A5057497769- Retinal Imaging and Analysis
- Optical Coherence Tomography Applications
- Medical Image Segmentation Techniques
- Retinal Diseases and Treatments
- AI in cancer detection
- Digital Imaging for Blood Diseases
- Radiomics and Machine Learning in Medical Imaging
- Retinal and Optic Conditions
- Glaucoma and retinal disorders
- Lung Cancer Diagnosis and Treatment
- Advanced MRI Techniques and Applications
- Machine Learning in Healthcare
- Diabetic Foot Ulcer Assessment and Management
- Cell Image Analysis Techniques
- Medical Imaging and Analysis
- Explainable Artificial Intelligence (XAI)
- Photoacoustic and Ultrasonic Imaging
- Body Contouring and Surgery
- Medical Imaging Techniques and Applications
- Textile materials and evaluations
- Neurological Disease Mechanisms and Treatments
- Ultrasound and Hyperthermia Applications
- Functional Brain Connectivity Studies
- Advanced Neural Network Applications
- Brain Tumor Detection and Classification
German Research Centre for Artificial Intelligence
2023-2024
University of Lübeck
2014-2024
Deutsches Forschungsnetz
2024
Medizinisches Laserzentrum Lübeck (Germany)
2017-2022
Jungheinrich (Germany)
2015-2016
Magnetic resonance imaging (MRI) has become key in the diagnosis and disease monitoring of patients with multiple sclerosis (MS). Both, T2 lesion load Gadolinium (Gd) enhancing T1 lesions represent important endpoints MS clinical trials by serving as a surrogate activity. T2- fluid-attenuated inversion recovery (FLAIR) quantification - largely due to methodological constraints – is still being performed manually or semi-automated fashion, although strong efforts have been made allow...
The growing popularity of black box machine learning methods for medical image analysis makes their interpretability to a crucial task. To make system, e.g. trained neural network, trustworthy clinician, it needs be able explain its decisions and predictions. In this work, we tackle the problem generating plausible explanations predictions classifiers, that are differentiate between different types pathologies healthy tissues. An intuitive solution determine which regions influence...
Optical coherence tomography (OCT) enables the non-invasive acquisition of high-resolution three-dimensional cross-sectional images at micrometer scale and is mainly used in field ophthalmology for diagnosis as well monitoring eye diseases. Also other areas, such dermatology, OCT already established. Due to its nature, also employed research studies involving animal models. Manual evaluation models a challenging task due lack imaging standards varying anatomy among In this paper, we present...
Self-Examination Low-Cost Full-Field Optical Coherence Tomography (SELFF-OCT) is a novel OCT technology that was specifically designed for home monitoring of neovascular age-related macular degeneration (AMD). First clinical findings have been reported before. This trial investigates an improved prototype patients with AMD and focusses on device operability diagnostic accuracy compared established spectral-domain (SD-OCT).Prospective single-arm study.Tertiary care centre (University Eye...
Optical coherence tomography (OCT) is an extensively used imaging tool for disease monitoring in both age-related macular degeneration (AMD) and retinal vein occlusion (RVO). However, there limited literature on minimum requirements of OCT settings reliable biomarker detection. This study systematically investigates the influence scan size interscan distance (ISD) activity We analyzed 80 volumes AMD patients 12 RVO presence subretinal fluid (SRF), intraretinal (IRF), pigment epithelium...
The assessment of lymph node metastases is critical for accurate cancer staging and consequently the decision treatment options. Lymph a challenging, time-consuming task due to fact that nodes have ill-defined borders as well varying sizes morphological characteristics. purpose this study evaluate effects using different anatomical priors with aim guiding network attention within application segmentation pathological in mediastinum. first presented prior, distance map, displays commonly...
MRI-based hippocampus volume, a core feasible biomarker of Alzheimer's disease (AD), is not yet widely used in clinical patient care, partly due to lack validation software tools for hippocampal volumetry that are compatible with routine workflow. Here, we evaluate fully-automated and computa tionally efficient FSL-FIRST prediction AD dementia (ADD) subjects amnestic mild cognitive impairment (aMCI) from phase 1 the Disease Neuroimaging Initiative. Receiver operating characteristic analysis...
Optical coherence tomography (OCT) is a non-invasive imaging modality that provides cross-sectional 3D images of biological tissue. Especially in ophthalmology OCT used for the diagnosis various eye diseases. Automatic retinal layer segmentation algorithms, which are increasingly based on deep learning techniques, can support diagnostics. However, topology properties, such as order layers, often not considered. In our work, we present an automatic approach shape regression using...
The registration of medical images often suffers from missing correspondences due to inter-patient variations, pathologies and their progression leading implausible deformations that cause misregistrations might eliminate valuable information. Detecting non-corresponding regions simultaneously with the process helps generating better has been investigated thoroughly classical iterative frameworks but rarely deep learning-based methods.We present joint non-correspondence segmentation image...
Optical coherence tomography (OCT) established as an essential part of the diagnosis, monitoring and treatment programs patients suffering from wet age-related macular degeneration (AMD). To further improve disease progression just-in-time therapy, home OCTs such innovative self-examination low-cost full-field OCT (SELFF-OCT) are developed, enabling by due to its technical simplicity cost efficiency, but coming at reduced image quality indicated a low signal-to-noise ratio (SNR). Although...
For a unified analysis of medical images from different modalities, data harmonization using image-to-image (I2I) translation is desired. We study this problem employing an optical coherence tomography (OCT) set Spectralis-OCT and Home-OCT images. I2I challenging because the are unpaired, bijective mapping does not exist due to information discrepancy between both domains. This has been addressed by Contrastive Learning for Unpaired Translation (CUT) approach, but it reduces semantic...
The diagnosis of cardiac function based on cine MRI requires the segmentation structures in images, but problem automatic is still open, due to imaging characteristics MR images and anatomical variability heart. In this paper, we present a variational framework for joint registration multiple To enable simultaneous objects, shape prior term introduced into region competition approach multi-object level set segmentation. proposed algorithm applied myocardium as well left right ventricular...
The main application of optical coherence tomography (OCT) is in the field ophthalmology, where it used for diagnosis various eye diseases. automatic segmentation individual retinal layers as well pathological structures OCT scans helpful clinical examination and treatment planning. Current methods often do not consider strict arrangement layers. Although graph-based are suitable correcting topology errors, their applicability costly complex, especially presence pathologies. In this work, a...
The treatment of age-related macular degeneration (AMD) requires continuous eye exams using optical coherence tomography (OCT). need for is determined by the presence or change disease-specific OCTbased biomarkers. Therefore, monitoring frequency has a significant influence on success AMD therapy. However, current schemes not individually adapted to patient and therefore often insufficient. While higher would have positive effect treatment, in practice it can only be achieved with home...
Manual detection of newly formed lesions in multiple sclerosis is an important but tedious and difficult task. Several approaches for automating the new have recently been proposed, they tend to either overestimate actual amount or miss many lesions. In this paper, image registration convolutional neural network (CNN) that adapts baseline follow-up by spatial deformations simulation proposed. Simultaneously, segmentations are generated, which shown reliably estimate real lesion load separate...
The evaluation of lymph node metastases plays a crucial role in achieving precise cancer staging, which turn influences subsequent decisions regarding treatment options. detection nodes poses challenges due to the presence unclear boundaries and diverse range sizes morphological characteristics, making it resource-intensive process. As part LNQ 2023 MICCAI challenge, we propose use anatomical priors as tool address that persist automatic mediastinal segmentation combination with partial...