A5089575197- Retinal Imaging and Analysis
- Retinal Diseases and Treatments
- Retinal and Optic Conditions
- Glaucoma and retinal disorders
- Optical Coherence Tomography Applications
- Cerebrovascular and Carotid Artery Diseases
- Digital Imaging for Blood Diseases
- Medical Image Segmentation Techniques
- Intracranial Aneurysms: Treatment and Complications
- AI in cancer detection
- Acute Ischemic Stroke Management
- Traumatic Brain Injury and Neurovascular Disturbances
- Coronary Interventions and Diagnostics
- Retinal Development and Disorders
- Advanced MRI Techniques and Applications
- Photoacoustic and Ultrasonic Imaging
- Retinal and Macular Surgery
- Cardiac Imaging and Diagnostics
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Advanced Vision and Imaging
- Renal and Vascular Pathologies
- Artificial Intelligence in Healthcare and Education
- Cell Image Analysis Techniques
- Visual Attention and Saliency Detection
Medical University of Vienna
2016-2025
Austrian Research Institute for Artificial Intelligence
2024-2025
Christian Doppler Laboratory for Thermoelectricity
2016-2024
Christian Doppler Research Association
2023-2024
University of Southampton
2023
Klinikum rechts der Isar
2023
Institute of Molecular and Clinical Ophthalmology Basel
2023
University of Basel
2023
Institute for Medical Informatics and Biostatistics
2023
Imperial College London
2023
Development and validation of a fully automated method to detect quantify macular fluid in conventional OCT images.Development diagnostic modality.The clinical dataset for detection consisted 1200 volumes patients with neovascular age-related degeneration (AMD, n = 400), diabetic edema (DME, or retinal vein occlusion (RVO, 400) acquired Zeiss Cirrus (Carl Meditec, Dublin, CA) (n 600) Heidelberg Spectralis (Heidelberg Engineering, Heidelberg, Germany) devices.A based on deep learning...
International challenges have become the standard for validation of biomedical image analysis methods. Given their scientific impact, it is surprising that a critical common practices related to organization has not yet been performed. In this paper, we present comprehensive conducted up now. We demonstrate importance and show lack quality control consequences. First, reproducibility interpretation results often hampered as only fraction relevant information typically provided. Second, rank...
Retinal swelling due to the accumulation of fluid is associated with most vision-threatening retinal diseases. Optical coherence tomography (OCT) current standard care in assessing presence and quantity image-guided treatment management. Deep learning methods have made their impact across medical imaging, many OCT analysis been proposed. However, it currently not clear how successful they are interpreting on OCT, which lack standardized benchmarks. To address this, we organized a challenge...
While millions of individuals show early age-related macular degeneration (AMD) signs, yet have excellent vision, the risk progression to advanced AMD with legal blindness is highly variable. We suggest means artificial intelligence individually predict progression.In eyes intermediate AMD, neovascular type choroidal neovascularization (CNV) or dry geographic atrophy (GA) was diagnosed based on standardized monthly optical coherence tomography (OCT) images by independent graders. obtained...
The morphologic changes and their pathognomonic distribution in progressing age-related macular degeneration (AMD) are not well understood.
Diagnosis and treatment guidance are aided by detecting relevant biomarkers in medical images. Although supervised deep learning can perform accurate segmentation of pathological areas, it is limited requiring a priori definitions these regions, large-scale annotations, representative patient cohort the training set. In contrast, anomaly detection not to specific pathologies allows for on healthy samples without annotation. Anomalous regions then serve as candidates biomarker discovery....
To investigate the therapeutic effect of intravitreal pegcetacoplan on inhibition photoreceptor (PR) loss and thinning in geographic atrophy (GA) conventional spectral-domain OCT (SD-OCT) imaging by deep learning-based automated PR quantification.Post hoc analysis a prospective, multicenter, randomized, sham (SM)-controlled, masked phase II trial investigating safety efficacy for treatment GA because age-related macular degeneration.Study eyes 246 patients, randomized 1:1:1 to monthly (AM),...
To evaluate the potential of machine learning to predict best-corrected visual acuity (BCVA) outcomes from structural and functional assessments during initiation phase in patients receiving standardized ranibizumab therapy for neovascular age-related macular degeneration (AMD).Post hoc analysis a randomized, prospective clinical trial.Data 614 evaluable intravitreal monthly or pro re nata according protocol-specified criteria HARBOR trial.Monthly spectral-domain (SD) OCT volume scans were...
Purpose: The purpose of this study was to predict low and high anti-VEGF injection requirements during a pro re nata (PRN) treatment, based on sets optical coherence tomography (OCT) images acquired the initiation phase in neovascular AMD. Methods: Two-year clinical trial data subjects receiving PRN ranibizumab according protocol specified criteria HARBOR after three initial monthly injections were included. OCT analyzed at baseline, month 1, 2. Quantitative spatio-temporal features computed...
PurposeAnti–vascular endothelial growth factor (VEGF) treatment of neovascular age-related macular degeneration (AMD) is a highly effective advance in the retinal armentarium. OCT offering 3-dimensional imaging retina widely used to guide treatment. Although poor outcomes reported from clinical practice are multifactorial, availability reliable, reproducible, and quantitative evaluation tools accurately measure fluid response, that is, "VEGF meter," may be better means monitoring treating...
Purpose: To develop a data-driven interpretable predictive model of incoming drusen regression as sign disease activity and identify optical coherence tomography (OCT) biomarkers associated with its risk in intermediate age-related macular degeneration (AMD). Methods: Patients AMD were observed every 3 months, using Spectralis OCT imaging, for minimum duration 12 months up to period 60 months. Segmentation the overlying layers was obtained graph-theoretic method, hyperreflective foci...
The identification and quantification of markers in medical images is critical for diagnosis, prognosis, disease management. Supervised machine learning enables the detection exploitation findings that are known a priori after annotation training examples by experts. However, supervision does not scale well, due to amount necessary examples, limitation marker vocabulary entities. In this proof-of-concept study, we propose unsupervised anomalies as candidates retinal optical coherence...
Modern optical coherence tomography (OCT) devices used in ophthalmology acquire steadily increasing amounts of imaging data. Thus, reliable automated quantitative analysis OCT images is considered to be utmost importance. Current retinal layer segmentation methods work reliably on healthy or mildly diseased retinas, but struggle with the complex interaction layers fluid accumulations macular edema. In this work, we present a fully 3D method which able segment all and fluid-filled regions...
To quantitatively measure hyperreflective foci (HRF) during the progression of geographic atrophy (GA) secondary to age-related macular degeneration (AMD) using deep learning (DL) and investigate association with local global growth GA.Eyes GA were prospectively included. Spectral-domain optical coherence tomography (SDOCT) fundus autofluorescence images acquired every 6 months. A 500-μm-wide junctional zone adjacent border was delineated HRF quantified a validated DL algorithm....
To identify disease activity and effects of intravitreal pegcetacoplan treatment on the topographic progression geographic atrophy (GA) secondary to age-related macular degeneration quantified in spectral-domain OCT (SD-OCT) by automated deep learning assessment.Retrospective analysis a phase II clinical trial study evaluating GA patients (FILLY, NCT02503332).SD-OCT scans 57 eyes with monthly treatment, 46 every-other-month (EOM) 53 sham injection from baseline 12-month follow-ups were...
Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in world. Early detection AMD great importance, as vision loss caused by this disease irreversible and permanent. Color fundus photography most cost-effective imaging modality to screen for retinal disorders. Cutting edge deep learning based algorithms have been recently developed automatically detecting from images. However, there are still lack a comprehensive annotated dataset standard...
The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) a cost-effective manner, making screening more accessible. While AI models for from CFPs have shown promising results laboratory settings, their performance decreases significantly real-world scenarios due the presence out-of-distribution and low-quality images. To address this issue, we propose Intelligence Robust Glaucoma...
ObjectiveTo identify the individual progression of geographic atrophy (GA) lesions from baseline optical coherence tomography (OCT) images in patients clinical routine.DesignClinical evaluation a deep-learning based algorithmSubjects184 eyes 100 consecutively enrolled patientsMethodsOCT and fundus autofluorescence (FAF) (both Spectralis, Heidelberg Engineering, Heidelberg, Germany) with GA secondary to age-related macular degeneration routine care were used for model validation. FAF...
Automated, anatomically coherent retinal layer segmentation in optical coherence tomography (OCT) is one of the most important components disease management. However, current methods rely on large amounts labeled data, which can be difficult and expensive to obtain. In addition, these systems tend often propose impossible results, undermines their clinical reliability. This study introduces a semi-supervised approach that leverages unlabeled data anatomical prior knowledge related structure...