Cosima Hufnagel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Cosima Hufnagel has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Frank Friedrich Gellrich
Department of Dermatology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universitaet Dresden, Dresden, Germany
3 shared publications - Sarah Hobelsberger
Department of Dermatology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universitaet Dresden, Dresden, Germany
3 shared publications - Stefan Beissert
Universitätsklinikum Carl Gustav Carus, Technische Universität Dresden Dresden Germany
3 shared publications - Alexander Max Funk
National Center for Tumor Diseases (NCT/UCC), 01307 Dresden, Germany
2 shared publications - Alpaslan Tasdogan
Department of Dermatology, University Hospital Essen & German Cancer Consortium, Partner Site (DKTK) and Research Alliance Ruhr, Research Center One Health, University Duisburg-Essen, Essen, Germany
2 shared publications Christina Feige
Department of Dermatology, Faculty of Medicine, University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
2 shared publications
Latest Publications
- Open Access
Integrating Histopathology Foundation Models and PRAME Immunohistochemistry in Melanoma Diagnosis
Background: The histopathological diagnosis of challenging melanocytic lesions remains limited by substantial interobserver variability. Although computational pathology foundation models demonstrated promising diagnostic performance, their predictions are often difficult to interpret in terms of established criteria. Objective: We evaluated a diagnostic framework combining foundation-model-based whole-slide image analysis, automated prediction of morphological features, and manually assessed PRAME immunohistochemistry. Methods: Using the Virchow2 foundation model and STAMP framework, we analyzed a retrospective cohort of 1,000 melanocytic lesions undergoing PRAME immunohistochemistry. Models were trained on 800 cases and evaluated on a temporally held-out test cohort of 200 cases. Results: The slide-level malignancy classifier achieved a test AUROC of 0.970 (AUPRC 0.984). Separate models predicted established histopathological criteria with high discrimination, including ulceration (AUROC 0.991) and dermal mitoses (AUROC 0.966). In contrast, predicting PRAME expression from H&E images alone showed lower performance (AUROC 0.776-0.780 for PRAME scores 4 and 0). An integrated model combining the slide-level malignancy score, AI-predicted morphological features, and manual PRAME status achieved an AUROC of 0.972 (AUPRC 0.975), comparable to the standalone classifier. In multivariable analysis, PRAME score 4 versus 0 was strongly associated with malignancy (adjusted OR 35.04, 95% CI 17.39-74.62). Conclusions: These findings demonstrate the feasibility of combining foundation-model-based histopathological analysis with established morphological criteria and PRAME immunohistochemistry. Although the integrated framework did not substantially improve overall discrimination, it provides a structured approach for incorporating complementary histopathological and immunohistochemical information into AI-assisted assessment of melanocytic lesions.
Open AccessIntegrating Histopathology Foundation Models and PRAME Immunohistochemistry in Melanoma Diagnosis
Background: The histopathological diagnosis of challenging melanocytic lesions remains limited by substantial interobserver variability. Although computational pathology foundation models demonstrated promising diagnostic performance, their predictions are often difficult to interpret in terms of established criteria. Objective: We evaluated a diagnostic framework combining foundation-model-based whole-slide image analysis, automated prediction of morphological features, and manually assessed PRAME immunohistochemistry. Methods: Using the Virchow2 foundation model and STAMP framework, we analyzed a retrospective cohort of 1,000 melanocytic lesions undergoing PRAME immunohistochemistry. Models were trained on 800 cases and evaluated on a temporally held-out test cohort of 200 cases. Results: The slide-level malignancy classifier achieved a test AUROC of 0.970 (AUPRC 0.984). Separate models predicted established histopathological criteria with high discrimination, including ulceration (AUROC 0.991) and dermal mitoses (AUROC 0.966). In contrast, predicting PRAME expression from H&E images alone showed lower performance (AUROC 0.776-0.780 for PRAME scores 4 and 0). An integrated model combining the slide-level malignancy score, AI-predicted morphological features, and manual PRAME status achieved an AUROC of 0.972 (AUPRC 0.975), comparable to the standalone classifier. In multivariable analysis, PRAME score 4 versus 0 was strongly associated with malignancy (adjusted OR 35.04, 95% CI 17.39-74.62). Conclusions: These findings demonstrate the feasibility of combining foundation-model-based histopathological analysis with established morphological criteria and PRAME immunohistochemistry. Although the integrated framework did not substantially improve overall discrimination, it provides a structured approach for incorporating complementary histopathological and immunohistochemical information into AI-assisted assessment of melanocytic lesions.
- Open Access
- 8 July 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 21194
Correction: 1H-NMR serum metabolomic profiling from clinical routine identifies signatures of progressive melanoma metastasis
- 8 July 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 21194
Open AccessCorrection: 1H-NMR serum metabolomic profiling from clinical routine identifies signatures of progressive melanoma metastasis
- Open Access
- 30 January 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
¹H-NMR serum metabolomic profiling from clinical routine identifies signatures of progressive melanoma metastasis
Early detection of active melanoma metastasis is crucial. Serum metabolomics may offer non-invasive biomarkers, but real-world applicability needs validation. This study aimed to identify ¹H-NMR-based serum metabolic signatures for active metastasis in a large clinical cohort. Serum from 963 melanoma patients (1698 samples) underwent ¹H-NMR spectroscopy. Patients were classified by active metastasis status. OPLS-DA and RFE followed by logistic regression models were developed on a patient-level training/test split. Subgroup analyses assessed signatures related to Immune Checkpoint Inhibitor (ICI) therapy, brain metastases, and BRAF status. Models for active metastasis showed moderate test set discrimination (Area Under the Curve [AUCs]: OPLS-DA 0.609, RFE 0.630). The RFE-model highlighted seven significant metabolites: increased pyruvate, phenylalanine, acetoacetate, glutamate, glucose, and decreased histidine and citrate were associated with active metastasis. OPLS-DA yielded concordant metabolites. Subgroup analyses revealed distinct metabolic associations, e.g., for ICI therapy (citrate, RFE AUC 0.721) and BRAF status (acetate, RFE AUC 0.655), but limited performance for brain metastases (RFE AUC 0.553). ¹H-NMR serum metabolomics detects systemic metabolic alterations of active melanoma metastasis with moderate accuracy in a real-world setting. Identified disruptions in energy and amino acid metabolism offer pathobiological insights and warrant investigation for multimodal biomarker panels.
- 30 January 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open Access¹H-NMR serum metabolomic profiling from clinical routine identifies signatures of progressive melanoma metastasis
Early detection of active melanoma metastasis is crucial. Serum metabolomics may offer non-invasive biomarkers, but real-world applicability needs validation. This study aimed to identify ¹H-NMR-based serum metabolic signatures for active metastasis in a large clinical cohort. Serum from 963 melanoma patients (1698 samples) underwent ¹H-NMR spectroscopy. Patients were classified by active metastasis status. OPLS-DA and RFE followed by logistic regression models were developed on a patient-level training/test split. Subgroup analyses assessed signatures related to Immune Checkpoint Inhibitor (ICI) therapy, brain metastases, and BRAF status. Models for active metastasis showed moderate test set discrimination (Area Under the Curve [AUCs]: OPLS-DA 0.609, RFE 0.630). The RFE-model highlighted seven significant metabolites: increased pyruvate, phenylalanine, acetoacetate, glutamate, glucose, and decreased histidine and citrate were associated with active metastasis. OPLS-DA yielded concordant metabolites. Subgroup analyses revealed distinct metabolic associations, e.g., for ICI therapy (citrate, RFE AUC 0.721) and BRAF status (acetate, RFE AUC 0.655), but limited performance for brain metastases (RFE AUC 0.553). ¹H-NMR serum metabolomics detects systemic metabolic alterations of active melanoma metastasis with moderate accuracy in a real-world setting. Identified disruptions in energy and amino acid metabolism offer pathobiological insights and warrant investigation for multimodal biomarker panels.