Publications
2026
- Establishing a functional osteochondral–synovial ex vivo joint model: Systematic evaluation of glucose and oxygen impactAuthors: Fatemeh Safari, Jovana Zvicer, Sibylle Grad, Martin J. Stoddart, Zhen Li
This study investigates how glucose and oxygen levels affect tissue viability and metabolic activity in osteochondral–synovial co-culture models. The findings show that high-glucose medium under physioxic conditions best preserves tissue viability and stabilizes molecular responses, providing guidance for improving the reliability and reproducibility of ex vivo joint models.
- Optical monitoring of inflammatory response in joint explant cultures using near infrared spectroscopyAuthors: Nithin Sadeesh,Fatemeh Safari Abolfazl Jalali, Jovana Zvicer, Arjen Gebraad, Ervin Nippolainen, Susanna Miettinen, Sibylle Grad, Zhen Li, Isaac O. Afara
This study explores near-infrared spectroscopy combined with machine learning to detect and estimate osteoarthritis-related inflammatory biomarkers in tissue culture models. The approach distinguished OA-like from non-inflammatory conditions with 95.3% accuracy, demonstrating its potential for rapid, non-destructive monitoring of inflammatory activity.
- Crosslinking strategies govern the morphology and biological performance of decellularized extracellular matrix particle–tyramine-modified hyaluronic acid hydrogelsAuthors: Jiangyao Xu, Jacek K. Wychowaniec, Matteo D'Este, Nan Jiang, Songsong Zhu, Sibylle Grad, Jeroen Geurts, Zhen Li
The study shows that incorporating decellularized extracellular matrix (dECM) particles into hyaluronic acid-based hydrogels can improve their mechanical and biological properties for cartilage regeneration. Among the tested approaches, HRP/Eo crosslinking enabled more homogeneous dECM integration, better matrix retention and stronger cartilage-related cellular responses.
- Objective stratification of knee osteoarthritis stages using a semi-supervised learning approach on multimodal MRI-CT cartilage featuresAuthors: Federica Kiyomi Ciliberti, Ida Maruotto, Halldor Jonsson Jr, Paolo Gargiulo
This study presents a semi-supervised learning approach that combines MRI and CT imaging to objectively classify different stages of knee osteoarthritis, even with limited labeled data. The results demonstrate reliable disease stratification and identify imaging biomarkers that could support earlier diagnosis and more accurate assessment of cartilage degeneration.
- Impact of automated and manual segmentation errors on knee osteoarthritis classification using MRI-registered data on CT scansAuthors: Sydney Fox, Federica Kiyomi Ciliberti, Halldór Jónsson Jr., Paolo Gargiulo, Marco Recenti
Machine learning (ML) approaches using quantitative imaging biomarkers show promise for automated OA classification, but their reliability under imperfect image segmentation remains unclear. This study evaluated the robustness of cartilage-based radiodensity and morphological features derived from MRI-registered CT scans against simulated segmentation errors.
- Mechanistic insights into cartilage-sensory nerve crosstalk in osteoarthritis progressionAuthors: Huan Meng, Junxuan Ma, Line Kawtharany, Rui Yue, Chunyi Wen, Sibylle Grad, Olivier Chassande, Zhen Li
This review highlights cartilage–sensory nerve crosstalk as a key mechanism underlying osteoarthritis pain, moving beyond a structure-centric view of disease progression. Mechanistic insights into neuroinflammatory and mechanosensitive pathways support the development of biomarkers for pain phenotyping and patient stratification.
2025
- Feature Selection in Healthcare Datasets: Towards a Generalizable SolutionAuthors: Ida Maruotto, Federica Kiyomi Ciliberti, Paolo Gargiulo, Marco Recenti
The increasing dimensionality of healthcare datasets presents major challenges for clinical data analysis and interpretation. This study introduces a scalable ensemble feature selection (FS) strategy optimized for multi-biometric healthcare datasets aiming to: address the need for dimensionality reduction, identify the most significant features, improve machine learning models’ performance, and enhance interpretability in a clinical context.
2024
- Innovative Diagnostic Approaches for Predicting Knee Cartilage Degeneration in Osteoarthritis Patients: A Radiomics-Based StudyAuthors: Francesca Angelone, Federica Kiyomi Ciliberti, Giovanni Paolo Tobia, Halldór Jónsson Jr, Alfonso Maria Ponsiglione, Magnus Kjartan Gislason, Francesco Tortorella, Francesco Amato & Paolo Gargiulo
Osteoarthritis (OA) is a common joint disease affecting people worldwide, notably impacting quality of life due to joint pain and functional limitations. This study explores the potential of radiomics — quantitative image analysis combined with machine learning — to enhance knee OA diagnosis.