A5038367345- Medical Image Segmentation Techniques
- Surgical Simulation and Training
- Advanced Neural Network Applications
- Augmented Reality Applications
- Generative Adversarial Networks and Image Synthesis
- Robotics and Sensor-Based Localization
- Ultrasound Imaging and Elastography
- Advanced MRI Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Face recognition and analysis
- 3D Shape Modeling and Analysis
- Soft Robotics and Applications
- Anatomy and Medical Technology
- Vascular Malformations Diagnosis and Treatment
- Cerebrospinal fluid and hydrocephalus
- Computer Graphics and Visualization Techniques
- Autonomous Vehicle Technology and Safety
- Intracranial Aneurysms: Treatment and Complications
- Medical Imaging Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Advanced Image Processing Techniques
- Medical Imaging and Analysis
- Traffic Prediction and Management Techniques
- AI in cancer detection
- Cerebrovascular and Carotid Artery Diseases
Norwegian University of Science and Technology
2016-2025
SINTEF
2010-2019
NTNU Samfunnsforskning
2014-2015
St Olav's University Hospital
2006-2014
Intraoperative ultrasound imaging is used in brain tumor surgery to identify remnants. The images may some cases be more difficult interpret the later stages of operation than beginning operation. aim this paper explain causes surgically induced artefacts and how they can recognized reduced.The theoretical reasons for are addressed impact discussed. Different setups acquisition different acoustic coupling fluids fill up resection cavity evaluated with respect improved image quality.The...
Real-time 3D Echocardiography (RT3DE) has been proven to be an accurate tool for left ventricular (LV) volume assessment. However, identification of the LV endocardium remains a challenging task, mainly because low tissue/blood contrast images combined with typical artifacts. Several semi and fully automatic algorithms have proposed segmenting in RT3DE data order extract relevant clinical indices, but systematic fair comparison between such methods so far impossible due lack publicly...
Generative Adversarial Networks (GANs) are widely adopted for anonymization of human figures. However, current state-of-the-art limits to the task face anonymization. In this paper, we propose a novel framework (DeepPrivacy2) realistic figures and faces. We introduce new large diverse dataset full-body synthesis, which significantly improves image quality diversity generated images. Furthermore, style-based GAN that produces high-quality, diverse, editable anonymizations. demonstrate our...
We have integrated a neuronavigation system into an ultrasound scanner and developed single-rack that enables the surgeon to perform frameless armless stereotactic using intraoperative three-dimensional data as well preoperative magnetic resonance or computed tomographic images. The purpose of this article is describe our two-rack prototype present results work on image quality enhancement.The consists high-end scanner, modest-cost computer, optical positioning/digitizer system. Special...
Three-dimensional (3D) images provide a comprehensive view of material microstructures, enabling numerical simulations unachievable with two-dimensional (2D) imaging alone. However, obtaining these 3D can be costly and constrained by resolution limitations. We introduce novel method capable generating large-scale such as metal or rock, from single 2D image. Our approach circumvents the need for image data while offering cost-effective, high-resolution alternative to existing techniques....
This paper presents an overview of the image-guided surgery toolkit (IGSTK). IGSTK is open source C++ software library that provides basic components needed to develop applications. It intended for fast prototyping and development The was developed through a collaboration between academic industry partners. Because designed safety-critical applications, team has adopted lightweight processes emphasizes safety robustness while, at same time, supporting geographically separated developers. A...
Introduction Our motivation is increased bronchoscopic diagnostic yield and optimized preparation, for navigated bronchoscopy. In bronchoscopy, virtual 3D airway visualization often used to guide a tool peripheral lesions, synchronized with the real time video Visualization during segmentation methods, differs. Time consumption logistics are two essential aspects that need be when integrating such technologies in interventional room. We compared three different approaches obtain centerlines...
Abstract Obtaining an accurate segmentation of images obtained by computed microtomography (micro-CT) techniques is a non-trivial process due to the wide range noise types and artifacts present in these images. Current methodologies are often time-consuming, sensitive artifacts, require skilled people give results. Motivated rapid advancement deep learning-based recent years, we have developed tool that aims fully automate one step, without need for any extra image processing steps such as...
Recent work on image anonymization has shown that generative adversarial networks (GANs) can generate near-photorealistic faces to anonymize individuals. However, scaling up these the entire human body remained a challenging and yet unsolved task. We propose new method generates realistic humans for in-the-wild images. A key part of our design is guide nets by dense pixel-to-surface correspondences between an canonical 3D surface. introduce Variational Surface-Adaptive Modulation (V-SAM)...