243 results
Filters
Settings
Now showing1 - 10 of 243
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Robust motion tracking and classification of zebrafish with deep learning(IEEE, 2026-09-01); ; ; ; Zebrafish serve as a key pre-clinical model for disease research. Studying disease progression requires long-term tracking of fish motion, particularly when considering the function of the musculoskeletal apparatus. While vision-based tracking has been studied, current approaches typically require substantial fine tuning and often lack robustness, especially when multiple fish need to be tracked and motion occurs along all three spatial dimensions. We propose a simplified setup and a 3D tracking method using only two cameras and two convolutional neural networks (CNN) to localize and track multiple fish robustly. We separate the localization of fish and their classification as an individual. This allows for simple training data acquisition by placing fish into the basin individually, without the need for manual annotation. We evaluate the approach on sets of two, five, and ten fish resulting in multiple object tracking accuracies (MOTA) of 0.997, 0.994, and 0.966, respectively. The mean MOTA over all scenarios is 0.99 compared to a mean MOTA of 0.89 for a state-of-the-art tracking algorithm (idtracker.ai). Finally, we present comprehensive data on the motion activity of individual fish in a 30-minute video sequence, demonstrating robust tracking and unique activity profiles of each fish.Publicationtype: Journal Article30 11 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , CMR-based aortic stiffness parameters in a symptomatic high risk obstructive sleep apnea cohort: results from the population-based Hamburg City Health Study(BioMed Central, 2026-08-13); ; ; ; Background: Aortic stiffness (AS) parameters as pulse wave velocity (PWV), aortic distensibility of the ascending and descending aorta (AD AoAsc, AD AoDesc) and pulse pressure (PP) are marker for vascular ageing, whereas data concerning obstructive sleep apnea (OSA) in population-based cohorts are sparse. Thus, we aimed to identify possible associations of AS with OSA in the Hamburg City Health Study (HCHS) cardiovascular magnetic resonance (CMR) cohort. Methods: HCHS is a population-based cohort-study quantifying PWV and AD by 2D-phase-contrast-CMR-measuring-methods and PP by blood pressure. OSA was defined as self-reported OSA by HCHS-study-interviews and/or a combination of snoring, respiratory arrest and Epworth-Sleepiness-Scale (ESS)> 10. Logistic regression analyses with adjustments were performed. Results: In the cohort of 1,498 participants (median age 66 years, 39.0% female), 143 (9.5%) participants were identified as symptomatic high risk OSA cohort with significantly higher rates of males (p < 0.001), hypertension (p < 0.001), and coronary artery disease (p = 0.037). Median PWV and AD (p = 0.741, p = 0.145, p = 0.191) were not significantly different, but median PP was significantly higher in this OSA cohort ( p = 0.003). In male OSA participants, median AD AoAsc and AD AoDesc were significantly lower and median PP significantly higher (p = 0.006, p = 0.015, p < 0.001). After adjustment for age, sex, cardiovascular risk factors (CVRF), diseases (CVD) and antihypertensive medication, OSA remained significantly associated with PP (p = 0.045), but not with PWV, AD AoAsc and AD AoDesc (p = 0.633, p = 0.503, p = 0.171). Conclusions: Higher PP was associated with OSA after adjustment for age, sex, CVRF, CVD and medication. Therefore, PP might be used to identify individuals at risk for OSA. Trial registration: The study has been registered at ClinicalTrial.gov (NCT03934957), retrospectively registered at 01/04/2019.Publicationtype: Journal Article38 19 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , An AI based mobile robot for autonomous ultrasound in legal medicineComprehensive documentation of internal tissue structures plays an important role in legal medicine. Although ultrasound is widely used in medical diagnostics as a powerful modality for injury detection and documentation, its integration into legal medicine workflows remains limited. Potential reasons include physical strain and infection risks due to manual probe placement at different locations along the body. Robotic ultrasound systems have been proposed to address such challenges. However, current systems are typically restricted to specific target regions and are limited in mobility and autonomy, complicating their clinical integration and fully autonomous, task-level operation. We therefore propose a mobile robotic system for autonomous ultrasound scanning across the body. The system localizes the body, estimates internal target structures, moves to reach the target structure, and performs ultrasound scans. We evaluate the system in three stages. First, we assess the accuracy and robustness of target localization and scan path planning across different body types. Second, we conduct experiments with a body phantom to evaluate the repeatability of covering target structures. Third, we demonstrate the system in a real legal medicine setting. Our experiments demonstrate that the system can approach the body, define the scan path, and acquire reproducible ultrasound images of target structures. These results demonstrate the feasibility of fully autonomous ultrasound imaging across multiple anatomical regions using a mobile robotic system. Beyond legal medicine, the proposed mobile system offers perspectives for autonomous imaging in broader clinical settings such as telemedicine and infectious disease settings, supporting remote diagnostics while reducing infection risks.Publicationtype: Journal Article11 8 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , KiMeKo: a collaborative AI platform for medical device developmentKiMeKo (KI-Med-Kollaborationsplattform) is a publically funded collaborative research project that develops a sustainable AI-Med ecosystem for AI-based medical device development. The project runs from July 2024 to December 2027 and joins seven Northern German research institutions. KiMeKo addresses the complete development trajectory, from concept and data acquisition to validation, regulatory evidence generation, and approval-oriented documentation. The project contributes a practical toolchain and platform capabilities for non-experts and experts, including structured innovation support, uncertaintyaware sensor-data fusion, hybrid expert-system modeling, and workflow-guided data acquisition and anonymization. This paper summarizes project objectives, expected outputs, relevance to IEEE COMPSAC 2026 themes, and current progress. In particular, KiMeKo aligns with Applied AI and Smart & Connected Health by combining AI engineering, privacy-conscious data processing, and regulation-aware medical software development.Publicationtype: Conference Paper26 12 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , A review of deep learning-based unsupervised anomaly detection in brain MRI(Elsevier, 2026-07-01); ; ; ; The manual assessment of brain Magnetic Resonance Imaging (MRI) scans can be labor-intensive and time-consuming for radiologists. Deep Learning methods have demonstrated the potential to aid this process. However, their effectiveness relies on the availability of large, annotated data sets. Unsupervised Anomaly Detection (UAD) presents a promising alternative, offering the potential to identify and localize anomalies without per-pixel annotations. Instead, a normative distribution is learned using healthy data, enabling the identification of abnormalities as deviations. This allows UAD methods to detect abnormalities that were unseen during training. This appealing feature has led to numerous studies proposing innovations and novel approaches. In this work, we provide a review of the literature and systematically collect and compare the proposed approaches. We observe that UAD has made significant advancements in brain MRI analysis. However, individual approaches are often evaluated in different contexts, i.e., changes in acquisition parameters, pre- and post-processing, and anomaly scoring. This variability makes it challenging to assess which models perform best, underscoring the need for comprehensive comparative studies concerning the specific context of MRI scans. Our collection, featuring public data sets, research studies, and open implementations, is available at our GitHub repository https://github.com/FinnBehrendt/Unsupervised-Anomaly-Detection-in-Brain-MRI .Publicationtype: Review Article14 26 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Pre-operative three-dimensional face scans for predicting difficult facemask ventilation: a prospective development study(Wiley-Blackwell, 2026-06-05); ; 17 14 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , 6D robotic OCT scanning of curved tissue surfacesOptical coherence tomography (OCT) is a non-invasive volumetric imaging modality with high spatial and temporal resolution. Imaging larger tissue regions requires moving the OCT probe to cover the target area. Handheld scanning approaches rely on overlapping volumes for stitching, whereas, robotic scanning approaches often restrict motion to pure translations to avoid full hand-eye calibration - a challenging problem given the OCT probe's small field of view. These registration- or translation-based stitching strategies, however, struggle when imaging curved tissue surfaces. We propose a fiducial marker enabling full six-degree-of-freedom hand-eye calibration for a robot-mounted OCT probe. Our method produces highly repeatable transform estimates and, in experiments on two phantom surfaces, enables consistent robotic scanning of large, curved geometries. Because the approach does not depend on image-based registration, it avoids error accumulation along scanning paths and outperforms conventional purely translational robotic scanning.Publicationtype: Conference Paper9 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Dual-domain artifact disentanglement for metal artifact reduction in CT images(SPIE, 2026-04-03); ; ; 18 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Automated estimation of anatomical risk metrics for endoscopic sinus surgery using deep learningEndoscopic sinus surgery requires careful preoperative assessment of the skull base anatomy to minimize risks such as cerebrospinal fluid leakage. Anatomical risk scores like the Keros, Gera and Thailand-Malaysia-Singapore score offer a standardized approach but require time-consuming manual measurements on coronal CT or CBCT scans. We propose an automated deep learning pipeline that estimates these risk scores by localizing key anatomical landmarks via heatmap regression. We compare a direct approach to a specialized global-to-local learning strategy and find mean absolute errors on the relevant anatomical measurements as low as 0.506 mm for the Keros, 4.516° for the Gera and 0.802 mm/0.777 mm for the TMS classification, each corresponding to the best-performing model for the respective measurement.Publicationtype: Conference Paper13 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Distilling expert surgical knowledge: how to train local surgical VLMs for anatomy explanation in complete mesocolic excision(IEEE, 2026-04); 15