KDKonstantin Drexler

Konstantin Drexler

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Konstantin Drexler has a total of 64 co-authors. Here are the top co-authors by number of shared publications:

  • Carola Berking

    Department of Dermatology, Deutsches Zentrum Immuntherapie (DZI), CCC Erlangen-EMN, Bavarian Cancer Research Center (BZKF), Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91054 Erlangen, Germany

    4 shared publications
  • Markus Valentin Heppt

    Department of Dermatology, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91054 Erlangen, Germany

    4 shared publications
  • Anja Wessely

    Department of Dermatology, Deutsches Zentrum Immuntherapie (DZI), CCC Erlangen-EMN, Bavarian Cancer Research Center (BZKF), Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91054 Erlangen, Germany

    3 shared publications
  • Anne Petzold

    Department of Dermatology, Deutsches Zentrum Immuntherapie (DZI), CCC Erlangen-EMN, Bavarian Cancer Research Center (BZKF), Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, 91054, Germany

    2 shared publications
  • Dennis Niebel

    Department of Dermatology, University Hospital Regensburg, Regensburg, 93053, Germany

    2 shared publications
  • Elias A. T. Koch

    Department of Dermatology, Deutsches Zentrum Immuntherapie (DZI), CCC Erlangen-EMN, Bavarian Cancer Research Center (BZKF), Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91054 Erlangen, Germany

    2 shared publications

Latest Publications

  • Open Access

    Vision transformer-based diagnosis of psoriasis and eczema in whole-slide histology

    by Luis Carlos Rivera Monroy, Anne Petzold, Melissa Sari, Katharina Breininger, Andreas Maier, Julio Vera-Gonzalez, Michael Erdmann, Stefan Schliep, Konstantin Drexler, Dennis Niebel, et al.

    Psoriasis and eczema are chronic inflammatory skin diseases with overlapping histopathological features, which often lead to diagnostic uncertainty even among experienced dermatopathologists. To address this challenge, we developed a computer-assisted diagnostic framework that combines the Virchow foundation model, pretrained on 1.5 million whole-slide images, with multi-instance learning (MIL) to classify psoriasis and eczema from digitized histopathology slides. Using an internal dataset ( n = 40) and an external validation cohort ( n = 40), equally balanced between both conditions and annotated by board-certified dermatopathologists, our best-performing configuration (Virchow + CLAM) achieved 85% accuracy, a macro-averaged F1 score of 0.80, and an AUC of 0.81 on the external cohort. This substantially outperformed baseline convolutional neural networks, which reached 61% accuracy, and models relying solely on pretrained feature extractors without MIL, which achieved an average accuracy of 68.8%. In a reader study on the same external cohort, individual dermatopathologist accuracies ranged from 47.5 to 70.0%, with a majority-vote consensus accuracy of 62.5%; our method outperformed both the average individual reader and the consensus under histology-only conditions. Furthermore, the model generates attention heatmaps that provide supportive visual context by highlighting regions associated with model predictions. Importantly, this study is designed as a methodological proof-of-concept conducted under controlled, histology-only conditions and is not intended for direct clinical deployment. Rather than demonstrating clinical readiness, it illustrates the potential of domain-specific foundation models combined with MIL for addressing diagnostically challenging inflammatory dermatoses.

  • Open Access

    An artificial intelligence model of whole-slide pathology specimens differentiating cutaneous high-grade squamous proliferations

    by Anne Petzold, Anja Wessely, Michael Erdmann, Stefan Schliep, Stephan Schreml, Luis Carlos Rivera Monroy, Julio Vera, Konstantin Drexler, Dennis Niebel, Kinan Maurice Hayani, et al.

    Cutaneous squamous cell carcinoma (cSCC) and verruca vulgaris (VV) are skin conditions involving the proliferation of epidermal keratinocytes requiring fundamentally different treatments. Histological evaluation of highly differentiated squamous cell proliferations can be challenging, particularly in small or superficial samples. This study aims to improve diagnostic accuracy using an AI model to distinguish cSCC from VV. We developed a deep-learning model using clustering-constrained attention multiple instance learning (CLAM) to classify hematoxylin and eosin-stained whole-slide images (WSIs) as cSCC or VV. The dataset comprised 289 WSIs (n = 148 cSCC, n = 141 VV). Quality control was ensured through expert review: the training cohort was evaluated by four dermatopathologists, and the evaluation cohort by six additional experts. On the training set, the model achieved an AUROC of 0.99, with an accuracy of 94.9% for cSCC and 91.2% for VV. On the evaluation set, it reached an AUROC of 0.96, and accuracies of 82.4% (cSCC) and 97.4% (VV), similar to the average performance of individual dermatopathologists. We successfully trained and implemented an interpretable deep-learning-based weakly supervised model on WSIs distinguishing cSCC from VV, which could enhance AI-supported diagnostics in the future.


  • Open Access

    Nectin-1 Expression Correlates with the Susceptibility of Malignant Melanoma to Oncolytic Herpes Simplex Virus In Vitro and In Vivo

    by Barbara Schwertner, Georg Lindner, Camila Toledo Stauner, Elisa Klapproth, Clara Magnus, Anette Rohrhofer, Stefanie Gross, Beatrice Schuler-Thurner, Veronika Öttl, Nicole Feichtgruber, et al.

    Talimogene laherparepvec (T-VEC), an oncolytic herpes simplex virus, is approved for intralesional injection of unresectable stage IIIB/IVM1a melanoma. However, it is still unclear which parameter(s) predict treatment response or failure. Our study aimed at characterizing surface receptors Nectin-1 and the herpes virus entry mediator (HVEM) in addition to intracellular molecules cyclic GMP-AMP synthase (cGAS) and stimulator of interferon genes (STING) as potential bio-markers for oncolytic virus treatment. In 20 melanoma cell lines, oncolytic activity of T-VEC was correlated with the expression of Nectin-1 but not HVEM, as evaluated via flow cytometry and immunohistochemistry. Knockout using CRISPR/Cas9 technology confirmed the superior role of Nectin-1 over HVEM for entry and oncolytic activity of T-VEC. Neither cGAS nor STING as evaluated by Western Blot and immunohistochemistry correlated with T-VEC induced oncolysis. The role of these biomarkers was retrospectively analyzed for the response of 35 cutaneous melanoma metastases of 21 patients to intralesional T-VEC injection, with 21 (60.0%) of these lesions responding with complete (n = 16) or partial regression (n = 5). Nectin-1 expression in pretreatment biopsies significantly predicted treatment outcome, while the expression of HVEM, cGAS, and STING was not prognostic. Altogether, Nectin-1 served as biomarker for T-VEC-induced melanoma regression in vitro and in vivo.


  • Open Access

    The Quality of Practice Guidelines for Melanoma: A Methodologic Appraisal with the AGREE II and AGREE-REX Instruments

    by Theresa Steeb, Anja Wessely, Konstantin Drexler, Martin Salzmann, Frédéric Toussaint, Lucie Heinzerling, Markus Reinholz, Carola Berking, Markus V. Heppt

    Multiple guidelines on cutaneous melanoma (CM) are available from several consortia and countries. To provide up-to-date guidance in the rapidly changing field of melanoma treatment, guideline developers have to provide regular updates without compromises of quality. We performed a systematic search in guideline databases, Medline and Embase to identify guidelines on CM. The methodological quality of the identified guidelines was independently assessed by five reviewers using the instruments “Appraisal of Guidelines for Research and Evaluation” (AGREE II) and “Recommendation EXcellence” (AGREE-REX). We performed descriptive analysis, explored subgroup differences using the Kruskal–Wallis (H) test and examined the relationship between distinct domains and items of the instruments with Spearman’s correlation. Six guidelines by consortia from Australia, France, Germany, Scotland, Spain and the United States of America were included. The German guideline fulfilled 71%–98% of criteria in AGREE II and 78%–96% for AGREE-REX, obtaining the highest scores. Deficiencies in the domains of “applicability” and “values and preferences” were observed in all guidelines. The German and Spanish guidelines significantly differed from each other in most of the domains. The domains “applicability” and “values and preferences” were identified as methodological weaknesses requiring careful revision and improvement in the future.


  • Open Access

    Treatment Motivations and Expectations in Patients with Actinic Keratosis: A German-Wide Multicenter, Cross-Sectional Trial

    by Theresa Steeb, Anja Wessely, Dagmar von Bubnoff, Thomas Dirschka, Konstantin Drexler, Conrad Falkenberg, Jessica C. Hassel, Kinan Hayani, Svea Hüning, Katharina C. Kähler, et al.

    Patient-centered motives and expectations of the treatment of actinic keratoses (AK) have received little attention until now. Hence, we aimed to profile and cluster treatment motivations and expectations among patients with AK in a nationwide multicenter, cross-sectional study including patients from 14 German skin cancer centers. Patients were asked to complete a self-administered questionnaire. Treatment motives and expectations towards AK management were measured on a visual analogue scale from 1–10. Specific patient profiles were investigated with subgroup and correlation analysis. Overall, 403 patients were included. The highest motivation values were obtained for the items “avoid transition to invasive squamous cell carcinoma” (mean ± standard deviation; 8.98 ± 1.46), “AK are considered precancerous lesions” (8.72 ± 1.34) and “treating physician recommends treatment” (8.10 ± 2.37; p < 0.0001). The highest expectation values were observed for the items “effective lesion clearance” (8.36 ± 1.99), “safety” (8.20 ± 2.03) and “treatment-related costs are covered by health insurance” (8.00 ± 2.41; p < 0.0001). Patients aged ≥77 years and those with ≥7 lesions were identified at high risk of not undergoing any treatment due to intrinsic and extrinsic motivation deficits. Heat mapping of correlation analysis revealed four clusters with distinct motivation and expectation profiles. This study provides a patient-based heuristic tool for a personalized treatment decision in patients with AK.