Assessing the Generalizability of Deep Learning Models Trained on Standardized and Nonstandardized Images and Their Performance Against Teledermatologists: Retrospective Comparative Study

Ayooluwatomiwa I Oloruntoba   ^{1, 2} , BMedSci ;   Tine Vestergaard   ³ , MD, PhD ;   Toan D Nguyen   ⁴ , PhD ;   Zhen Yu   ^{2, 5} , BME ;   Maithili Sashindranath   ¹ , PhD ;   Brigid Betz-Stablein   ⁶ , PhD ;   H Peter Soyer   ⁶ , MD ;   Zongyuan Ge   ^{2, 4, 7, 8} , PhD ;   Victoria Mar   ^{1, 9} , MBBS, PhD

¹ School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia

² Monash Medical Artificial Intelligence, Monash University, Clayton, Melbourne, Australia

³ Department of Dermatology and Allergy Centre, Odense University Hospital, Odense, Denmark

⁴ Monash eResearch Centre, Monash University, Clayton, Victoria, Melbourne, Australia

⁵ Central Clinical School, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia

⁶ Dermatology Research Centre, The University of Queensland Diamantina Institute, The University of Queensland, Brisbane, Australia

⁷ Airdoc-Monash Research, Monash University, Clayton, Melbourne, Australia

⁸ NVIDIA Artificial Intelligence Tech Centre, Monash University, Clayton, Victoria, Melbourne, Australia

⁹ Victorian Melanoma Service, Alfred Health, Melbourne, Australia