DNA Methylation Profiling in Melanoma: From Lesion Classification to Therapeutic Stratification
Authors: Jana T. Winterstein, Lukas Heinlein, Günter Raddatz, Carina Nogueira Garcia, Sarah Haggenmüller, Christoph Wies, Lucas Schneider, Annemarie Hoffsommer, +29 more
Organizations: Division of Digital Prevention, Diagnostics and Therapy Guidance, German Cancer Research Center (DKFZ), INF 223, 69120 Heidelberg, Germany · Medical Faculty, University Heidelberg, Heidelberg, Germany · Department of Epigenetics, German Cancer Research Center (DKFZ), Heidelberg, Germany · Department of Dermatology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Germany, Skin Cancer Center at the University Cancer Center and National Center for Tumor Diseases Dresden, Dresden, Germany · Department of Dermatology and Allergy, University Hospital, LMU Munich, Munich, Germany · Department of Dermatology, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg; Comprehensive Cancer Center Erlangen – European Metropolitan Region Nürnberg, CCC Alliance WERA, Erlangen; Bavarian Cancer Research Center (BZKF), Erlangen, Germany · Department of Dermatology, Venereology and Allergology, Charité – Universitätsmedizin Berlin, Corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany · Vivantes Hospital Spandau, Department of Dermatology and Allergology, Berlin, Germany · Department of Dermatology, University Hospital Regensburg, Regensburg, Germany · Department of Dermatology, Venereology and Allergology, University Hospital Essen, Essen, Germany · Department of Dermatology, Uniklinikum Erlangen, Friedrich-Alexander University Erlangen-Nürnberg, Erlangen, Germany. · Deutsches Zentrum Immuntherapie (DZI), Uniklinikum Erlangen, Erlangen, Germany. · Department of Dermatology, Venereology and Allergology, University Hospital Würzburg, National Center for Tumor Diseases (NCT) WERA Würzburg and Bavarian Cancer Research Center (BZKF), Würzburg, Germany · Goethe-University Frankfurt, University Hospital, Department of Dermatology, Germany. · Division of Translational Medical Oncology, German Cancer Research Center (DKFZ), Heidelberg, Germany · National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and Heidelberg University Hospital, Heidelberg, Germany · German Cancer Consortium (DKTK), Core Center Heidelberg, Heidelberg, Germany · Division of Translational Precision Medicine, Institute of Human Genetics, Heidelberg University, Heidelberg, Germany · Department of Neuropathology, Heidelberg University Hospital, Heidelberg, Germany; CCU Neuropathology, DKTK, DKFZ · Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany · Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany · Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany · Pathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, United Kingdom · Institute of Pathology, University Hospital Cologne, Medical Faculty, University of Cologne, Cologne, Germany · Department of Dermatology, Venereology and Allergology, University Medical Center Mannheim, Ruprecht-Karl University of Heidelberg, Mannheim, Germany · Department of Medicine, Division of Hematology/Oncology, Herbert Irving Comprehensive Cancer Center, Columbia University Irving Medical Center, New York, NY, USA · Department of Dermatology, Massachusetts General Hospital, Boston, Massachusetts; Harvard Medical School, Boston, Massachusetts; Harvard Data Science Initiative, Harvard University, Boston, Massachusetts.
DNA methylation provides a stable record of cellular identity, capturing epigenetic programs that distinguish specialized cell states despite a shared genome. Because malignant transformation and tumour progression are accompanied by extensive epigenetic remodeling, we hypothesized that the methylome of melanocytic lesions contains biologically and clinically relevant information for both diagnosis and disease progression. In a cohort of 1,001 tissue samples prospectively collected across eight German university hospitals profiled using Illumina Infinium MethylationEPIC arrays, we compared machine-learning models based on selected Cytosine phosphate Guanine (CpG) methylation sites with models incorporating biology-guided features, including epigenetic age acceleration, cell type composition and copy-number variation burden. In an external test set, the best diagnostic classifier was CpG-based and distinguished melanocytic nevi, noninvasive melanoma and invasive melanoma with a macro-averaged area under the receiver operating characteristic curve of 0.919 (95% CI: 0.878 to 0.952). Notably, across CpGs most strongly hyper- and hypomethylated between NV and IM, NIM showed an intermediate methylation profile, providing a molecular correlate of its diagnostic complexity. The best model for clinically relevant treatment group prediction, with AJCC stages grouped according to guideline-based management recommendations, relied on biology-guided features and achieved a macro-averaged mean absolute error of 0.627 (95% CI: 0.477 to 0.808). Together, these findings demonstrate that methylation-based models can capture both diagnostic identity and clinically relevant disease stratification, supporting DNA methylation as a promising biomarker for further validation and potential clinical translation.
We present a modular and multi-level framework for the differential diagnosis of malignant melanoma. Our framework integrates contextual information and evidence at the lesion, patient, and population levels, enabling decision-making at each level. We introduce an anatomic-site aware masked transformer, which effectively models the patient context by considering all lesions in a patient, which can be variable in count, and their site of incidence. Additionally, we incorporate patient metadata via learnable demographics embeddings to capture population statistics. Through extensive experiments, we explore the influence of specific information on the decision-making process and examine the tradeoff in metrics when considering different types of information. Validation results using the SIIM-ISIC 2020 dataset indicate including the lesion context with location and metadata improves specificity by 17.15% and 7.14%, respectively, while enhancing balanced accuracy. The code is available at https://github.com/narenakash/meldd.
Naren Akash, Anirudh Kaushik, Jayanthi Sivaswamy
Center for Visual Information Technology International Institute of Information Technology Hyderabad, India
NA methylation profiling has become a powerful approach for central nervous system (CNS) tumor classification, yet important challenges remain regarding cross-cohort transferability, methodological correctness, and robust multiclass evaluation. In this work, we propose a novel and methodologically rigorous machine-learning approach for methylation-based CNS tumor classification that combines Sparse Random Projection for dimensionality reduction with multinomial logistic regression for classification. We evaluate the proposed approach in the same general experimental setting established by a widely used reference classifier. On the 2,801-sample reference cohort, our method achieves a mean accuracy of 96% under stratified 3-fold cross-validation. On the independent 1,104-sample clinical evaluation cohort, it reaches 86% accuracy at the 91-class level and 93% when predictions are evaluated at the methylation class family level. These results improve upon the corresponding state-of-the-art reference figures of 82% class-level concordance and 88% family-level concordance, yielding absolute gains of approximately 4 and 5 percentage points, respectively. This improvement is clinically relevant: in a diagnostic setting, a 5-point increase in correct tumor classification can directly affect cancer subtype assignment and, in turn, influence treatment selection and downstream clinical decision-making. Our results show that the proposed model, grounded in stronger methodological practice in machine learning, consistently outperforms the previous state of the art across evaluation settings and can materially improve the reliability of CNS tumor classification.
Paulo R. Ferreira, Lucas Coutinho Freitas, Laís dos Santos Gonçalves +4
Universidade Federal de Pelotas, Pelotas, Rio Grande do Sul, Brazil · Hospital de Clínicas de Porto Alegre, Porto Alegre, Rio Grande do Sul, Brazil
Purpose. To compare deep learning architectures and classification schemes for dermoscopic images of skin neoplasms and assess their generalization on transfer from open international datasets to independent clinical datasets of Russian practice. Methods. Four architectures (ViT-B/16, Swin-S, ConvNeXt-S, EfficientNetV2-S) were compared in three schemes: binary (malignant/benign), single-stage four-class (benign, MEL, SCC, BCC), and a two-stage cascade (binary triage, then three-class differentiation MEL/SCC/BCC). All models used ImageNet-pretrained weights and a single augmentation protocol on aggregated open ISIC Archive data, and were evaluated on an internal held-out sample and two clinical datasets (Melanoscope AI mobile system; Sechenov University). Results. Internally the binary stage attains ROC-AUC 0.952-0.966; on Sechenov University it drops to 0.797-0.893, sensitivity to 0.53-0.67, and ECE rises from 0.02 to 0.27-0.39 with underestimation of malignancy, quantifying a generalization gap in ranking and calibration. Paired tests confirm one inter-architecture result on clinical data: the deficit of ViT-B/16 at the binary stage (p<0.05); at the differentiation stage no architecture has a proven advantage. The cascade raises macro F1 over single-stage four-class classification for most architectures, but significantly only for ViT-B/16, by recovering malignant lesions assigned to the dominant benign class. On ISIC MILK10k, direct 11-class classification yields mean-class sensitivity 0.525. Conclusion. A tunable triage threshold gives sensitivity control not attainable in standard single-stage (argmax) classification and better reproduces clinical differential-diagnosis logic. The persistent generalization gap mandates external clinical validation and recalibration before deployment.
Elena S. Kozachok, Sergey S. Seregin, Aleksandr V. Kozachok +2
Ivannikov Institute for System Programming of the Russian Academy of Sciences (ISP RAS), Moscow, Russia · Orel Oncological Dispensary, Orel, Russia