Achim Hekler1, Jochen Sven Utikal2, Alexander H Enk3, Carola Berking4, Joachim Klode5, Dirk Schadendorf5, Philipp Jansen5, Cindy Franklin6, Tim Holland-Letz7, Dieter Krahl8, Christof von Kalle1, Stefan Fröhling1, Titus Josef Brinker9. 1. National Center for Tumor Diseases, German Cancer Research Center, Heidelberg, Germany. 2. Department of Dermatology, Heidelberg University, Mannheim, Germany; Skin Cancer Unit, German Cancer Research Center, Heidelberg, Germany. 3. Department of Dermatology, University Hospital Heidelberg, Heidelberg, Germany. 4. Department of Dermatology, University Hospital Munich (LMU), Munich, Germany. 5. Department of Dermatology, University Hospital Essen, Essen, Germany. 6. Department of Dermatology, University Hospital Cologne, Cologne, Germany. 7. Department of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg. 8. Private Laboratory of Dermatohistopathology, Mönchhofstraße 52, 69120 Heidelberg. 9. National Center for Tumor Diseases, German Cancer Research Center, Heidelberg, Germany; Department of Dermatology, University Hospital Heidelberg, Heidelberg, Germany. Electronic address: titus.brinker@dkfz.de.
Abstract
BACKGROUND: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports 25-26% of discordance for classifying a benign nevus versus malignant melanoma. Deep learning was successfully implemented to enhance the precision of lung and breast cancer diagnoses. The aim of this study is to illustrate the potential of deep learning to assist human assessment for a histopathologic melanoma diagnosis. METHODS: Six hundred ninety-five lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi and 345 melanomas). Only the haematoxylin and eosin stained (H&E) slides of these lesions were digitalised using a slide scanner and then randomly cropped. Five hundred ninety-five of the resulting images were used for the training of a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison with the original class labels. FINDINGS: The total discordance with the histopathologist was 18% for melanoma (95% confidence interval [CI]: 7.4-28.6%), 20% for nevi (95% CI: 8.9-31.1%) and 19% for the full set of images (95% CI: 11.3-26.7%). INTERPRETATION: Even in the worst case, the discordance of the CNN was about the same compared with the discordance between human pathologists as reported in the literature. Despite the vastly reduced amount of data, time necessary for diagnosis and cost compared with the pathologist, our CNN archived on-par performance. Conclusively, CNNs indicate to be a valuable tool to assist human melanoma diagnoses.
BACKGROUND: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports 25-26% of discordance for classifying a benign nevus versus malignant melanoma. Deep learning was successfully implemented to enhance the precision of lung and breast cancer diagnoses. The aim of this study is to illustrate the potential of deep learning to assist human assessment for a histopathologic melanoma diagnosis. METHODS: Six hundred ninety-five lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi and 345 melanomas). Only the haematoxylin and eosin stained (H&E) slides of these lesions were digitalised using a slide scanner and then randomly cropped. Five hundred ninety-five of the resulting images were used for the training of a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison with the original class labels. FINDINGS: The total discordance with the histopathologist was 18% for melanoma (95% confidence interval [CI]: 7.4-28.6%), 20% for nevi (95% CI: 8.9-31.1%) and 19% for the full set of images (95% CI: 11.3-26.7%). INTERPRETATION: Even in the worst case, the discordance of the CNN was about the same compared with the discordance between human pathologists as reported in the literature. Despite the vastly reduced amount of data, time necessary for diagnosis and cost compared with the pathologist, our CNN archived on-par performance. Conclusively, CNNs indicate to be a valuable tool to assist humanmelanoma diagnoses.
Authors: Max Schmitt; Roman Christoph Maron; Achim Hekler; Albrecht Stenzinger; Axel Hauschild; Michael Weichenthal; Markus Tiemann; Dieter Krahl; Heinz Kutzner; Jochen Sven Utikal; Sebastian Haferkamp; Jakob Nikolas Kather; Frederick Klauschen; Eva Krieghoff-Henning; Stefan Fröhling; Christof von Kalle; Titus Josef Brinker Journal: J Med Internet Res Date: 2021-02-02 Impact factor: 5.428
Authors: Lulu Sun; Jon N Marsh; Matthew K Matlock; Ling Chen; Joseph P Gaut; Elizabeth M Brunt; S Joshua Swamidass; Ta-Chiang Liu Journal: EBioMedicine Date: 2020-09-24 Impact factor: 8.143