Development of an artificial intelligence algorithm for the diagnosis of infantile hemangiomas
- PMID: 36164801
- DOI: 10.1111/pde.15149
Development of an artificial intelligence algorithm for the diagnosis of infantile hemangiomas
Abstract
Prompt and accurate diagnosis of infantile hemangiomas is essential to prevent potential complications. This can be difficult due to high rates of misdiagnosis and poor access to pediatric dermatologists. In this study, we trained an artificial intelligence algorithm to diagnose infantile hemangiomas based on clinical images. Our algorithm achieved a 91.7% overall accuracy in the diagnosis of facial infantile hemangiomas.
Keywords: artificial intelligence; hemangioma; infants; machine learning; neoplasms; vascular tissue.
© 2022 Wiley Periodicals LLC.
References
REFERENCES
-
- Murphree DH, Puri P, Shamim H, et al. Deep learning for dermatologists: part I. Fundamental concepts. J Am Acad Dermatol. 2020;S0190-9622(20)30921-X.
-
- Puri P, Comfere N, Drage LA, et al. Deep learning for dermatologists: part II. Current applications. J Am Acad Dermatol. 2020;S0190-9622(20)30918-X.
-
- He, K, Zhang XY, Ren SQ, et al. Deep residual learning for image recognition. Paper presented at the 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2015.
-
- Greene AK, Liu AS, Mulliken JB, Chalache K, Fishman SJ. Vascular anomalies in 5621 patients: guidelines for referral. J Pediatr Surg. 2011;46(9):1784-1789.
-
- Macfie CC, Jeffery SL. Diagnosis of vascular skin lesions in children: an audit and review. Pediatr Dermatol. 2008;25(1):7-12.
MeSH terms
LinkOut - more resources
Full Text Sources
Medical