A5047066555- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Advanced Radiotherapy Techniques
- Tracheal and airway disorders
- Augmented Reality Applications
- Ultrasound in Clinical Applications
- Flow Measurement and Analysis
- Dysphagia Assessment and Management
- Robotics and Sensor-Based Localization
- Salivary Gland Tumors Diagnosis and Treatment
- Voice and Speech Disorders
- Esophageal Cancer Research and Treatment
- Ultrasound Imaging and Elastography
- Oral and Maxillofacial Pathology
- AI in cancer detection
- Cardiovascular Health and Disease Prevention
- Soft Robotics and Applications
- Computer Graphics and Visualization Techniques
- Orthopedic Infections and Treatments
- Medical Imaging and Pathology Studies
- Neuroscience of respiration and sleep
- Elasticity and Material Modeling
- Head and Neck Surgical Oncology
- Anesthesia and Neurotoxicity Research
- Obstructive Sleep Apnea Research
Norwegian University of Science and Technology
2014-2025
Levanger Hospital
2014-2025
St Olav's University Hospital
2013-2017
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...
Mechanical characterization of hydrogels and ultra-soft tissues is a challenging task both from an experimental material parameter estimation perspective because they are much softer than many biological materials, ceramics, or polymers. The elastic modulus such materials within the 1 - 100 kPa range, behaving as hyperelastic solid with strain hardening capability at large strains. In current study, indentation experiments have been performed on agarose hydrogels, bovine liver, lymph node...
Endobronchial ultrasound (EBUS) is used in the minimally invasive sampling of thoracic lymph nodes. In lung cancer staging, accurate assessment mediastinal structures essential but challenged by variations anatomy, image quality, and operator-dependent interpretation. This study aimed to automatically detect segment nodes blood vessels employing a novel U-Net architecture-based approach EBUS images. A total 1161 images from 40 patients were annotated. For training validation, 882 30 145 5...
Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a cornerstone in minimally invasive thoracic lymph node sampling. In lung cancer staging, precise assessment of position crucial for clinical decision-making. This study aimed to demonstrate new deep learning method classify nodes based on their anatomical location using EBUS images. Bronchoscopists labeled stations real-time according the Mountain Dressler nomenclature. images were then used train and test...
The purpose of this pilot study was to investigate if sleep classification data from a non-contact monitor placed in the patient's bedroom at home were associated with obstructive apnea (OSA) severity time primary investigation. Secondly, we aimed effect established continuous positive airway pressure (CPAP) therapy on objective measurements. We performed prospective single center medium size hospital. Adult patients referred symptoms that could indicate OSA underwent standard respiratory...
The increased workload in pathology laboratories today means automated tools such as artificial intelligence models can be useful, helping pathologists with their tasks. In this paper, we propose a segmentation model (DRU-Net) that provide delineation of human non-small cell lung carcinomas and an augmentation method improve classification results. proposed is fused combination truncated pre-trained DenseNet201 ResNet101V2 patch-wise classifier, followed by lightweight U-Net refinement...
LBA8005 Background: A majority of patients with LS SCLC relapse after potentially curative CRT and better treatment is needed. Immunotherapy prolongs survival in extensive stage non-small cell lung cancer. We investigated whether atezolizumab (“atezo”) SCLC. Methods: Patients PS 0-2 non-progression (PD) platinum/etoposide chemotherapy concurrent twice-daily thoracic radiotherapy (TRT) 45 Gy/30 or 60 Gy/40 fractions were randomized 1:1 to observation atezo 1200 mg Q3W for 1 year, until PD...
Endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA) of mediastinal lymph nodes is essential for lung cancer staging and distinction between curative palliative treatment. Precise sampling crucial. Navigation multimodal imaging may improve the efficiency EBUS-TBNA. We demonstrate a novel EBUS-TBNA navigation system in dedicated airway phantom.Using convex probe EBUS bronchoscope (CP-EBUS) with an integrated sensor electromagnetic (EM) position tracking, we performed...
Chronic obstructive pulmonary disease (COPD), low lung function independent of diagnosis and markers inflammation are all associated with increased morbidity mortality. Microalbuminuria, reflecting endothelial dysfunction, could be a relevant inflammatory marker potential systemic effects COPD. We hypothesised that there was positive association between microalbuminuria mortality in individuals conducted 12-year follow-up study 3129 participants the second survey Nord-Trøndelag Health Study...
The accuracy of navigated bronchoscopy relies on a best possible correlation between the preoperative computed tomography images used for planning and actual tumor position during bronchoscopy. Change in lung structure procedure may reduce success rate. size changes breathing, which be predicted at least partly compensated by navigation system. We have studied effect itself, to see if how causes further distortions, might harder predict compensate.Using newly developed tracking sensors, we...
Purpose: Electromagnetic based navigated bronchoscopy using preoperative CT images has reached the clinic during last decade. One of challenges is “CT to patient anatomy alignment” acquired days or even weeks ahead bronchoscopy. An automatic registration method, without manual anatomical landmarks, was developed, implemented, and evaluated in current study. Methods: The method aligns automatically patientˈs initial part algorithm a modified version an iterative closest point algorithm, which...
Background Endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA) is the endoscopic method of choice for confirming lung cancer metastasis to mediastinal lymph nodes. Precision crucial correct staging and clinical decision-making. Navigation multimodal imaging can potentially improve EBUS-TBNA efficiency. Aims To demonstrate feasibility a image guiding system using electromagnetic navigation bronchoschopy in humans. Methods Four patients referred diagnosis with were enrolled...
One of the major challenges in electromagnetic navigated bronchoscopy is navigation accuracy. An initial rigid image-to-patient registration may not be optimal for entire lung volume, as tissue anatomy likely to have shifted since time computer tomography (CT) acquisition. The accuracy will also affected throughout procedure by breathing, coughing, patient movement and displacements due pressure from tools. A method minimize negative impact these factors updating locally during needed...
In flexible endoscopy techniques, such as bronchoscopy, there is often a challenge visualizing the path from start to target based on preoperative data and accessing these during procedure. An example of this only inside central airways in bronchoscopy. Virtual bronchoscopy (VB) does not meet pulmonologist's need detect, define sample frequent targets outside bronchial wall. Our aim was develop study new visualization technique for navigated bronchoscopy.We extracted shortest possible top...
The established method for assessment of mediastinal and hilar lymph nodes is endobronchial ultrasound bronchoscopy (EBUS) with needle aspirations. Previously, we presented an electromagnetic navigation platform this purpose. There were several issues the permanent tracking (EMT) sensor attachment on tip experimental EBUS bronchoscope. purpose was to develop a device on-site EMT sensor.A clip-on 3D-printed in Ultem™ attached A specially designed probe calibration adapter developed quick...
<b>Introduction</b> Multimodal image guiding systems may improve precision, safety and documentation of lung cancer staging with endobronchial ultrasound fine needle aspiration (EBUS-TBNA). 3D EBUS is possible using electromagnetic (EM) navigated EBUS. <b>Aims objectives</b> We wanted to demonstrate the clinical feasibility multimodal guiding. <b>Methods</b> Four patients referred for participated in study. Models predefined lymph nodes were created from preoperative computed tomography...
Background: Bronchoscopy for peripheral lung lesions may involve image sources such as computed tomography (CT), fluoroscopy, radial endobronchial ultrasound (R-EBUS), and virtual/electromagnetic navigation bronchoscopy. Our objective was to evaluate the feasibility of replacing these multiple monitors with a head-mounted display (HMD), always providing relevant data in line sight bronchoscopist. Methods: A total 17 pulmonologists wearing HMD (Microsoft ® HoloLens 2) performed bronchoscopy...
Abstract Background and objective Patients suspected to have lung cancer, undergo endobronchial ultrasound bronchoscopy (EBUS) for the purpose of diagnosis staging. For presumptive curable patients, EBUS is planned based on images data from computed tomography (CT) positron emission (PET). Our study aimed evaluate feasibility a multimodal electromagnetic navigation platform bronchoscopy, integrating segmented CT, PET scan imaging data. Methods The proof-of-concept included patients with...
Considering the increased workload in pathology laboratories today, automated tools such as artificial intelligence models can help pathologists with their tasks and ease workload. In this paper, we are proposing a segmentation model (DRU-Net) that provide delineation of human non-small cell lung carcinomas an augmentation method improve classification results. The proposed is fused combination truncated pre-trained DenseNet201 ResNet101V2 patch-wise classifier followed by lightweight U-Net...
<title>Abstract</title> Considering the increased workload in pathology laboratories today, automated tools such as artificial intelligence models can help pathologists with their tasks and ease workload. In this paper, we are proposing a segmentation model (DRU-Net) that provide delineation of human non-small cell lung carcinomas an augmentation method improve classification results. The proposed is fused combination truncated pre-trained DenseNet201 ResNet101V2 patch-wise classifier...
Patients suspected to have lung cancer, undergo endobronchial ultrasound bronchoscopy (EBUS) for the purpose of diagnosis and staging. For presumptive curable patients, EBUS is planned based on images data from computed tomography (CT) positron emission (PET). Our study aimed evaluate feasibility a multimodal electromagnetic navigation platform bronchoscopy, integrating segmented CT, PET scan imaging data.