Comparative Analysis of AI Models for Atypical Pigmented Facial Lesion Diagnosis.

Abstract

Diagnosing atypical pigmented facial lesions (aPFLs) is a challenging topic for dermatologists. Accurate diagnosis of these lesions is crucial for effective patient management, especially in dermatology, where visual assessment plays a central role. Incorrect diagnoses can result in mismanagement, delays in appropriate interventions, and potential harm. AI, however, holds the potential to enhance diagnostic accuracy and provide reliable support to clinicians. This work aimed to evaluate and compare the effectiveness of machine learning (logistic regression of lesion features and patient metadata) and deep learning (CNN analysis of images) models in dermoscopy diagnosis and the management of aPFLs. This study involved the analysis of 1197 dermoscopic images of facial lesions excised due to suspicious and histologically confirmed malignancy, classified into seven classes (lentigo maligna-LM; lentigo maligna melanoma-LMM; atypical nevi-AN; pigmented actinic keratosis-PAK; solar lentigo-SL; seborrheic keratosis-SK; and seborrheic lichenoid keratosis-SLK). Image samples were collected through the Integrated Dermoscopy Score (iDScore) project. The statistical analysis of the dataset shows that the patients mean age was 65.5 ± 14.2, and the gender was equally distributed (580 males-48.5%; 617 females-51.5%). A total of 41.7% of the sample constituted malignant lesions (LM and LMM). Meanwhile, the benign lesions were mainly PAK (19.3%), followed by SL (22.2%), AN (10.4%), SK (4.0%), and SLK (2.3%). The lesions were mainly localised in the cheek and nose areas. A stratified analysis of the assessment provided by the enrolled dermatologists was also performed, resulting in 2445 evaluations of the 1197 images (2.1 evaluations per image on average). The physicians demonstrated higher accuracy in differentiating between malignant and benign lesions (71.2%) than in distinguishing between the seven specific diagnoses across all the images (42.9%). The logistic regression model obtained a precision of 39.1%, a sensitivity of 100%, a specificity of 33.9%, and an accuracy of 53.6% on the test set, while the CNN model showed lower sensitivity (58.2%) and higher precision (47.0%), specificity (90.8%), and accuracy (59.5%) for melanoma diagnosis. This research demonstrates how AI can enhance the diagnostic accuracy in complex dermatological cases like aPFLs by integrating AI models with clinical data and evaluating different diagnostic approaches, paving the way for more precise and scalable AI applications in dermatology, showing their critical role in improving patient management and the outcomes in dermatology.