nmagnetic resonance imaging using artificial neural networks (Other)"^^ . . . . . . "medium.jpg"^^ . . . "Prediction of ventricular pressure and diagnosis from cardiac\r\nmagnetic resonance imaging using artificial neural networks (Other)"^^ . . . . . . "small.jpg"^^ . . "HTML Summary of #35861 \n\nPrediction of ventricular pressure and diagnosis from cardiac \nmagnetic resonance imaging using artificial neural networks\n\n" . "text/html" . . . "000 Allgemeines, Wissenschaft, Informatik"@de . "000 Generalities, Science"@en . . . "004 Informatik"@de . "004 Data processing Computer science"@en . .