CNN-Based AI Versus Physicians for Solitary Skin Lesion Diagnosis

Overview

The goal of this observational study is to evaluate the diagnostic accuracy of a CNN-based artificial intelligence model in patients with solitary skin lesions. The main questions it aims to answer are: * What is the diagnostic performance (sensitivity and specificity) of the CNN-based model in identifying solitary skin lesions using macroscopic clinical images? * How does the diagnostic accuracy of the CNN-based model compare with the evaluations performed by dermatologists and non-dermatologist physicians? Researchers will compare the AI model's diagnostic outputs to the independent evaluations of dermatologists and non-dermatologist physicians to see if the AI model can achieve a diagnostic performance comparable to or better than human clinicians. Participants (physicians acting as clinical readers) will: * Independently review a predefined set of anonymized macroscopic clinical images sourced from a retrospective patient archive. * Provide a primary diagnosis for each lesion based solely on the images, without access to patient history or histopathological results. * Submit their assessments to be compared against the gold standard (histopathological diagnosis) and the AI model's results.

This study is a retrospective, observational diagnostic accuracy study designed to evaluate the performance of a convolutional neural network (CNN)-based artificial intelligence model in the assessment of solitary skin lesions using macroscopic clinical images. Macroscopic clinical images of solitary skin lesions with histopathological or clinically confirmed diagnoses will be retrospectively retrieved from the dermatology image archive of Istanbul Training and Research Hospital. All images and associated clinical documents will be anonymized prior to analysis, and any identifying visual or textual information will be removed. Data processing and analysis will be conducted in a secure, institution-based environment with restricted access limited to the study team. A CNN-based artificial intelligence model will be developed using supervised learning techniques. Image preprocessing steps will include resizing to standardized input dimensions, color normalization, and removal of regions containing potentially identifiable information. The dataset will be partitioned into training, validation, and test subsets to enable model development, hyperparameter optimization, and independent performance evaluation. Model training and evaluation will be implemented using the PyTorch deep learning framework. The diagnostic performance of the CNN-based model will be evaluated using standard classification metrics and will be compared with the independent assessments of dermatologists, dermatology residents, and non-dermatologist physicians who evaluate the same set of anonymized images without access to additional clinical or histopathological information. Comparative analyses will be performed to assess differences in diagnostic performance and agreement between the artificial intelligence model and physician groups.