Search

Your search keyword '"Marion Mickler"' showing total 11 results
Start Over Author "Marion Mickler"
11 results on '"Marion Mickler"'

1. CLAUDIUS Study: Risk of materno-fetal transmission of melanoma cells in pregnant women with high grade melanoma – A retrospective multicenter study and literature review

Author

Svenja Vanessa Wiedemann, Verena Müller, Bettina Toth, Michael Erdmann, Bodo Bühler, Susanne Dugas-Breit, Kerstin Schatton, Lydia Reinhardt, Markus Meissner, Marion Mickler, Claudia Pföhler, Carsten Weishaupt, Rudolf Herbst, Dirk Debus, Laura Susok, Julia Katharina Tietze, Julia Welzel, Andreas Arnold, Evelyn Dabrowski, Andrea Forschner, Steven Goetze, Kinan Hayani, Céleste Lebbe, Florian Löhr, Miriam Mengoni, Barbara Hermes, Wiebke Katharina Peitsch, Gabriela Poch, Michael Max Sachse, Anca Sindrilaru, Saskia Wenk, Mirjana Ziemer, Kjell Kaune, Lisette Meier-Naust, Georgios Nikolakis, Florian Oberndörfer, Ulrich Wesselmann, Jochen Sven Utikal, and Maria Rita Gaiser

Subjects
Melanoma, Multicentre, Pregnancy, Retrospective, Transplacental metastases, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282
Abstract

Background: Vertical transmission of maternal cancer cells to the child is extremely rare, but melanoma represents the most common culprit. The aim of this study is to determine individual risks for materno-fetal transmission of melanoma cells and to establish standardized procedures for pregnant melanoma patients and their offspring. Patients and methods: In this retrospective multicenter study, data on women with stage III or IV melanoma that had been diagnosed before, during or up to 12 months after pregnancy, were analyzed for the occurrence of metastases in the placenta or the infant. In addition, a literature search for previously described materno-fetal transmission in case of maternal melanoma was conducted. A historical patient group was established from these cases and a statistical analysis was performed (SAS, p < 0.05 significant). Results: In total, 67 children born to women with stage III or IV melanoma were included. No placental or infant metastases were detected in any of the cases. The additional literature search revealed 37 cases with placental metastases and 14 cases with infant metastases (6 of them overlapping). Of the affected children, 10 (71.43%) died from their disease. Maternal death shortly after birth seems to be an unfavorable factor for transmission to the infant. Conclusion: The risk of materno-fetal transmission of maternal melanoma metastases seems to be much lower than anticipated based on former studies. However, thorough placental screening and systematic follow-up of the children resulting from pregnancies of high-risk melanoma patients should be performed.

Published
2023
Full Text
View/download PDF

2. Virus-specific memory T cell responses unmasked by immune checkpoint blockade cause hepatitis

Author

James A. Hutchinson, Katharina Kronenberg, Paloma Riquelme, Jürgen J. Wenzel, Gunther Glehr, Hannah-Lou Schilling, Florian Zeman, Katja Evert, Martin Schmiedel, Marion Mickler, Konstantin Drexler, Florian Bitterer, Laura Cordero, Lukas Beyer, Christian Bach, Josef Koestler, Ralph Burkhardt, Hans J. Schlitt, Dirk Hellwig, Jens M. Werner, Rainer Spang, Barbara Schmidt, Edward K. Geissler, and Sebastian Haferkamp

Subjects
Science
Abstract

Checkpoint blocking therapies are used to treat metastatic melanoma, but can have adverse immune-mediated effects, including liver pathology. Here the authors identify an expanded pool of CD4+ effector memory T cells resulting from prior CMV exposure as a risk factor for this adverse effect in these patients.

Published
2021
Full Text
View/download PDF

3. Immunometabolic Markers in a Small Patient Cohort Undergoing Immunotherapy

Author

Joshua Hofbauer, Andreas Hauck, Carina Matos, Nathalie Babl, Sonja-Maria Decking, Michael Rechenmacher, Christian Schulz, Sabine Regotta, Marion Mickler, Sebastian Haferkamp, Peter J. Siska, Wolfgang Herr, Kathrin Renner, Marina Kreutz, and Annette Schnell

Subjects
PD-1, immunotherapy, PD-1+ monocytes, metabolism, hormones, immune cells, Microbiology, QR1-502
Abstract

Although the discovery of immune checkpoints was hailed as a major breakthrough in cancer therapy, generating a sufficient response to immunotherapy is still limited. Thus, the objective of this exploratory, hypothesis-generating study was to identify potentially novel peripheral biomarkers and discuss the possible predictive relevance of combining scarcely investigated metabolic and hormonal markers with immune subsets. Sixteen markers that differed significantly between responders and non-responders were identified. In a further step, the correlation with progression-free survival (PFS) and false discovery correction (Benjamini and Hochberg) revealed potential predictive roles for the immune subset absolute lymphocyte count (rs = 0.51; p = 0.0224 *), absolute basophil count (rs = 0.43; p = 0.04 *), PD-1+ monocytes (rs = −0.49; p = 0.04 *), hemoglobin (rs = 0.44; p = 0.04 *), metabolic markers LDL (rs = 0.53; p = 0.0224 *), free androgen index (rs = 0.57; p = 0.0224 *) and CRP (rs = −0.46; p = 0.0352 *). The absolute lymphocyte count, LDL and free androgen index were the most significant individual markers, and combining the immune subsets with the metabolic markers into a biomarker ratio enhanced correlation with PFS (rs = −0.74; p ≤ 0.0001 ****). In summary, in addition to well-established markers, we identified PD-1+ monocytes and the free androgen index as potentially novel peripheral markers in the context of immunotherapy. Furthermore, the combination of immune subsets with metabolic and hormonal markers may have the potential to enhance the power of future predictive scores and should, therefore, be investigated further in larger trials.

Published
2022
Full Text
View/download PDF

4. Superior skin cancer classification by the combination of human and artificial intelligence

Author

Achim Hekler, Jochen S. Utikal, Alexander H. Enk, Axel Hauschild, Michael Weichenthal, Roman C. Maron, Carola Berking, Sebastian Haferkamp, Joachim Klode, Dirk Schadendorf, Bastian Schilling, Tim Holland-Letz, Benjamin Izar, Christof von Kalle, Stefan Fröhling, Titus J. Brinker, Laurenz Schmitt, Wiebke K. Peitsch, Friederike Hoffmann, Jürgen C. Becker, Christina Drusio, Philipp Jansen, Georg Lodde, Stefanie Sammet, Wiebke Sondermann, Selma Ugurel, Jeannine Zader, Alexander Enk, Martin Salzmann, Sarah Schäfer, Knut Schäkel, Julia Winkler, Priscilla Wölbing, Hiba Asper, Ann-Sophie Bohne, Victoria Brown, Bianca Burba, Sophia Deffaa, Cecilia Dietrich, Matthias Dietrich, Katharina Antonia Drerup, Friederike Egberts, Anna-Sophie Erkens, Salim Greven, Viola Harde, Marion Jost, Merit Kaeding, Katharina Kosova, Stephan Lischner, Maria Maagk, Anna Laetitia Messinger, Malte Metzner, Rogina Motamedi, Ann-Christine Rosenthal, Ulrich Seidl, Jana Stemmermann, Kaspar Torz, Juliana Giraldo Velez, Jennifer Haiduk, Mareike Alter, Claudia Bär, Paul Bergenthal, Anne Gerlach, Christian Holtorf, Ante Karoglan, Sophie Kindermann, Luise Kraas, Moritz Felcht, Maria R. Gaiser, Claus-Detlev Klemke, Hjalmar Kurzen, Thomas Leibing, Verena Müller, Raphael R. Reinhard, Jochen Utikal, Franziska Winter, Laurie Eicher, Daniela Hartmann, Markus Heppt, Katharina Kilian, Sebastian Krammer, Diana Lill, Anne-Charlotte Niesert, Eva Oppel, Elke Sattler, Sonja Senner, Jens Wallmichrath, Hans Wolff, Anja Gesierich, Tina Giner, Valerie Glutsch, Andreas Kerstan, Dagmar Presser, Philipp Schrüfer, Patrick Schummer, Ina Stolze, Judith Weber, Konstantin Drexler, Marion Mickler, Camila Toledo Stauner, Alexander Thiem, Schmitt, Laurenz (Beitragende*r), Peitsch, Wiebke K. (Beitragende*r), Hoffmann, Friederike (Beitragende*r), Becker, Jürgen (Beitragende*r), Drusio, Christina (Beitragende*r), Jansen, Philipp (Beitragende*r), Lodde, Georg (Beitragende*r), Sammet, Stefanie (Beitragende*r), Sondermann, Wiebke (Beitragende*r), Ugurel, Selma (Beitragende*r), Zader, Jeannine (Beitragende*r), Salzmann, Martin (Beitragende*r), Schäfer, Sarah (Beitragende*r), Schäkel, Knut (Beitragende*r), Winkler, Julia (Beitragende*r), Wölbing, Priscilla (Beitragende*r), Asper, Hiba (Beitragende*r), Bohne, Ann-Sophie (Beitragende*r), Brown, Victoria (Beitragende*r), Burba, Bianca (Beitragende*r), Deffaa, Sophia (Beitragende*r), Dietrich, Cecilia (Beitragende*r), Dietrich, Matthias (Beitragende*r), Drerup, Katharina Antonia (Beitragende*r), Egberts, Friederike (Beitragende*r), Erkens, Anna-Sophie (Beitragende*r), Greven, Salim (Beitragende*r), Harde, Viola (Beitragende*r), Jost, Marion (Beitragende*r), Kaeding, Merit (Beitragende*r), Kosova, Katharina (Beitragende*r), Lischner, Stephan (Beitragende*r), Maagk, Maria (Beitragende*r), Messinger, Anna Laetitia (Beitragende*r), Metzner, Malte (Beitragende*r), Motamedi, Rogina (Beitragende*r), Rosenthal, Ann-Christine (Beitragende*r), Seidl, Ulrich (Beitragende*r), Stemmermann, Jana (Beitragende*r), Torz, Kaspar (Beitragende*r), Velez, Juliana Giraldo (Beitragende*r), Haiduk, Jennifer (Beitragende*r), Alter, Mareike (Beitragende*r), Bär, Claudia (Beitragende*r), Bergenthal, Paul (Beitragende*r), Gerlach, Anne (Beitragende*r), Holtorf, Christian (Beitragende*r), Karoglan, Ante (Beitragende*r), Kindermann, Sophie (Beitragende*r), Kraas, Luise (Beitragende*r), Felcht, Moritz (Beitragende*r), Gaiser, Maria R. (Beitragende*r), Klemke, Claus-Detlev (Beitragende*r), Kurzen, Hjalmar (Beitragende*r), Leibing, Thomas (Beitragende*r), Müller, Verena (Beitragende*r), Reinhard, Raphael R. (Beitragende*r), Winter, Franziska (Beitragende*r), Eicher, Laurie (Beitragende*r), Hartmann, Daniela (Beitragende*r), Heppt, Markus (Beitragende*r), Kilian, Katharina (Beitragende*r), Krammer, Sebastian (Beitragende*r), Lill, Diana (Beitragende*r), Niesert, Anne-Charlotte (Beitragende*r), Oppel, Eva (Beitragende*r), Sattler, Elke (Beitragende*r), Senner, Sonja (Beitragende*r), Wallmichrath, Jens (Beitragende*r), Wolff, Hans (Beitragende*r), Gesierich, Anja (Beitragende*r), Giner, Tina (Beitragende*r), Glutsch, Valerie (Beitragende*r), Kerstan, Andreas (Beitragende*r), Presser, Dagmar (Beitragende*r), Schrüfer, Philipp (Beitragende*r), Schummer, Patrick (Beitragende*r), Stolze, Ina (Beitragende*r), Weber, Judith (Beitragende*r), Drexler, Konstantin (Beitragende*r), Mickler, Marion (Beitragende*r), Stauner, Camila Toledo (Beitragende*r), and Thiem, Alexander (Beitragende*r)

Subjects
0301 basic medicine, Cancer Research, Skin Neoplasms, Computer science, Medizin, Dermoscopy, Convolutional neural network, 03 medical and health sciences, Class imbalance, Deep Learning, 0302 clinical medicine, Image Interpretation, Computer-Assisted, medicine, Humans, Medical diagnosis, Observer Variation, business.industry, Deep learning, Prognosis, medicine.disease, 030104 developmental biology, Oncology, Binary classification, 030220 oncology & carcinogenesis, Neural Networks, Computer, Artificial intelligence, Gradient boosting, Skin cancer, business, Classifier (UML), Algorithms, Dermatologists
Abstract

Background In recent studies, convolutional neural networks (CNNs) outperformed dermatologists in distinguishing dermoscopic images of melanoma and nevi. In these studies, dermatologists and artificial intelligence were considered as opponents. However, the combination of classifiers frequently yields superior results, both in machine learning and among humans. In this study, we investigated the potential benefit of combining human and artificial intelligence for skin cancer classification. Methods Using 11,444 dermoscopic images, which were divided into five diagnostic categories, novel deep learning techniques were used to train a single CNN. Then, both 112 dermatologists of 13 German university hospitals and the trained CNN independently classified a set of 300 biopsy-verified skin lesions into those five classes. Taking into account the certainty of the decisions, the two independently determined diagnoses were combined to a new classifier with the help of a gradient boosting method. The primary end-point of the study was the correct classification of the images into five designated categories, whereas the secondary end-point was the correct classification of lesions as either benign or malignant (binary classification). Findings Regarding the multiclass task, the combination of man and machine achieved an accuracy of 82.95%. This was 1.36% higher than the best of the two individual classifiers (81.59% achieved by the CNN). Owing to the class imbalance in the binary problem, sensitivity, but not accuracy, was examined and demonstrated to be superior (89%) to the best individual classifier (CNN with 86.1%). The specificity in the combined classifier decreased from 89.2% to 84%. However, at an equal sensitivity of 89%, the CNN achieved a specificity of only 81.5% Interpretation Our findings indicate that the combination of human and artificial intelligence achieves superior results over the independent results of both of these systems.

Published
2019
Full Text
View/download PDF

5. Virus-specific memory T cell responses unmasked by immune checkpoint blockade cause hepatitis

Author

Paloma Riquelme, Konstantin Drexler, Hans J. Schlitt, Marion Mickler, Martin Schmiedel, Josef Koestler, Laura Cordero, Jens M. Werner, Sebastian Haferkamp, Jürgen J. Wenzel, Dirk Hellwig, Christian Bach, Katja Evert, Gunther Glehr, Edward K. Geissler, James A. Hutchinson, Florian Zeman, Ralph Burkhardt, Lukas Philipp Beyer, Rainer Spang, Hannah-Lou Schilling, Barbara Schmidt, Katharina Kronenberg, F Bitterer, and Publica

Subjects
CD4-Positive T-Lymphocytes, 0301 basic medicine, Immunotherapy Melanoma, Predictive markers, Tumour immunology, Viral host response, Science, Programmed Cell Death 1 Receptor, Congenital cytomegalovirus infection, 610 Medizin, Cytomegalovirus, General Physics and Astronomy, CD8-Positive T-Lymphocytes, Predictive markers, Antiviral Agents, Article, General Biochemistry, Genetics and Molecular Biology, Virus, 03 medical and health sciences, 0302 clinical medicine, medicine, Humans, Valganciclovir, CTLA-4 Antigen, ddc:610, Immune Checkpoint Inhibitors, Melanoma, Hepatitis, Multidisciplinary, business.industry, Viral host response, General Chemistry, Hepatitis A, Viral Load, medicine.disease, Immune checkpoint, Blockade, 030104 developmental biology, medicine.anatomical_structure, 030220 oncology & carcinogenesis, Cytomegalovirus Infections, Immunology, Tumour immunology, Immunotherapy, business, Immunologic Memory, Memory T cell, Viral load, medicine.drug
Abstract

Treatment of advanced melanoma with combined PD-1/CTLA-4 blockade commonly causes serious immune-mediated complications. Here, we identify a subset of patients predisposed to immune checkpoint blockade-related hepatitis who are distinguished by chronic expansion of effector memory CD4+ T cells (TEM cells). Pre-therapy CD4+ TEM cell expansion occurs primarily during autumn or winter in patients with metastatic disease and high cytomegalovirus (CMV)-specific serum antibody titres. These clinical features implicate metastasis-dependent, compartmentalised CMV reactivation as the cause of CD4+ TEM expansion. Pre-therapy CD4+ TEM expansion predicts hepatitis in CMV-seropositive patients, opening possibilities for avoidance or prevention. 3 of 4 patients with pre-treatment CD4+ TEM expansion who received αPD-1 monotherapy instead of αPD-1/αCTLA-4 therapy remained hepatitis-free. 4 of 4 patients with baseline CD4+ TEM expansion given prophylactic valganciclovir and αPD-1/αCTLA-4 therapy remained hepatitis-free. Our findings exemplify how pathogen exposure can shape clinical reactions after cancer therapy and how this insight leads to therapeutic innovations., Checkpoint blocking therapies are used to treat metastatic melanoma, but can have adverse immune-mediated effects, including liver pathology. Here the authors identify an expanded pool of CD4+ effector memory T cells resulting from prior CMV exposure as a risk factor for this adverse effect in these patients.

Published
2021

7. Systematic outperformance of 112 dermatologists in multiclass skin cancer image classification by convolutional neural networks

Author

Roman C. Maron, Michael Weichenthal, Jochen S. Utikal, Achim Hekler, Carola Berking, Axel Hauschild, Alexander H. Enk, Sebastian Haferkamp, Joachim Klode, Dirk Schadendorf, Philipp Jansen, Tim Holland-Letz, Bastian Schilling, Christof von Kalle, Stefan Fröhling, Maria R. Gaiser, Daniela Hartmann, Anja Gesierich, Katharina C. Kähler, Ulrike Wehkamp, Ante Karoglan, Claudia Bär, Titus J. Brinker, Laurenz Schmitt, Wiebke K. Peitsch, Friederike Hoffmann, Jürgen C. Becker, Christina Drusio, Georg Lodde, Stefanie Sammet, Wiebke Sondermann, Selma Ugurel, Jeannine Zader, Alexander Enk, Martin Salzmann, Sarah Schäfer, Knut Schäkel, Julia Winkler, Priscilla Wölbing, Hiba Asper, Ann-Sophie Bohne, Victoria Brown, Bianca Burba, Sophia Deffaa, Cecilia Dietrich, Matthias Dietrich, Katharina Antonia Drerup, Friederike Egberts, Anna-Sophie Erkens, Salim Greven, Viola Harde, Marion Jost, Merit Kaeding, Katharina Kosova, Stephan Lischner, Maria Maagk, Anna Laetitia Messinger, Malte Metzner, Rogina Motamedi, Ann-Christine Rosenthal, Ulrich Seidl, Jana Stemmermann, Kaspar Torz, Juliana Giraldo Velez, Jennifer Haiduk, Mareike Alter, Paul Bergenthal, Anne Gerlach, Christian Holtorf, Sophie Kindermann, Luise Kraas, Moritz Felcht, Claus-Detlev Klemke, Hjalmar Kurzen, Thomas Leibing, Verena Müller, Raphael R. Reinhard, Jochen Utikal, Franziska Winter, Laurie Eicher, Markus Heppt, Katharina Kilian, Sebastian Krammer, Diana Lill, Anne-Charlotte Niesert, Eva Oppel, Elke Sattler, Sonja Senner, Jens Wallmichrath, Hans Wolff, Tina Giner, Valerie Glutsch, Andreas Kerstan, Dagmar Presser, Philipp Schrüfer, Patrick Schummer, Ina Stolze, Judith Weber, Konstantin Drexler, Marion Mickler, Camila Toledo Stauner, and Alexander Thiem

Subjects
0301 basic medicine, Male, Cancer Research, medicine.medical_specialty, Skin Neoplasms, Biopsy, Medizin, Dermoscopy, Sensitivity and Specificity, Multiclass classification, Diagnosis, Differential, Hospitals, University, 03 medical and health sciences, 0302 clinical medicine, McNemar's test, Surveys and Questionnaires, medicine, Humans, Medical diagnosis, Melanoma, Nevus, Contextual image classification, business.industry, Deep learning, medicine.disease, Dermatology, Confidence interval, 030104 developmental biology, Oncology, Binary classification, 030220 oncology & carcinogenesis, Female, Artificial intelligence, Neural Networks, Computer, Skin cancer, business, Algorithms, Dermatologists
Abstract

Background: Recently, convolutional neural networks (CNNs) systematically outperformed dermatologists in distinguishing dermoscopic melanoma and nevi images. However, such a binary classification does not reflect the clinical reality of skin cancer screenings in which multiple diagnoses need to be taken into account. Methods: Using 11,444 dermoscopic images, which covered dermatologic diagnoses comprising the majority of commonly pigmented skin lesions commonly faced in skin cancer screenings, a CNN was trained through novel deep learning techniques. A test set of 300 biopsy-verified images was used to compare the classifier's performance with that of 112 dermatologists from 13 German university hospitals. The primary end-point was the correct classification of the different lesions into benign and malignant. The secondary end-point was the correct classification of the images into one of the five diagnostic categories. Findings: Sensitivity and specificity of dermatologists for the primary end-point were 74.4% (95% confidence interval [CI]: 67.0–81.8%) and 59.8% (95% CI: 49.8–69.8%), respectively. At equal sensitivity, the algorithm achieved a specificity of 91.3% (95% CI: 85.5–97.1%). For the secondary end-point, the mean sensitivity and specificity of the dermatologists were at 56.5% (95% CI: 42.8–70.2%) and 89.2% (95% CI: 85.0–93.3%), respectively. At equal sensitivity, the algorithm achieved a specificity of 98.8%. Two-sided McNemar tests revealed significance for the primary end-point (p < 0.001). For the secondary end-point, outperformance (p < 0.001) was achieved except for basal cell carcinoma (on-par performance). Interpretation: Our findings show that automated classification of dermoscopic melanoma and nevi images is extendable to a multiclass classification problem, thus better reflecting clinical differential diagnoses, while still outperforming dermatologists at a significant level (p < 0.001).

Published
2019

8. Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task

Author

Titus J. Brinker, Achim Hekler, Alexander H. Enk, Joachim Klode, Axel Hauschild, Carola Berking, Bastian Schilling, Sebastian Haferkamp, Dirk Schadendorf, Tim Holland-Letz, Jochen S. Utikal, Christof von Kalle, Wiebke Ludwig-Peitsch, Judith Sirokay, Lucie Heinzerling, Magarete Albrecht, Katharina Baratella, Lena Bischof, Eleftheria Chorti, Anna Dith, Christina Drusio, Nina Giese, Emmanouil Gratsias, Klaus Griewank, Sandra Hallasch, Zdenka Hanhart, Saskia Herz, Katja Hohaus, Philipp Jansen, Finja Jockenhöfer, Theodora Kanaki, Sarah Knispel, Katja Leonhard, Anna Martaki, Liliana Matei, Johanna Matull, Alexandra Olischewski, Maximilian Petri, Jan-Malte Placke, Simon Raub, Katrin Salva, Swantje Schlott, Elsa Sody, Nadine Steingrube, Ingo Stoffels, Selma Ugurel, Anne Zaremba, Christoffer Gebhardt, Nina Booken, Maria Christolouka, Kristina Buder-Bakhaya, Therezia Bokor-Billmann, Alexander Enk, Patrick Gholam, Holger Hänßle, Martin Salzmann, Sarah Schäfer, Knut Schäkel, Timo Schank, Ann-Sophie Bohne, Sophia Deffaa, Katharina Drerup, Friederike Egberts, Anna-Sophie Erkens, Benjamin Ewald, Sandra Falkvoll, Sascha Gerdes, Viola Harde, Marion Jost, Katja Kosova, Laetitia Messinger, Malte Metzner, Kirsten Morrison, Rogina Motamedi, Anja Pinczker, Anne Rosenthal, Natalie Scheller, Thomas Schwarz, Dora Stölzl, Federieke Thielking, Elena Tomaschewski, Ulrike Wehkamp, Michael Weichenthal, Oliver Wiedow, Claudia Maria Bär, Sophia Bender-Säbelkampf, Marc Horbrügger, Ante Karoglan, Luise Kraas, Jörg Faulhaber, Cyrill Geraud, Ze Guo, Philipp Koch, Miriam Linke, Nolwenn Maurier, Verena Müller, Benjamin Thomas, Jochen Sven Utikal, Ali Saeed M. Alamri, Andrea Baczako, Matthias Betke, Carolin Haas, Daniela Hartmann, Markus V. Heppt, Katharina Kilian, Sebastian Krammer, Natalie Lidia Lapczynski, Sebastian Mastnik, Suzan Nasifoglu, Cristel Ruini, Elke Sattler, Max Schlaak, Hans Wolff, Birgit Achatz, Astrid Bergbreiter, Konstantin Drexler, Monika Ettinger, Anna Halupczok, Marie Hegemann, Verena Dinauer, Maria Maagk, Marion Mickler, Biance Philipp, Anna Wilm, Constanze Wittmann, Anja Gesierich, Valerie Glutsch, Katrin Kahlert, Andreas Kerstan, and Philipp Schrüfer

Subjects
0301 basic medicine, Cancer Research, Skin Neoplasms, Head to head, Medizin, Dermoscopy, Convolutional neural network, Sensitivity and Specificity, Hospitals, University, 03 medical and health sciences, 0302 clinical medicine, Deep Learning, Germany, Medicine, Humans, Melanoma, Nevus, Contextual image classification, Receiver operating characteristic, business.industry, Deep learning, Pattern recognition, University hospital, 030104 developmental biology, Oncology, 030220 oncology & carcinogenesis, Artificial intelligence, business, Dermatologists
Abstract

Background Recent studies have successfully demonstrated the use of deep-learning algorithms for dermatologist-level classification of suspicious lesions by the use of excessive proprietary image databases and limited numbers of dermatologists. For the first time, the performance of a deep-learning algorithm trained by open-source images exclusively is compared to a large number of dermatologists covering all levels within the clinical hierarchy. Methods We used methods from enhanced deep learning to train a convolutional neural network (CNN) with 12,378 open-source dermoscopic images. We used 100 images to compare the performance of the CNN to that of the 157 dermatologists from 12 university hospitals in Germany. Outperformance of dermatologists by the deep neural network was measured in terms of sensitivity, specificity and receiver operating characteristics. Findings The mean sensitivity and specificity achieved by the dermatologists with dermoscopic images was 74.1% (range 40.0%–100%) and 60% (range 21.3%–91.3%), respectively. At a mean sensitivity of 74.1%, the CNN exhibited a mean specificity of 86.5% (range 70.8%–91.3%). At a mean specificity of 60%, a mean sensitivity of 87.5% (range 80%–95%) was achieved by our algorithm. Among the dermatologists, the chief physicians showed the highest mean specificity of 69.2% at a mean sensitivity of 73.3%. With the same high specificity of 69.2%, the CNN had a mean sensitivity of 84.5%. Interpretation A CNN trained by open-source images exclusively outperformed 136 of the 157 dermatologists and all the different levels of experience (from junior to chief physicians) in terms of average specificity and sensitivity.

Published
2019

9. A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task

Author

Titus J. Brinker, Achim Hekler, Alexander H. Enk, Joachim Klode, Axel Hauschild, Carola Berking, Bastian Schilling, Sebastian Haferkamp, Dirk Schadendorf, Stefan Fröhling, Jochen S. Utikal, Christof von Kalle, Wiebke Ludwig-Peitsch, Judith Sirokay, Lucie Heinzerling, Magarete Albrecht, Katharina Baratella, Lena Bischof, Eleftheria Chorti, Anna Dith, Christina Drusio, Nina Giese, Emmanouil Gratsias, Klaus Griewank, Sandra Hallasch, Zdenka Hanhart, Saskia Herz, Katja Hohaus, Philipp Jansen, Finja Jockenhöfer, Theodora Kanaki, Sarah Knispel, Katja Leonhard, Anna Martaki, Liliana Matei, Johanna Matull, Alexandra Olischewski, Maximilian Petri, Jan-Malte Placke, Simon Raub, Katrin Salva, Swantje Schlott, Elsa Sody, Nadine Steingrube, Ingo Stoffels, Selma Ugurel, Wiebke Sondermann, Anne Zaremba, Christoffer Gebhardt, Nina Booken, Maria Christolouka, Kristina Buder-Bakhaya, Therezia Bokor-Billmann, Alexander Enk, Patrick Gholam, Holger Hänßle, Martin Salzmann, Sarah Schäfer, Knut Schäkel, Timo Schank, Ann-Sophie Bohne, Sophia Deffaa, Katharina Drerup, Friederike Egberts, Anna-Sophie Erkens, Benjamin Ewald, Sandra Falkvoll, Sascha Gerdes, Viola Harde, Marion Jost, Katja Kosova, Laetitia Messinger, Malte Metzner, Kirsten Morrison, Rogina Motamedi, Anja Pinczker, Anne Rosenthal, Natalie Scheller, Thomas Schwarz, Dora Stölzl, Federieke Thielking, Elena Tomaschewski, Ulrike Wehkamp, Michael Weichenthal, Oliver Wiedow, Claudia Maria Bär, Sophia Bender-Säbelkampf, Marc Horbrügger, Ante Karoglan, Luise Kraas, Jörg Faulhaber, Cyrill Geraud, Ze Guo, Philipp Koch, Miriam Linke, Nolwenn Maurier, Verena Müller, Benjamin Thomas, Jochen Sven Utikal, Ali Saeed M. Alamri, Andrea Baczako, Matthias Betke, Carolin Haas, Daniela Hartmann, Markus V. Heppt, Katharina Kilian, Sebastian Krammer, Natalie Lidia Lapczynski, Sebastian Mastnik, Suzan Nasifoglu, Cristel Ruini, Elke Sattler, Max Schlaak, Hans Wolff, Birgit Achatz, Astrid Bergbreiter, Konstantin Drexler, Monika Ettinger, Anna Halupczok, Marie Hegemann, Verena Dinauer, Maria Maagk, Marion Mickler, Biance Philipp, Anna Wilm, Constanze Wittmann, Anja Gesierich, Valerie Glutsch, Katrin Kahlert, Andreas Kerstan, and Philipp Schrüfer

Subjects
0301 basic medicine, Cancer Research, Skin Neoplasms, Computer science, Medizin, Dermoscopy, Dermatology, Convolutional neural network, Sensitivity and Specificity, 03 medical and health sciences, 0302 clinical medicine, Image Interpretation, Computer-Assisted, Humans, Melanoma, Receiver operating characteristic, Contextual image classification, Artificial neural network, business.industry, Deep learning, Pattern recognition, University hospital, Human assessment, 030104 developmental biology, Oncology, 030220 oncology & carcinogenesis, Artificial intelligence, Neural Networks, Computer, business, Dermatologists
Abstract

Background: Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists. Methods: We compared automatic digital melanoma classification with the performance of 145 dermatologists of 12 German university hospitals. We used methods from enhanced deep learning to train a CNN with 12,378 open-source dermoscopic images. We used 100 clinical images to compare the performance of the CNN to that of the dermatologists. Dermatologists were compared with the deep neural network in terms of sensitivity, specificity and receiver operating characteristics. Findings: The mean sensitivity and specificity achieved by the dermatologists with clinical images was 89.4% (range: 55.0%-100%) and 64.4% (range: 22.5%-92.5%). At the same sensitivity, the CNN exhibited a mean specificity of 68.2% (range 47.5%-86.25%). Among the dermatologists, the attendings showed the highest mean sensitivity of 92.8% at a mean specificity of 57.7%. With the same high sensitivity of 92.8%, the CNN had a mean specificity of 61.1%. Interpretation: For the first time, dermatologist-level image classification was achieved on a clinical image classification task without training on clinical images. The CNN had a smaller variance of results indicating a higher robustness of computer vision compared with human assessment for dermatologic image classification tasks. (C) 2019 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Published
2018

11. Phacomatosis pigmentokeratotica is caused by a postzygotic HRAS mutation in a multipotent progenitor cell

Author

Michael Landthaler, Blanca Diaz-Ley, Eva Herschberger, Andreas Wollenberg, Sigrid Tinschert, Lorea Bagazgoitia, Ana Sagrera, Antonio Torrelo, Laura Maximiliane Ehmann, Tor Shwayder, Christian Hafner, Katharina Flux, Sebastian Singer, Marion Mickler, Francisco X. Real, Leopold Groesser, Agustí Toll, and Ilske Oschlies

Subjects
Adult, Proto-Oncogene Proteins B-raf, Skin Neoplasms, Class I Phosphatidylinositol 3-Kinases, Dermatology, Nevus, Sebaceous of Jadassohn, Gene mutation, Biology, RASopathy, Oncogene Protein p21(ras), Biochemistry, Proto-Oncogene Proteins p21(ras), symbols.namesake, Phosphatidylinositol 3-Kinases, medicine, Nevus, Humans, Receptor, Fibroblast Growth Factor, Type 3, HRAS, Progenitor cell, skin and connective tissue diseases, Molecular Biology, Genetics, Sanger sequencing, Nevus, Pigmented, Mosaicism, Multipotent Stem Cells, Cell Biology, Melanocytic nevus, Epidermal nevus syndrome, medicine.disease, Cancer research, symbols, Female
Abstract

Phacomatosis pigmentokeratotica (PPK) is a rare epidermal nevus syndrome characterized by the co-occurrence of a sebaceous nevus and a speckled lentiginous nevus. The coexistence of an epidermal and a melanocytic nevus has been explained by two homozygous recessive mutations, according to the twin spot hypothesis, of which PPK has become a putative paradigm in humans. However, the underlying gene mutations remained unknown. Multiple tissues of six patients with PPK were analyzed for the presence of RAS, FGFR3, PIK3CA, and BRAF mutations using SNaPshot assays and Sanger sequencing. We identified a heterozygous HRAS c.37G>C (p.Gly13Arg) mutation in four patients and a heterozygous HRAS c.182A>G (p.Gln61Arg) mutation in two patients. In each case, the mutations were present in both the sebaceous and the melanocytic nevus. In the latter lesion, melanocytes were identified to carry the HRAS mutation. Analysis of various nonlesional tissues showed a wild-type sequence of HRAS, consistent with mosaicism. Our data provide no genetic evidence for the previously proposed twin spot hypothesis. In contrast, PPK is best explained by a postzygotic-activating HRAS mutation in a multipotent progenitor cell that gives rise to both a sebaceous and a melanocytic nevus. Therefore, PPK is a mosaic RASopathy.

Published
2012

Catalog

Books, media, physical & digital resources
See catalog results