610 Medizin und Gesundheit
Refine
Document Type
- Article (15)
- Conference Paper (14)
- Article in a Periodical of the TH Wildau (2)
- Part of a Book (1)
- Doctoral Thesis (1)
Year of publication
Institute
Has Fulltext
- yes (33)
Keywords
- bone density (5)
- computed tomography (3)
- multispiral computer tomography (3)
- uncertainty (3)
- biomaterial (2)
- bioprinting (2)
- deep learning (2)
- deep learning segmentation (2)
- maxillary sinus (2)
- paranasal sinus (2)
Die Auswertung komplexer anatomischer Strukturen auf Basis dreidimensionaler Bilddaten stellt eine zentrale Aufgabe der medizinisch-technischen Bildverarbeitung dar. Insbesondere Strukturen mit hoher interindividueller Variabilität erfordern robuste Segmentierungs- und Modellierungsverfahren, um reproduzierbare morphologische Analysen zu ermöglichen. Der Sinus sphenoidalis nimmt hierbei eine besondere Stellung ein, da er aufgrund seiner tiefen Lage an der Schädelbasis weitgehend vor äußeren Einflüssen geschützt ist und zugleich ausgeprägte individuelle Unterschiede aufweist.
In dieser Arbeit wird ein durchgängiger volumetrischer Workflow zur Segmentierung, dreidimensionalen Rekonstruktion und geometrischen Analyse des Sinus sphenoidalis auf Basis kranialer CT-Daten vorgestellt. Der methodische Schwerpunkt liegt auf standardisierter Vorverarbeitung, semi-automatischer Segmentierung sowie Deep-Learning-basierter Volumensegmentierung unter Einsatz des nnU-Net-Frameworks.
Die Ergebnisse zeigen, dass durch eine Kombination aus intensitätsbasierter Normalisierung, geometrischer Vereinheitlichung und datenadaptiver Segmentierung konsistente und vergleichbare 3D-Modelle erzeugt werden können. Auch bei deutlich heterogenen Akquisitionsparametern ließ sich eine stabile Segmentierungsleistung erzielen. Der vorgestellte Ansatz bietet damit eine belastbare Grundlage für weiterführende automatisierte morphologische Vergleichsverfahren.
This research paper addresses the critical cybersecurity issues of healthcare IT systems. Through the use of artificial intelligence, specifically natural language processing (NLP) and advanced neural networks such as long short-term memory (LSTM), the study closely analyzes vulnerabilities documented in the National Vulnerability Database (NVD). The main objective is to identify patterns in the Common Vulnerabilities and Exposures (CVE) datasets to predict Common Vulnerability Scoring System (CVSS) scores with high accuracy, which is of utmost importance in the healthcare sector where IT failures can have catastrophic consequences.
The work aims not only to predict the potential impact on healthcare but also to prioritize the vulnerabilities according to their severity and their relevance to healthcare facilities. The vulnerability descriptions, vectors, and affected software configurations will be evaluated in detail. Through this analytical effort, the study will develop a differentiated framework for the early detection and professional management of IT security threats, aiming to strengthen the cybersecurity defenses of healthcare infrastructures. By contributing to the strategic anticipation and mitigation of risks, the research seeks to improve the resilience of critical healthcare systems and ensure the continuity and integrity of patient care.
Background: Human identification in forensic contexts becomes challenging when fingerprints, dental records, or DNA are unavailable. The sphenoid sinus, owing to its protected anatomical location and high inter-individual variability, offers potential as a biometric marker.
Methods: We first replicated a YOLOv8-nano segmentation experiment using annotated CT scans in DICOM data format. Images were preprocessed with soft-tissue windowing and converted into high-quality PNGs for training. Model performance was evaluated with standard segmentation metrics. Based on observed limitations, we decided for 3D modelling approaches involving manual, semi-automatic, and normalization-based segmentation pipelines.
Results: The YOLOv8 model achieved high validation performance (mAP50 = 0.921; true positive rate = 91%; true negative rate = 100%), which is promising for the future implementation. However, its reliability for consistent sphenoid sinus segmentation was limited by anatomical complexity and heterogeneous datasets. In contrast, 3D modelling methods produced more robust and accurate reconstructions of the sphenoid sinus.
Conclusion: While deep learning-based 2D segmentation provides a strong baseline for sinus analysis, 3D modelling approaches currently offer greater reliability for forensic applications. Combining both strategies may pave the way toward fully automated, scalable identification frameworks based on sphenoid sinus morphology.
Decentralized Tele-Rehabilitation via Edge AI-Oracle Architecture for Spatiotemporal Pain Assessment
(2026)
Remote tele-rehabilitation requires objective pain assessment, but existing approaches fail in two distinct ways. Self-report scales such as the Visual Analog Scale and the Numeric Pain Rating Scale are easy to falsify, opening a special case of the Oracle problem in blockchain-based insurance. Cloud-based computer vision handles falsification but transmits raw biometric video off the patient’s device, violating privacy requirements. A decentralized Edge AI-Oracle architecture is proposed that combines MediaPipe Face Mesh landmark extraction with a recurrent classifier mapping Action-Unit feature sequences to a learned pain score aligned with the Prkachin and Solomon Pain Intensity scale. The recurrent cell is selected empirically across short-context (T = 2) and long-context (T = 120 frames at 24 fps) regimes, with a two-layer Long Short-Term Memory (LSTM) network adopted for deployment. Inference and Elliptic Curve Digital Signature Algorithm (ECDSA) signing run inside an ARM TrustZone Trusted Execution Environment (TEE). Biometric logs are stored off-chain on the InterPlanetary File System (IPFS). Smart contracts anchor results on-chain and open a 24 h optimistic verification window for an off-chain Watchtower auditor. On SynPAIN the LSTM reaches F1 = 0.683 on T = 120 video (leave-one-stratum-out), with a directional but non-significant advantage over Gated Recurrent Unit (GRU) (Wilcoxon p = 0.167). Cross-dataset validation on BioVid Heat Pain Database Part A (87 subjects, 174 paired observations, leave-one-subject-out) yields F1 = 0.519 for LSTM and 0.499 for GRU (Wilcoxon p = 0.549). A processor-only TEE surrogate benchmark estimates 1.96 ms (FP32) and 0.45 ms (INT8) inference latency at T = 120 with a 0.34 MB footprint and 707 μs ECDSA signing latency, leaving the INT8 inference latency more than an order of magnitude below the 33 ms per-frame budget. The dual-layer storage reduces gas costs by a factor of 23.4 (160,261 vs. 3,744,872 gas), corresponding to an illustrative mainnet cost of approximately 0.53 USD per submission at 1 gwei, rising to roughly 16 USD at a busier 30 gwei, and falling to approximately 0.005 USD on Arbitrum One (April 2026 reference parameters), so that continuous monitoring is economically practical on Layer-2. An adaptive-adversary analysis of the Watchtower shows that gross score tampering is detected at every usable operating threshold, whereas a rational adversary who inflates by less than the dispute threshold, or who shapes the injected score to fall just inside it, evades detection. Because the false-positive rate reaches zero only for δ≳0.15, the protocol bounds rather than eliminates patient-side fraud and motivates a zero-knowledge proof-of-inference successor. The framework is architecturally and economically feasible as a cryptographically verifiable, privacy-preserving tele-rehabilitation substrate aligned with General Data Protection Regulation (GDPR) and Health Insurance Portability and Accountability Act (HIPAA) requirements through the Zero-Video Transmission principle, while remaining economically viable under post-Dencun mainnet and Layer-2 conditions. Recognition accuracy on real-world data and robustness to small-magnitude tampering remain limitations that the interchangeable recognition and audit components must improve before clinical deployment.
Background
Leishmaniasis is a vector-borne parasitic disease caused by Leishmania protozoa. The disease manifests in several clinical presentations including cutaneous, mucocutaneous, and visceral leishmaniasis. The diagnosis of leishmaniasis is complex and often requires a combination of clinical assessment, microscopy, serological tests, and molecular techniques especially in immunocompromised cases. However, traditional diagnostic methods have limitations in terms of accuracy, sensitivity, and the expertise required, leading to an urgent need for advanced, automated diagnostic tools. The aim of this research is to develop a deep learning-based decision-support system for the microscopic examination of tissue samples to support non-experts with the live diagnosis of the disease.
Methods
Tissue samples from lesions were collected from patients diagnosed with cutaneous leishmaniasis in Libya and Palestine for the purpose of preparing microscopic slides. The samples were then visualized using a high-performance laboratory microscope and a mobile, low-cost device. The captured images were subsequently used to train the object detection framework YOLOv8 with the aim of identifying Leishmania parasites. A graphical user interface was developed for the application of the deep learning model, which enables real-time detection of the parasites using a microscope camera, as well as recognition from previously generated images and videos.
Results
The deep learning YOLOv8 framework was successfully trained using data generated by the advanced microscope and employed for the detection of Leishmania parasites. Subsequent finetuning with a combined set containing the aforementioned data and microscopic images generated with the low-cost device resulted in a considerable improvement in accuracy. The efficacy of the model was demonstrated through its successful operation on previously unseen data. Object detection yielded a mean average precision of 0.78 for the combined datasets. The evaluation process for determining the presence of parasites in an image resulted in 91% accuracy, 91% sensitivity, 90% specificity and 94% precision on the test data.
Conclusions
Deep learning-based YOLOv8 achieved accurate Leishmania detection in tissue samples, enhancing decision-support for non-experts via real-time graphical user interface support. This innovation can simplify diagnostics by addressing traditional method limitations, enabling early, accessible leishmaniasis detection in resource-limited settings, and potentially inspiring similar applications in other parasitic diseases.
Reliable identification of deceased individuals may be difficult when conventional biometric methods such as facial recognition, fingerprint analysis, or DNA profiling cannot be applied. In such cases, medical imaging records acquired during a person’s lifetime may serve as an alternative source of identifying information. Certain anatomical structures visible in computed tomography (CT), including the sphenoid sinus, exhibit considerable inter-individual variability while remaining relatively stable within the same individual. This study investigates the feasibility of using sphenoid sinus morphology as an anatomical biometric for automated identification from head CT scans. Identification is formulated as a ranking problem in which a query CT examination is compared with a reference database using geometric descriptors derived from segmentation masks, reducing dependence on CT intensity values. The dataset consisted of CT scans from 816 individuals acquired in two patient positioning modes: Head First Supine (HFS) and Head First Prone (HFP). Several deep learning architectures, including YOLOv8 variants, YOLO11L-seg, UNet++, DeepLabV3+, HRNet, and SegFormer-B2, were evaluated for sphenoid sinus segmentation. Based on F1-score performance and cross-mode stability, YOLO11L-seg was selected and further trained to construct a database of binary masks representing individual sphenoid sinus anatomy. Identification was performed using pairwise mask comparison based on the Intersection over Union (IoU) metric. To reduce the influence of segmentation artifacts and slice-level variability, the final similarity score for each candidate was computed as the average of the four highest IoU values across slice comparisons. Individuals were ranked according to similarity, and identification was considered successful if the correct subject appeared among the top five candidates and exceeded a predefined similarity threshold. The proposed approach achieved Top-5 identification accuracies of 97.27% for HFP and 87.67% for HFS acquisitions. These results demonstrate the feasibility of using sphenoid sinus geometry as a stable anatomical biometric for automated identification. The key contribution of this study is the introduction of a ranking-based identification framework that utilizes anatomical biometrics derived from CT data for reliable patient matching.
Die vorliegende Arbeit präsentiert ein redundantes System, das Vitalparameter als Schnittstelle zwischen physischen Entitäten und virtuellen Repräsentationen in Unity verbindet. Die Echtzeiterfassung physiologischer Parameter wie der Herzfrequenz (EKG), der Hautleitwert (EDA) oder der Muskelaktivität (EMG) ermöglicht die Übertragung der jeweiligen physiologischen Zustände in virtuelle Modelle. Diese neuartige Form der Interaktion zwischen Mensch und Maschine eröffnet ein breites Spektrum an Anwendungsmöglichkeiten. Der präsentierte Ansatz mittels EMG gewährleistet durch redundante Signalverarbeitung eine robuste Kommunikation zwischen physischer und virtueller Ebene und erweitert die Möglichkeiten von Digitalen Zwillingen, um eine physiologisch fundierte Dimension als Beschreibungselement für sozio-kognitive Entitäten.
In vorhergehenden Arbeiten wurden sowohl ein Bildverarbeitungsmodell zur automatisierten Erkennung von Messarealen als auch Studien zur Akzeptanz robotergestützter in vivo-Messungen entwickelt und erprobt. Auf dieser Grundlage wurde ein prototypischer Hautmessroboter aufgebaut, der Anforderungen an Ergonomie, Sicherheit und Bedienbarkeit integriert. Im vorliegenden Beitrag wird eine erste Validierungsstudie vorgestellt, in der robotergestützte Messungen systematisch mit manuellen Referenzmessungen verglichen werden. Die Ergebnisse zeigen eine insgesamt hohe Korrelation zwischen manueller und robotergestützter Messung für beide untersuchten Hautparameter. Nach Produktanwendung zeigen die Ergebnisse, dass mit der robotergestützten Messung statistisch signifikante Produkteffekte erfasst werden können. Die Resultate deuten darauf hin, dass robotergestützte in vivo Messungen ein hohes Potenzial für den Einsatz im dermatologischen Studienbetrieb haben können.
This study presents the development of a realistic brain phantom as a humane, practical alternative to animal use in medical training, in line with the 3R principles and Directive 2010/63/EU. The phantom is designed to support ultrasound-based education for diagnostic and interventional procedures while improving patient safety through controlled, repeatable practice. High‑resolution CT data were converted to CAD models and additively manufactured as moulds; a gelatin‑based soft‑tissue matrix with glycerin and potassium sorbate provides elasticity and durability. Functional features include fluid‑fillable ventricular structures enabling drainage and puncture simulations, and an integrated high‑density tumour insert to model advanced scenarios.
Ultrasound evaluation demonstrated clear echogenic differentiation between tumour, ventricles, and surrounding tissue, confirming the model’s imaging fidelity and suitability for hands‑on training. The phantom proved cost‑efficient and reusable, facilitating standardised teaching of complex procedures without ethical approval barriers. A limitation is the material’s gradual mechanical instability under repeated probe contact, motivating investigations into synthetic or hybrid matrices to enhance longevity and reuse.
Overall, the brain phantom constitutes an ethical, technically robust, and resource‑efficient training tool that addresses critical needs in healthcare quality and safety by reducing avoidable errors through simulation‑based competence development.
The development of novel photonic integrated microchips (PIC) is a promising approach to allow for the convenient detection of key biomarkers in complex matrices through multichannel real-time analysis in a highly compact package. This study reports the successful development and application of a backside released CMOS chip designed for the multichannel real-time detection of biomarkers. Operating at the C-band at approx. 1550 nm, the microchip features three dedicated detection sensors in addition to a reference sensor, enabling simultaneous analysis of multiple biomarkers. The compact and highly miniaturized design of this microchip, with a footprint of just 1 mm², positions it as promising candidate for point-of-care diagnostics and personalized medicine applications. This technology opens a path to transform biomarker detection across various medical fields, offering rapid, reliable, and cost-effective diagnostic solutions. In conclusion, the presented multichannel photonic microchips signify a substantial leap forward in real-time biomarker detection, providing a highly capable platform for future research and clinical applications.
