Explanipedia

Automated CT-based sarcopenia assessment for risk stratification of patients undergoing colorectal cancer resection Open

J Vogelsang, Fabian Hörst, René Hosch, Christopher Martin Sauer, David Albers , et al. · 2025

Despite the prognostic relevance of sarcopenia in colorectal cancer, it has not yet been incorporated into routine clinical patient assessment. This study investigates the potential of automatically CT-derived muscle-to-bone ratio (MBR) fo…

Contrastive virtual staining enhances deep learning‐based <span>PDAC</span> subtyping from H&E‐stained tissue cores Open

Maximilian Fischer, Alexander Muckenhuber, Robin Peretzke, Luay Farah, Constantin Ulrich , et al. · 2025

Pancreatic ductal adenocarcinoma (PDAC) subtyping typically relies on immunohistochemistry (IHC) staining for critical markers like HNF1A and KRT81, a labor‐intensive manual staining process that introduces variability. Virtual staining me…

Advancing Continuous Glucose Monitoring (CGM) for Inpatient Clinical Decision Support: Individual Algorithmic Mean Absolute Relative Difference (MARD) Open

Jill von Conta, Fin Hendrik Bahnsen, Lutz Heinemann, Lukas van Baal, Jens Kleesiek , et al. · 2025

Objective: Continuous glucose monitoring (CGM) is widely used to monitor glucose levels in patients with diabetes and guide insulin dosing in outpatients. In inpatient care, special regulatory requirements necessitate CGM accuracy as a pre…

Advancing Continuous Glucose Monitoring (CGM) for Inpatient Clinical Decision Support: Individual Algorithmic Mean Absolute Relative Difference (MARD) Open

Jill von Conta, Fin Hendrik Bahnsen, Lutz Heinemann, Lukas van Baal, Jens Kleesiek , et al. · 2025

Objective: Continuous glucose monitoring (CGM) is widely used to monitor glucose levels in patients with diabetes and guide insulin dosing in outpatients. In inpatient care, special regulatory requirements necessitate CGM accuracy as a pre…

278P Genetic subtype prediction in diffuse gliomas with a vision transformer-based model Open

Pranav Swaroop Gundla, Mahdi Nezamabadi, Stefan Alig, Stanley A. Klein, Jens Kleesiek , et al. · 2025

OncoVR - Virtual Reality in Oncology for Patient-centered Care: A Systematic Review and Meta-Analysis Open

Miriam Balzer, Abdelrahman Elsaqqa, Gijs Luijten, Katrin Schormann, Saša Jović , et al. · 2025

1 Abstract Due to the significant research effort in the field of virtual reality (VR) and the increasing interest of the gaming industry, the technical possibilities have developed rapidly. In recent years, VR applications have become mor…

Leveraging Sarcopenia index by automated CT body composition analysis for pan cancer prognostic stratification Open

Katarzyna Borys, Johannes Haubold, Julius Keyl, Maria Antonietta Bali, Riccardo De Angelis , et al. · 2025

This study evaluates the CT-based volumetric sarcopenia index (SI) as a baseline prognostic factor for overall survival (OS) in 10,340 solid tumor patients (40% female). Automated body composition analysis was applied to internal baseline …

Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking Open

Ting Han, Linara Adilova, Henning Petzka, Jens Kleesiek, Michael Kamp · 2025

Neural collapse, i.e., the emergence of highly symmetric, class-wise clustered representations, is frequently observed in deep networks and is often assumed to reflect or enable generalization. In parallel, flatness of the loss landscape h…

FHIR-Former: enhancing clinical predictions through Fast Healthcare Interoperability Resources and large language models Open

Merlin Engelke, Giulia Baldini, Jens Kleesiek, Felix Nensa, Amin Dada · 2025

Objective To address the challenges of data heterogeneity and manual feature engineering in clinical predictive modeling, we introduce FHIR-Former, an open-source framework integrating Fast Healthcare Interoperability Resources (FHIR) with…

LiMeTrack: A lightweight biosample management platform for the multicenter SATURN3 consortium Open

Florian Heyl, Jonas Gassenschmidt, Lukas Heine, Frederik Voigt, Jens Kleesiek , et al. · 2025

Biomedical research projects involving large patient cohorts are increasingly complex, both in terms of data modalities and number of samples. Such projects require robust data management solutions to foster data integrity, reproducibility…

Large Language Models Improve Cancer Survival Prediction Using Real-World Clinical Notes Open

Niklas Kiermeyer, Tim Lenfers, Amin Dada, Julian Friedrich, Sameh Khattab , et al. · 2025

In medical documentation, vast amounts of unstructured text are generated that are still underutilized in current prognostic models. We investigate the potential of self-hosted large language models (LLM) to extract clinically meaningful, …

Automated ICD-O-3 Coding of Real-World Pathology Reports Using Self-Hosted Large Language Models Open

Kamyar Arzideh, René Hosch, Amin T. Turki, Bahadir Erilymaz, Mikel Bahn , et al. · 2025

While large language models (LLMs) have shown promise in medical text processing, their real-world application in self-hosted clinical settings remains underexplored. Here, we evaluated five state-of-the-art self-hosted LLMs for automated …

Nursing-centered development of an AI-based decision support system in pressure ulcer and incontinence-associated dermatitis management - a mixed methods study Open

Khalid Majjouti, Vanessa Priester, Michaela Tapp-Herrenbrueck, Alexander Brehmer, Hannah Pinnekamp , et al. · 2025

Enhancing Privacy: The Utility of Stand-Alone Synthetic CT and MRI for Tumor and Bone Segmentation Open

André Ferreira, Kunpeng Xie, Caroline Wilpert, Gustavo Correia, Felix Barajas Ordonez , et al. · 2025

AI requires extensive datasets, while medical data is subject to high data protection. Anonymization is essential, but poses a challenge for some regions, such as the head, as identifying structures overlap with regions of clinical interes…

De-identification of medical imaging data: a comprehensive tool for ensuring patient privacy Open

Moritz Rempe, Lukas Heine, Constantin Seibold, Fabian Hörst, Jens Kleesiek · 2025

Low-branching vessel architecture shapes immune cell niches and predicts immune responses in renal cancer Open

Marieta Toma, Yangping Li, Melina Kehl, Tim Kempchen, Laura Esser , et al. · 2025

Clear cell renal cell carcinoma (ccRCC) is characterized by marked histological heterogeneity, encompassing its vasculature. Here, we introduce PropSegNet, a learning-based algorithm that segments and classifies three distinct vascular pat…

Beyond the Desktop: XR-Driven Segmentation with Meta Quest 3 and MX Ink Open

Lisle Faray de Paiva, Gijs Luijten, A. S. Santos, Moon Kim, Behrus Puladi , et al. · 2025

Medical imaging segmentation is essential in clinical settings for diagnosing diseases, planning surgeries, and other procedures. However, manual annotation is a cumbersome and effortful task. To mitigate these aspects, this study implemen…

From Screen to Space: Evaluating Siemens' Cinematic Reality Open

Gijs Luijten, Sebastian Krueger, Alexander Brost, Laura Mazilescu, A. S. Santos , et al. · 2025

As one of the first research teams with full access to Siemens' Cinematic Reality, we evaluate its usability and clinical potential for cinematic volume rendering on the Apple Vision Pro. We visualized venous-phase liver computed tomograph…

Good Enough: Is it Worth Improving your Label Quality? Open

Alexander Jaus, Zdravko Marinov, Constantin Seibold, Simon Reiß, Jens Kleesiek , et al. · 2025

Improving label quality in medical image segmentation is costly, but its benefits remain unclear. We systematically evaluate its impact using multiple pseudo-labeled versions of CT datasets, generated by models like nnU-Net, TotalSegmentat…

Performing the HINTS-exam using a mixed-reality head-mounted display in patients with acute vestibular syndrome: a feasibility study Open

Nadia Sadok, Gijs Luijten, Fin Hendrik Bahnsen, Christina Gsaxner, Lorenz Peters , et al. · 2025

Background In patients with acute vestibular syndrome (AVS) differentiating between benign acute peripheral vestibular disorders and possible life-threatening central, causes such as stroke, can be challenging due to similar symptoms. AVS …

Fine-Grained Classification of Pressure Ulcers and Incontinence-Associated Dermatitis Using Multimodal Deep Learning: Algorithm Development and Validation Study Open

Alexander Brehmer, Constantin Seibold, Jan Egger, Khalid Majjouti, Michaela Tapp‐Herrenbrück , et al. · 2025

Background Pressure ulcers (PUs) and incontinence-associated dermatitis (IAD) are prevalent conditions in clinical settings, posing significant challenges due to their similar presentations but differing treatment needs. Accurate different…

Accuracy and Reliability of Intermittent Scanning and Real-Time Continuous Glucose Monitoring Systems in Diabetes Emergencies Open

Lukas van Baal, Lutz Heinemann, Johanna Reinold, Jill von Conta, Fin Hendrik Bahnsen , et al. · 2025

Background: Diabetes care is a major challenge of patients treated in hospitals. A continuous glucose monitoring system (CGM) provides a more comprehensive assessment of glucose control than capillary blood glucose measurements. Especially…

Controlled Pilot Intervention Study on the Effects of an AI‐Based Application to Support Incontinence‐Associated Dermatitis and Pressure Injury Assessment, Nursing Care and Documentation: Study Protocol Open

Hannah Pinnekamp, Vanessa Rentschler, Khalid Majjouti, Alexander Brehmer, Michaela Tapp‐Herrenbrück , et al. · 2025

Artificial Intelligence (AI)‐based applications have significant potential to differentiate between pressure injuries (PI) and incontinence‐associated dermatitis (IAD), common challenges in nursing practice. Within the KIADEKU overall proj…

Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks Open

Alexander Jaus, Constantin Seibold, Simon Reiß, Zdravko Marinov, Keyi Li , et al. · 2025

We present Connected-Component (CC)-Metrics, a novel semantic segmentation evaluation protocol, targeted to align existing semantic segmentation metrics to a multi-instance detection scenario in which each connected component matters. We m…

Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning Open

Amr Abourayya, Jens Kleesiek, K. Praveen Kumar Rao, Erman Ayday, B. Tarakeswara Rao , et al. · 2025

In many critical applications, sensitive data is inherently distributed and cannot be centralized due to privacy concerns. A wide range of federated learning approaches have been proposed to train models locally at each client without shar…

Towards Conditioning Clinical Text Generation for User Control Open

Osman Alperen Koraş, Rabi Bahnan, Jens Kleesiek, Amin Dada · 2025

Deploying natural language generation systems in clinical settings remains challenging despite advances in Large Language Models (LLMs), which continue to exhibit hallucinations and factual inconsistencies, necessitating human oversight. T…

MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters Open

Amin Dada, Osman Alperen Koraş, Marie Bauer, Amanda Saravia-Butler, Kaleb E. Smith , et al. · 2025

While increasing patients' access to medical documents improves medical care, this benefit is limited by varying health literacy levels and complex medical terminology. Large language models (LLMs) offer solutions by simplifying medical in…

Virtual reality support during systemic cancer therapy to improve anxiety/depressive symptoms and reduce toxicity in patients with gastrointestinal cancers—OncoVR Open

Stefan Kasper, Stefan Liszio, K. Schorrmann, Magda Gerigk, Saša Jović , et al. · 2025

Background: Systemic cancer therapy may trigger anxiety/depressive symptoms and toxicity. Relaxation techniques can help alleviate toxicities but their implementation in clinical practice is challenging. We hypothesize that virtual reality…

Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence Open

Julius Keyl, Philipp Keyl, Grégoire Montavon, René Hosch, Alexander Brehmer , et al. · 2025

Despite advances in precision oncology, clinical decision-making still relies on limited variables and expert knowledge. To address this limitation, we combined multimodal real-world data and explainable artificial intelligence (xAI) to in…

Unlocking the potential of digital pathology: Novel baselines for compression Open

Maximilian Fischer, Peter Neher, Peter J. Schüffler, Sebastian Ziegler, Shuhan Xiao , et al. · 2025

Digital pathology offers a groundbreaking opportunity to transform clinical practice in histopathological image analysis, yet faces a significant hurdle: the substantial file sizes of pathological whole slide images (WSIs). Whereas current…

Jens Kleesiek YOU? Author Swipe