摘要
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).
学科与关键词
- Deep neural networks are superior to dermatologists in melanoma image classificationBrinker, Titus J.*; Hekler, Achim; Enk, Alexander H.; Berking, Carola; Haferkamp, Sebastian; Hauschild, Axel; Weichenthal, Michael; Klode, Joachim; Schadendorf, Dirk; Holland-Letz, Tim; von Kalle, Christof; Froehling, Stefan; Schilling, Bastian; Utikal, Jochen S.European Journal of Cancer, 2019, 119: 11-17.被引 170
- Skin lesions of face and scalp - Classification by a market-approved convolutional neural network in comparison with 64 dermatologistsHaenssle, Holger Andreas*; Winkler, Julia Katharina; Fink, Christine; Toberer, Ferdinand; Enk, Alexander; Stolz, Wilhelm; Deinlein, Teresa; Hofmann-Wellenhof, Rainer; Kittler, Harald; Tschandl, Philipp; Rosendahl, Cliff; Lallas, Aimilios; Blum, Andreas; Abassi, Mohamed Souhayel; Thomas, Luc; Tromme, Isabelle; Rosenberger, AlbertEuropean Journal of Cancer, 2021, 144: 192-199.被引 25
- Convolutional neural network assistance significantly improves dermatologists' diagnosis of cutaneous tumours using clinical imagesBa, Wei; Wu, Huan; Chen, Wei W.; Wang, Shu H.; Zhang, Zi Y.; Wei, Xuan J.; Wang, Wen J.; Yang, Lei; Zhou, Dong M.; Zhuang, Yi X.; Zhong, Qin; Song, Zhi G.*; Li, Cheng X.*European Journal of Cancer, 2022, 169: 156-165.被引 14
