A5006902389- Cardiac pacing and defibrillation studies
- Colorectal Cancer Screening and Detection
- Advanced MRI Techniques and Applications
- Esophageal Cancer Research and Treatment
- Gastric Cancer Management and Outcomes
- Advanced X-ray and CT Imaging
- Cardiac Arrhythmias and Treatments
- Radiomics and Machine Learning in Medical Imaging
- Advanced Vision and Imaging
- Photoacoustic and Ultrasonic Imaging
- Atrial Fibrillation Management and Outcomes
- Neurological disorders and treatments
- Ultrasound and Hyperthermia Applications
- Lung Cancer Diagnosis and Treatment
- COVID-19 diagnosis using AI
- Video Surveillance and Tracking Methods
- Image Processing Techniques and Applications
- Advanced Image Processing Techniques
- Traumatic Brain Injury and Neurovascular Disturbances
- Cardiac Valve Diseases and Treatments
- Image Retrieval and Classification Techniques
- Esophageal and GI Pathology
- Photonic Crystal and Fiber Optics
- Acute Ischemic Stroke Management
- Colorectal Cancer Surgical Treatments
University Hospital of Zurich
2024
University of Pecs
2023-2024
London Vision Clinic
2020-2023
University of Miskolc
2017-2023
Comenius University Bratislava
2022-2023
King's College London
2016-2021
Vienna General Hospital
2020
Siemens (United Kingdom)
2016-2018
St Thomas' Hospital
2017
Probity Medical Research
2016
Pruritus and skin discomfort/pain negatively impact health-related quality of life (HRQoL). The effects apremilast, an oral phosphodiesterase inhibitor, on pruritus, discomfort/pain, patient global assessment psoriasis disease activity (PgAPDA) were assessed in moderate/severe chronic plaque patients the phase 3 ESTEEM trials. Significant improvements pruritus observed at Week 2 with apremilast versus placebo (both studies, p < 0.0001) sustained through 32. Among apremilast-treated patients,...
Abstract Background and aims Seattle protocol biopsies for Barrett's Esophagus (BE) surveillance are labour intensive with low compliance. Dysplasia detection rates vary, leading to missed lesions. This can potentially be offset computer aided detection. We have developed convolutional neural networks (CNNs) identify areas of dysplasia where target biopsy. Methods 119 Videos were collected in high‐definition white light optical chromoendoscopy i‐scan (Pentax Hoya, Japan) imaging patients...
Colonoscopy is the gold standard for early diagnosis and pre-emptive treatment of colorectal cancer by detecting removing colonic polyps. Deep learning approaches to polyp detection have shown potential enhancing rates. However, majority these systems are developed evaluated on static images from colonoscopies, whilst in clinical practice performed a real-time video feed. Non-curated data remains challenge, as it contains low-quality frames when compared still, selected often obtained...
Moving objects in image sequences acquired by a static camera can be detected analyzing the grey-level difference between successive frames. Direct motion detection, however, will also detect fast variations of scene illumination. This paper describes method for detection that is considerably less sensitive to time-varying It based on combining algorithm with an homomorphic filter which effectively suppresses variable To this end, sequence modelled as being generated illumination and...
This study sought to test the feasibility of a purpose-built, integrated software platform process, analyze, and overlay cardiac magnetic resonance (CMR) data in real time within combined catheter laboratory imaging scanner suite (X-MRI) guide left ventricular (LV) lead implantation.Suboptimal LV position is major determinant poor resynchronization therapy (CRT) response, optimal site highly patient specific. Pacing myocardial scar associated with poorer outcomes; conversely, targeting...
In cardiac interventions, such as resynchronization therapy (CRT), image guidance can be enhanced by involving preoperative models. Multimodality 3D/2D registration for guidance, however, remains a significant research challenge fundamentally different data, i.e., MR to X-ray. Registration methods must account differences in intensity, contrast levels, resolution, dimensionality, field of view. Furthermore, same anatomical structures may not visible both modalities. Current approaches have...
Initial reports indicate that transcranial harmonic imaging after ultrasound contrast agent bolus injection (BHI) can detect cerebral perfusion deficits in acute ischemic stroke. We evaluated parametric images of the washout kinetics.Twenty-three patients with internal carotid artery infarction were investigated SonoVue < or =40 hour onset symptoms. The findings compared those cranial computed tomography (CCT) and clinical course 4 months stroke.Images pixel-wise peak intensity (PPI) time to...
Object recognition, i.e. classification of objects into one several known object classes, generally is a difficult task. In this paper we address the problem detecting and classifying moving in image sequences from traffic scenes recorded with static camera. first step, statistical, illumination invariant motion detection algorithm used to produce binary masks scene-changes. Next, Fourier descriptors shapes refined are computed as feature vectors describing different scene. Finally,...
There is uncertainty regarding the efficacy of artificial intelligence (AI) software to detect advanced subtle neoplasia, particularly flat lesions and sessile serrated (SSLs), due low prevalence in testing datasets prospective trials. This has been highlighted as a top research priority for field.An AI algorithm was evaluated on four video test containing 173 polyps (35,114 polyp-positive frames 634,988 polyp-negative frames) specifically enriched with SSLs, including challenging dataset...
Optimal positioning of the left ventricular (LV) lead is an important determinant cardiac resynchronization therapy (CRT) response.
Convolutional neural networks (CNN) for computer-aided diagnosis of polyps are often trained using high-quality still images in a single chromoendoscopy imaging modality with sessile serrated lesions (SSLs) excluded. This study developed CNN from videos to classify as adenomatous or nonadenomatous standard narrow-band (NBI) and NBI-near focus (NBI-NF) created publicly accessible polyp video database.
We describe an algorithm for change detection which is insensitive to both slow and fast temporal variations of scene illumination. Our based on statistical decision theory by using a Bayesian approach. The goal detect only changes are induced true changes, like motion, but not due varying illumination or noise. To this end, our uses simple model invariant common camera nonlinearities gamma-nonlinearity. This combined with the influence noise as well priori expected properties sought masks....
Dynamic perviousness is a novel imaging biomarker, with clot density measurements at multiple timepoints to allow longer contrast thrombus interaction. We investigated the correlations between dynamic and composition in setting of acute ischemic stroke. Thirty-nine patients large vessel occlusion (LVO) undergoing mechanical thrombectomy (MT) were analyzed. Patients received three-phase CT pre-thrombectomy histopathological analysis retrieved clots. Clot densities for every phase change...
An algorithm that discriminates moving objects from their shadows is presented. Starting the change mask of an image sequence, first all changed area divided into subregions consisting pixels with similar colour properties. This done using mean shift algorithm, which very powerful in non-parametric clustering data. In a second step significance test performed to classify each pixel inside one classes foreground or shadow. To do this straightforward model used where grey level covered by...
To retrospectively assess the use of a combination cancellous bone reconstructions (CBR) and multiplanar (MPRs) for detection metastases at thoracoabdominal computed tomography (CT) compared with MPRs alone.The study was approved by local institutional review board. Included were 156 consecutive patients confirmed cancer who underwent whole-body positron emission (PET)/CT examination clinical purposes (93 male 63 female patients; mean age ± standard deviation, 59.8 years 14.9; range, 11-85...
Atrial flutter (AFL) represents a prevalent variant of supraventricular tachycardia, distinguished by macro-reentrant pathway encompassing the cavotricuspid isthmus (CTI). Radiofrequency (RF) catheter ablation stands as favored therapeutic modality for managing recurring CTI-dependent AFL. Intracardiac echocardiography (ICE) has been proposed method to reduce radiation exposure during CTI ablation. This study aims comprehensively compare procedural parameters between ICE-guided and...
Introduction Catheter ablation is the preferred treatment for typical atrial flutter (AFl), but it can be challenging due to anatomical abnormalities. The use of 3D electroanatomical mapping systems (EAMS) has reduced fluoroscopy exposure during AFl ablation. Intracardiac echocardiography (ICE) also shown benefits in reducing radiation However, there a lack evidence on feasibility ICE-guided, zero-fluoroscopy without EAMS. Methods In this prospective study, we enrolled 80 patients with...
Patients with drug-refractory heart failure can greatly benefit from cardiac resynchronization therapy (CRT). A CRT device resynchronize the contractions of left ventricle (LV) leading to reduced mortality. Unfortunately, 30%-50% patients do not respond treatment when assessed by objective criteria such as remodeling. significant contributing factor is suboptimal placement LV lead. It has been shown that placing this lead away scar and at point latest mechanical activation improve response...