The Application of Convolutional Neural Networks in Diagnosing Cutaneous Fungal Infections: A Systematic Review of Diagnostic Accuracy

Cutaneous fungal infections are prevalent worldwide, posing diagnostic challenges in clinical and laboratory settings. These infections, including tinea infections, onychomycosis, and fungal keratitis, often rely on conventional methods like potassium hydroxide (KOH) examinations, microscopy, and culture, which can be time-consuming, resource-intensive, and subject to human error. Recent advancements in artificial intelligence, particularly convolutional neural networks (CNNs), have revolutionized the field of dermatology by providing automated, accurate, and real-time diagnostic tools. This systematic review explored the application, efficacy, and diagnostic performance of CNN-based models for identifying and classifying cutaneous fungal infections.

کلیدواژه ها:

Convolutional Neural Networks ، Deep Learning ، Cutaneous Fungal Infections ، Tinea ، Onychomycosis ، Fungal Keratitis ، Image-Based Diagnosis ، Artificial Intelligence