Titus J Brinker1, Lennard Kiehl2, Max Schmitt2, Tanja B Jutzi2, Eva I Krieghoff-Henning2, Dieter Krahl3, Heinz Kutzner4, Patrick Gholam5, Sebastian Haferkamp6, Joachim Klode7, Dirk Schadendorf7, Achim Hekler2, Stefan Fröhling8, Jakob N Kather9, Sarah Haggenmüller2, Christof von Kalle10, Markus Heppt11, Franz Hilke12, Kamran Ghoreschi12, Markus Tiemann13, Ulrike Wehkamp14, Axel Hauschild14, Michael Weichenthal14, Jochen S Utikal15. 1. Digital Biomarkers for Oncology Group, National Center for Tumor Diseases, German Cancer Research Center, Heidelberg, Germany. Electronic address: titus.brinker@dkfz.de. 2. Digital Biomarkers for Oncology Group, National Center for Tumor Diseases, German Cancer Research Center, Heidelberg, Germany. 3. Private Laboratory of Dermatohistopathology, Mönchhofstraße 52, 69120, Heidelberg, Germany. 4. Dermatopathology Laboratory, Friedrichshafen, Germany. 5. Department of Dermatology, University Hospital Heidelberg, Heidelberg. Germany. 6. Department of Dermatology, University Hospital Regensburg, Regensburg, Germany. 7. Department of Dermatology, University Hospital Essen, Essen, Germany. 8. Translational Medical Oncology, German Cancer Research Center (DKFZ), National Center for Tumor Diseases (NCT), 69120, Heidelberg, Germany. 9. Translational Medical Oncology, German Cancer Research Center (DKFZ), National Center for Tumor Diseases (NCT), 69120, Heidelberg, Germany; Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany. 10. Department of Clinical-Translational Sciences, Charité University Medicine and Berlin Institute of Health (BIH), Berlin, Germany. 11. Department of Dermatology, University Hospital Erlangen, Erlangen, Germany. 12. Department of Dermatology, Venereology and Allergology, Charité - Universitätsmedizin, Berlin, Germany. 13. Institute for Hematopathology Hamburg, Hamburg, Germany. 14. Skin Cancer Unit, German Cancer Research Center (DKFZ), Heidelberg, Germany. 15. Department of Dermatology, Venereology and Allergology, University Medical Center Mannheim, Ruprecht-Karl University of Heidelberg, Mannheim, Germany; Department of Dermatology, University Hospital (UKSH), Kiel, Germany.
Abstract
AIM: Sentinel lymph node status is a central prognostic factor for melanomas. However, the surgical excision involves some risks for affected patients. In this study, we therefore aimed to develop a digital biomarker that can predict lymph node metastasis non-invasively from digitised H&E slides of primary melanoma tumours. METHODS: A total of 415 H&E slides from primary melanoma tumours with known sentinel node (SN) status from three German university hospitals and one private pathological practice were digitised (150 SN positive/265 SN negative). Two hundred ninety-one slides were used to train artificial neural networks (ANNs). The remaining 124 slides were used to test the ability of the ANNs to predict sentinel status. ANNs were trained and/or tested on data sets that were matched or not matched between SN-positive and SN-negative cases for patient age, ulceration, and tumour thickness, factors that are known to correlate with lymph node status. RESULTS: The best accuracy was achieved by an ANN that was trained and tested on unmatched cases (61.8% ± 0.2%) area under the receiver operating characteristic (AUROC). In contrast, ANNs that were trained and/or tested on matched cases achieved (55.0% ± 3.5%) AUROC or less. CONCLUSION: Our results indicate that the image classifier can predict lymph node status to some, albeit so far not clinically relevant, extent. It may do so by mostly detecting equivalents of factors on histological slides that are already known to correlate with lymph node status. Our results provide a basis for future research with larger data cohorts.
AIM: Sentinel lymph node status is a central prognostic factor for melanomas. However, the surgical excision involves some risks for affected patients. In this study, we therefore aimed to develop a digital biomarker that can predict lymph node metastasis non-invasively from digitised H&E slides of primary melanoma tumours. METHODS: A total of 415 H&E slides from primary melanoma tumours with known sentinel node (SN) status from three German university hospitals and one private pathological practice were digitised (150 SN positive/265 SN negative). Two hundred ninety-one slides were used to train artificial neural networks (ANNs). The remaining 124 slides were used to test the ability of the ANNs to predict sentinel status. ANNs were trained and/or tested on data sets that were matched or not matched between SN-positive and SN-negative cases for patient age, ulceration, and tumour thickness, factors that are known to correlate with lymph node status. RESULTS: The best accuracy was achieved by an ANN that was trained and tested on unmatched cases (61.8% ± 0.2%) area under the receiver operating characteristic (AUROC). In contrast, ANNs that were trained and/or tested on matched cases achieved (55.0% ± 3.5%) AUROC or less. CONCLUSION: Our results indicate that the image classifier can predict lymph node status to some, albeit so far not clinically relevant, extent. It may do so by mostly detecting equivalents of factors on histological slides that are already known to correlate with lymph node status. Our results provide a basis for future research with larger data cohorts.