Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 24 for “"3D U-Net"”.
-
Entwicklung eines 3D-U-Net-Modells zur automatisierten Segmentierung anatomischer Regionen der Maxilla und Mandibula
… Aufnahmen unter Verwendung einer 3D-U-Net-Architektur entwickelt. Die Segmentierungsgenauigkeit wurde mittels Ähnlichkeitskoeffizienten nach Dice, 95 %-Hausdorff-Distanz und flächenbasierten Ähnlichkeitsmaßes nach Dice anhand 20 unabhängiger Aufnahmen mit der manuellen …
-
U-Net for Cerebral Cortical MR Image Segmentation
… from three-dimensional structural Magnetic Resonance (MR) brain images plays an important role in measuring loss of cortical tissues for disorders such as Alzheimer's disease (AD). U-Net, a type of deep convolutional neural networks architecture, is a widely-used approach for …
-
STATISTICAL SHAPE AND DEEP LEARNING EYE SEGMENTATION FROM CT SCANS
… for this task. In stage one, an attention 3D U-Net has been applied to segment the whole eyeball from the brain CT images. In stage two, a multi-class 3D U-Net is designed to label different regions in the eyeball. The two-stage 3D U-Net achieves real-time segmentation in test images with …
-
Advanced boundary-enhanced instance segmentation and spatial-temporal transformer models for automated schizophrenic investigation
… thesis introduces Boundary-Refined Attention Network (BoRefAttnNet), a novel boundary-refined 3D U-Net variant specifically designed for precise segmentation of subcortical brain structures from structural magnetic resonance imaging (sMRI). BoRefAttnNet incorporates multi-scale boundary …
-
Reliable and robust hip dysplasia measurement with three-dimensional ultrasound and convolutional neural networks
… in probe positioning, leading to misdiagnosis. 3D ultrasound, being more robust to errors in probe positioning, has been introduced as a more reliable alternative. In this thesis, we aim to further improve the image processing techniques of the 3D ultrasound-based system, addressing three …
-
Automated Deep Learning Segmentation of Neonatal Cerebral Lateral Ventricles from Three-Dimensional Ultrasound Images
… (2D) ultrasound (US), three-dimensional (3D) US is a more sensitive alternative that can provide quantitative information for monitoring neonatal cerebral lateral ventricles. Currently, manual segmentation of the cerebral ventricles is time-consuming due to poor image contrast and complex …
-
Deep Learning to Construct Computational Head Models for Modelling Electroconvulsive Therapy
… simulating ECT stimulation, segmentation of magnetic resonance image (MRI) head scans is essential. This segmentation can be performed manually, which is laborious and time-consuming, or automatically. Various automatic segmentation approaches have been utilized to segment MRI head scans, …
-
Volumetric medical image segmentation with deep learning pipelines
… clinical workflow. Fully convolutional networks (FCNs) have been heavily used in this area due to the level of success that they have achieved. In this work, we first leverage recent architectural innovations to make an initial segmentation: (i) spatial and channel-wise squeeze and …
-
Tree Structure Retrieval for Apple Trees from 3D Pointcloud
3D reconstruction is a challenging problem and has been an important research topic in the areas of remote sensing and computer vision for many years. Existing 3D reconstruction approaches are not suitable for orchard applications due to complicated tree structures. Current tree reconstruction has …
-
Deep Learning for Validating Resolution and Detecting Secondary Structure Elements of Proteins in 3D Cryo-Electron Microscopy Images
… growing number of published three-dimensional (3D) cryo-EM density maps. However, the resolution value claimed for the reconstructed 3D density map has been the topic of scientific debate for many years. The Fourier Shell Correlation (FSC) is the currently accepted cryo-EM resolution measure, …
-
Deep Learning Approach for Cell Nuclear Pore Detection and Quantification over High Resolution 3D Data
… cell nuclear pores in high-resolution 3D microscopy data is critical for cellular biology and disease research. This thesis introduces a deep learning pipeline crafted to automate the segmentation and quantification of nuclear pores from high-resolution 3D cell organelle images. Our aim …
-
Deep Learning Domain Adaptation in Brain MRI: Investigating Motion Mitigation in Adult and Neonatal Scans
Magnetic Resonance Imaging (MRI) is a vital non-invasive tool for high-resolution brain imaging, yet its long acquisition time frequently results in patient movement leading to motion artifacts, particularly among non-compliant patients like newborns. While Deep Learning (DL) models have emerged as …
-
Deep Learning-Based Prediction of Daily Delivered Dose for Advanced Lung Cancer Radiotherapy
… for every treatment fraction is impractical. A 3D U-Net model was adapted and optimised to predict daily dose distributions in advanced non-small-cell lung cancer (NSCLC), enabling evaluation of dose deviations due to interfractional changes and supporting timely re-planning decisions. The U-Net …
-
Utilização de inteligência artificial para mensurar a espessura do palato em tomografias computadorizadas com vistas à técnica marpe
… using the "Create new point list" tool in the 3D Slicer® software. These points served as the ground-truth for training a 3D U-Net neural network. The landmark detection model was trained using 3D patches, employing convolutional neural networks techniques and lightweight attention mechanisms. …
-
Deep learning for ultrasonic non-destructive evaluation of aerospace composites
… supervised model was then employed to train a 3D U-Net for segmentation, which performed well in sizing and localising defects within the training distribution. However, the model's performance declined when tested on out-of-distribution samples.The final phase of research explored …
-
Advancing a tracked two-dimensional ultrasound system for assessing dysplasia metrics toward clinical deployment
… placement, and patient positioning. Although 3D ultrasound (3DUS) offers improved reliability, its high cost and limited availability restrict widespread clinical use. To address this gap, we developed an Optically Tracked Ultrasound (OTUS) system that reconstructs 3D volumes from tracked …
-
Automatic assessment of spinal deformities in 2D and 3D
… on dual energy X-ray absorptiometry (DXA) and 3D measurements on Magnetic Resonance Imaging (MRI), unifying 2D and 3D information. <br><br>We start by the development of an end-to-end pipeline for 2D scoliosis assessment using DXA scans from the UK Biobank. This foundational work introduces a …
-
Artificial intelligence for cancer imaging: Integrated frameworks for hepatocellular carcinoma and pulmonary nodules.
… framework that combines ROI localization with a 3D U-Net trained using an adaptive focal cross-entropy loss to sharpen boundaries under severe voxel imbalance; (v) a diagnosis model that leverages higher-order texture via a modified local ternary pattern alongside a stacking classifier to improve …
-
Novel approaches to automated target volume definition in glioblastoma patients using machine learning
… Zu diesem Zweck wurde eine modifizierte 3D-U-Net-Architektur verwendet. Das Training erfolgte mit 45 Patienten und die Validierung anschließend mit 15 Patienten. Die Rezidivanalyse umfasste 97 Patienten, die zwischen 2013 und 2017 an der Universitätsklinik Freiburg behandelt wurden. Der …
-
Learning diffusion MR from commercially available protocols: bringing advanced tractography into routine neurosurgical practice
… diffusivity of brain tissues on diffusion magnetic resonance imaging (dMRI). To obtain high-quality local fiber orientation distributions (FODs), which are necessary for reliable tractography, it is required acquisition parameters with high signal magnitude (b-values) and a high number of …
Page 1 of 2