AI powered detection and assessment of onychomycosis: A spotlight on yellow and deep learning

Abstract

Background

Despite significant advances in computer-aided diagnostics, onychomycosis, a widespread fungal nail infection, lacks an automated approach for objective analysis and classification.

Objectives

Our study aimed to develop and validate automated machine learning models to accurately detect and classify onychomycosis-affected areas in toenails.

Methods

The images in this study were captured using the Scarletred® Vision mobile App and SkinPatch, a CE certified medical device system working seamlessly together to deliver auto-color calibrated, high-resolution clinical images. Considering a total of 1687 images from 440 subjects, the research explores various degrees of onychomycosis and evaluates the infection extent in the toenails detected. We developed an advanced machine learning algorithm for precise segmentation and classification of onychomycosis-affected toenails, utilizing expert annotations and advanced post-processing techniques. Additionally, an analysis of nail growth was performed, and a comparison graph with the percentage of infection was estimated.

Results

Using advanced machine learning algorithms, we successfully detected toenails, enabling detailed analysis of intricate structures within the images. We achieved a final validation loss of 0.0236 and an F1 score of 0.8566 for accurate toenail detection, while the Random Forest algorithm demonstrated 81% accuracy in classifying and distinguishing between infected and healthy toenail areas. Our applied superpixel method furthermore improved the algorithm's precision in identifying the infected regions.

Conclusions

Our AI-powered image analysis method, initially focused on the big toe's toenail, shows great promise for broader validation on comprehensive datasets, enabling more detailed assessments of onychomycosis severity and disease dynamics. The potential impact of limited patient diversity, particularly with darker skin tones, needs further assessment. Proven to measure nail growth and assess treatment effectiveness over time, our developed AI is the first of its kind to demonstrate this capability, representing a significant advancement as a novel decision support tool for clinical research and routine medical practice.