1. Clinical Melanoma Diagnosis with Artificial Intelligence: Insights from a Prospective Multicenter Study
- Author
-
Heinlein, Lukas, Maron, Roman C., Hekler, Achim, Haggenmüller, Sarah, Wies, Christoph, Utikal, Jochen S., Meier, Friedegund, Hobelsberger, Sarah, Gellrich, Frank F., Sergon, Mildred, Hauschild, Axel, French, Lars E., Heinzerling, Lucie, Schlager, Justin G., Ghoreschi, Kamran, Schlaak, Max, Hilke, Franz J., Poch, Gabriela, Korsing, Sören, Berking, Carola, Heppt, Markus V., Erdmann, Michael, Haferkamp, Sebastian, Drexler, Konstantin, Schadendorf, Dirk, Sondermann, Wiebke, Goebeler, Matthias, Schilling, Bastian, Krieghoff-Henning, Eva, and Brinker, Titus J.
- Subjects
Electrical Engineering and Systems Science - Image and Video Processing ,Computer Science - Computer Vision and Pattern Recognition ,Statistics - Applications - Abstract
Early detection of melanoma, a potentially lethal type of skin cancer with high prevalence worldwide, improves patient prognosis. In retrospective studies, artificial intelligence (AI) has proven to be helpful for enhancing melanoma detection. However, there are few prospective studies confirming these promising results. Existing studies are limited by low sample sizes, too homogenous datasets, or lack of inclusion of rare melanoma subtypes, preventing a fair and thorough evaluation of AI and its generalizability, a crucial aspect for its application in the clinical setting. Therefore, we assessed 'All Data are Ext' (ADAE), an established open-source ensemble algorithm for detecting melanomas, by comparing its diagnostic accuracy to that of dermatologists on a prospectively collected, external, heterogeneous test set comprising eight distinct hospitals, four different camera setups, rare melanoma subtypes, and special anatomical sites. We advanced the algorithm with real test-time augmentation (R-TTA, i.e. providing real photographs of lesions taken from multiple angles and averaging the predictions), and evaluated its generalization capabilities. Overall, the AI showed higher balanced accuracy than dermatologists (0.798, 95% confidence interval (CI) 0.779-0.814 vs. 0.781, 95% CI 0.760-0.802; p<0.001), obtaining a higher sensitivity (0.921, 95% CI 0.900- 0.942 vs. 0.734, 95% CI 0.701-0.770; p<0.001) at the cost of a lower specificity (0.673, 95% CI 0.641-0.702 vs. 0.828, 95% CI 0.804-0.852; p<0.001). As the algorithm exhibited a significant performance advantage on our heterogeneous dataset exclusively comprising melanoma-suspicious lesions, AI may offer the potential to support dermatologists particularly in diagnosing challenging cases.
- Published
- 2024