Sökning: "Computational Tomography"

Visar resultat 1 - 5 av 15 uppsatser innehållade orden Computational Tomography.

1. 1. Uncertainty Estimation in Volumetric Image Segmentation

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Donggyun Park; [2023]
   Nyckelord :Uncertainty Estimation; Uncertainty Quantification UQ ; Volumetric Image Segmentation; 3D U-Net; test-time data augmentation; Deep ensemble;

   Sammanfattning : The performance of deep neural networks and estimations of their robustness has been rapidly developed. In contrast, despite the broad usage of deep convolutional neural networks (CNNs)[1] for medical image segmentation, research on their uncertainty estimations is being far less conducted. LÄS MER

3. 2. Semi-Automatic Analysis and Visualization of Cardiac 4D Flow CT

   Master-uppsats, Linköpings universitet/Institutionen för hälsa, medicin och vård

   Författare :Anthony van Oosten; [2022]
   Nyckelord :4D CT; CT; 4D flow; Flow Component Analysis; Singular value decomposition; left atrial appendage; LAA; CFD; 3 chamber view; computed tomography; maximum outflow velocity; volume rendered CT; semi-automatic; visualization; flow visualization; cardiac views; semi-automatic analysis; semi-automatic visualization; visualization of 4D flow;

   Sammanfattning : The data obtained from computational fluid dynamics (CFD) simulations of blood flow in the heart is plentiful, and processing this data takes time and the procedure for that is not straightforward. This project aims to develop a tool that can semi-automatically process CFD simulation data, which is based on 4D flow computed tomography (CT) data, with minimal user input. LÄS MER

4. 3. Exploring Deep Learning Frameworks for Multiclass Segmentation of 4D Cardiac Computed Tomography

   Master-uppsats, Linköpings universitet/Institutionen för hälsa, medicin och vård

   Författare :Norman Janurberg; Christian Luksitch; [2021]
   Nyckelord :Computed Tomography; Multiclass Segmentation; Image Segmentation; 4D; Deep Learning; MONAI; Unet; Cropping network; Multiaxis Segmentation;

   Sammanfattning : By combining computed tomography data with computational fluid dynamics, the cardiac hemodynamics of a patient can be assessed for diagnosis and treatment of cardiac disease. The advantage of computed tomography over other medical imaging modalities is its capability of producing detailed high resolution images containing geometric measurements relevant to the simulation of cardiac blood flow. LÄS MER

5. 4. Subject-specific image analysis and computational modelling of the human Achilles tendon

   Master-uppsats, Lunds universitet/Avdelningen för Biomedicinsk teknik

   Författare :Johanna Panzar; Erika Thörn; [2021]
   Nyckelord :image analysis; Achilles tendon; FE model; biomechanics; CT image; Technology and Engineering;

   Sammanfattning : Achilles tendon rupture is becoming more prevalent with an increasing population of middle aged people participating in recreational sports. A torn Achilles tendon will likely not regain its original function, and it is unknown what treatment options are optimal. LÄS MER

7. 5. Evaluation of novel S-ICD electrode placements using computational modeling

   Master-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)

   Författare :Anne-Marie Plancke; [2018]
   Nyckelord :ICD; modeling;

   Sammanfattning : OBJECTIVES The aim of this study is to investigate the influence of new subcutaneous Implantable Cardioverter Defibrillator (ICD) electrode placements on the Defibrillation Threshold (DFT), shock impedance, and sites of activation in the heart caused by a low voltage shock. BACKGROUND The subcutaneous ICD, though it has many advantages due to its less invasive nature compared to the transvenous ICD, requires higher energy shocks to terminate ventricular arrhythmias, and is not currently thought to be able to reliably pace the heart. LÄS MER