<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "Data-driven Measures for Dose Reduction and Image Quality Enhancement in Computed Tomography"^^ . "Dose reduction without sacrificing image quality is one of the primary aims of computed\r\ntomography (CT) research. Especially in interventional applications, which require multiple\r\nscans, dose reduction is paramount. Two pathways of arbitrarily reducing dose are the reduction\r\nof tube current (low-mAs CT) and reduction of number of projections (sparse-view CT). The\r\nformer will increase noise, the latter sparseness artifacts, such that there is a trade-off between\r\ndose and image quality in either case. Additionally, if the patient does not fully fit in the\r\nfield of measurement, as is typical for interventional cone-beam CT, the image will suffer from\r\ntruncation artifacts and a small field of view. Novel deep neural networks have shown promising\r\nresults in a variety of image processing tasks. The aim of this thesis is therefore to analyze the\r\ndifferent low-dose CT realizations in conjunction with deep learning-based image processing and\r\nfacilitate reconstruction from truncated projections with both a data-driven and iterative method.\r\nQuantitative image quality analysis of low-dose CT is performed with several conventional and\r\ntask-based methods. The latter are able to distinguish between sufficiently and insufficiently\r\ntrained networks, ensuring a safe utilization of deep learning-based methods. The well-trained\r\nneural networks are able to support the tested 80% dose reduction by restoring image quality.\r\nBetween the different realizations of low-dose CT, low-mAs CT is determined as preferable.\r\nBoth detruncation methods achieve satisfactory results. However, the computational cost of\r\nDART remains prohibitive while the deep learning-based detruncation promises to increase the\r\nfield of view in real-time. This in turn may improve image guidance and secondary algorithms\r\nduring operations."^^ . "2024" . . . . . . . "Achim Jan"^^ . "Byl"^^ . "Achim Jan Byl"^^ . . . . . . "Data-driven Measures for Dose Reduction and Image Quality Enhancement in Computed Tomography (PDF)"^^ . . . "2024 Diss Data-Driven Dose Reduction and Image Quality Enhancements Achim Byl.pdf"^^ . . . "Data-driven Measures for Dose Reduction and Image Quality Enhancement in Computed Tomography (Other)"^^ . . . . . . "lightbox.jpg"^^ . . . "Data-driven Measures for Dose Reduction and Image Quality Enhancement in Computed Tomography (Other)"^^ . . . . . . "preview.jpg"^^ . . . "Data-driven Measures for Dose Reduction and Image Quality Enhancement in Computed Tomography (Other)"^^ . . . . . . "medium.jpg"^^ . . . "Data-driven Measures for Dose Reduction and Image Quality Enhancement in Computed Tomography (Other)"^^ . . . . . . "small.jpg"^^ . . . "Data-driven Measures for Dose Reduction and Image Quality Enhancement in Computed Tomography (Other)"^^ . . . . . . "indexcodes.txt"^^ . . "HTML Summary of #34983 \n\nData-driven Measures for Dose Reduction and Image Quality Enhancement in Computed Tomography\n\n" . "text/html" . . . "530 Physik"@de . "530 Physics"@en . .