Artificial intelligence for skin lesion classification and diagnosis in dermatology: A narrative review

Abstract

Introduction: Artificial intelligence (AI) is increasingly present in dermatology, demonstrating accuracy levels comparable to, or even superior to, those of dermatologists in diagnosing skin lesions from clinical and dermoscopic images. This review provides an overview of AI's role in the automated classification and monitoring of skin lesions. Objective: To explore and map the existing literature on the use and benefits of AI in dermatology. Methods: This narrative review focused on exploring the use and benefits of AI in dermatology, utilizing MeSH/DeCS terms such as "Dermatology," "Artificial Intelligence," "Diagnosis," and "Computer Aided Diagnosis." Three databases (PubMed, Lillacs, and Scopus) from 2008 to 2024. We excluded articles that did not focus on dermatology, lacked the topic of Artificial Intelligence, or presented theoretical designs without practical application or evidence, resulting in a final selection of forty-four articles. Results: The results strongly support AI's effectiveness, displaying its precision in diagnosis, comparable to or exceeding that of human dermatologists across diverse tasks. The evolution of AI in dermatology implies a substantial transformation in care, extending its applications from skin cancer to various dermatological pathologies. While emphasizing the vital collaboration between AI and healthcare professionals, a critical gap remains in the real-world clinical validation of AI. Ethical considerations, especially in automated decision-making, need careful attention. Conclusions: This narrative review highlights the crucial role of AI in dermatology, emphasizing its potential to enhance diagnostic accuracy for skin lesions.

Ähnliche Arbeiten