Deep Convolutional Neural Networks for Onychomycosis Detection using Microscopic Images with KOH Examination

Artificial Intelligence in the Diagnosis of Onychomycosis-Literature Review

Onychomycosis is a common fungal nail infection that is difficult to diagnose due to its similarity to other nail conditions. Accurate identification is essential for effective treatment. The current gold standard methods include microscopic examination with potassium hydroxide, fungal cultures, and Periodic acid-Schiff biopsy staining. These conventional techniques, however, suffer from high turnover times, variable sensitivity, reliance on human interpretation, and costs. This study examines the potential of integrating AI (artificial intelligence) with visualization tools like dermoscopy and microscopy to improve the accuracy and efficiency of onychomycosis diagnosis. AI algorithms can further improve the interpretation of these images. The review includes 14 studies from PubMed and IEEE databases published between 2010 and 2024, involving clinical and dermoscopic pictures, histopathology slides, and KOH microscopic images. Data extracted include study type, sample size, image assessment model, AI algorithms, test performance, and comparison with clinical diagnostics. Most studies show that AI models achieve an accuracy comparable to or better than clinicians, suggesting a promising role for AI in diagnosing onychomycosis. Nevertheless, the niche nature of the topic indicates a need for further research.

Novel B-DNA dermatophyte assay for demonstration of canonical DNA in dermatophytes: Histopathologic characterization by artificial intelligence

We describe a novel assay and artificial intelligence-driven histopathologic approach identifying dermatophytes in human skin tissue sections (ie, B-DNA dermatophyte assay) and demonstrate, for the first time, the presence of dermatophytes in tissue using immunohistochemistry to detect canonical right-handed double-stranded (ds) B-DNA. Immunohistochemistry was performed using anti-ds-B-DNA monoclonal antibodies with formalin-fixed paraffin-embedded tissues to determine the presence of dermatophytes. The B-DNA assay resulted in a more accurate identification of dermatophytes, nuclear morphology, dimensions, and gene expression of dermatophytes (ie, optical density values) than periodic acid-Schiff (PAS), Grocott methenamine silver (GMS), or hematoxylin and eosin (H&E) stains. The novel assay guided by artificial intelligence allowed for efficient identification of different types of dermatophytes (eg, hyphae, microconidia, macroconidia, and arthroconidia). Using the B-DNA dermatophyte assay as a clinical tool for diagnosing dermatophytes is an alternative to PAS, GMS, and H&E as a fast and inexpensive way to accurately detect dermatophytosis and reduce the number of false negatives. Our assay resulted in superior identification, sensitivity, life cycle stages, and morphology compared to H&E, PAS, and GMS stains. This method detects a specific structural marker (ie, ds-B-DNA), which can assist with diagnosis of dermatophytes. It represents a significant advantage over methods currently in use.

A comprehensive review of nondermatophyte mould onychomycosis: Epidemiology, diagnosis and management

Nondermatophyte moulds (NDMs) are widely distributed and can be detected in association with mycotic nails; however, sometimes it can be challenging to establish the role of NDMs in the pathogenesis of onychomycosis (i.e. causative vs. contaminant). In studies where the ongoing invasive presence of NDMs is confirmed through repeat cultures, the global prevalence of NDMs in onychomycosis patients is estimated at 6.9% with the 3 most common genus being: Aspergillus, Scopulariopsis and Fusarium. NDM onychomycosis can, in many cases, appear clinically indistinguishable from dermatophyte onychomycosis. Clinical features suggestive of NDMs include proximal subungual onychomycosis with paronychia associated with Aspergillus spp., Fusarium spp. and Scopulariopsis brevicaulis, as well as superficial white onychomycosis in a deep and diffused pattern associated with Aspergillus and Fusarium. Longitudinal streaks seen in patients with distal and lateral onychomycosis may serve as an additional indicator. For diagnosis, light microscopic examination should demonstrate fungal filaments consistent with an NDM with at least two independent isolations in the absence of a dermatophyte; the advent of molecular testing combined with histological assessment may serve as an alternative with improved sensitivity and turnover time. In most instances, antifungal susceptibility testing has limited value. Information on effective treatments for NDM onychomycosis is relatively scarce, unlike the situation in the study of dermatophyte onychomycosis. Terbinafine and itraconazole therapy (continuous and pulsed) appear effective to varying extents for treating onychomycosis caused by Aspergillus, Fusarium or Scopulariopsis. There is scant literature on oral treatments for Neoscytalidium.

Emerging Trends and Focus in Human Skin Microbiome Over the Last Decade: A Bibliometric Analysis and Literature Review

Background

Human skin microbiome is the first barrier against exogenous attack and is associated with various skin disease pathogenesis and progression. Advancements in high-throughput sequencing technologies have paved the way for a deeper understanding of this field. Based on the bibliometric analysis, this investigation aimed to identify the hotspots and future research trends associated with human skin microbiomes studied over the past decade.

Methods

The published research on skin microbiome from January 2013 to January 2023 was retrieved from the Web of Science Core Collection. Data cleaning processes to ensure robust data and the bibliometrix packages R, CiteSpace, VOSviewer, Origin, and Scimago Graphica for bibliometric and visual analyses were utilized.

Results

A total of 1629 published documents were analyzed. The overall publication trend steadily increased, with relatively fast growth in 2017 and 2020. The United States of America has the highest number of publications and citations and shows close collaborations with China and Germany. The University of California, San Diego, indicated a higher number of publications than other institutions and the fastest growth rate. The top three most publishing journals on this topic are Microorganisms, Frontiers in Microbiology, and Experimental dermatology. Gallo RL is the most influential author with the highest h- and g-index and most publications in skin microecology, followed by Grice EA and Kong HH. The top 10 most frequently used keywords in recent years included skin microbiome, microbiome, staphylococcus aureus, diversity, atopic dermatitis, skin, bacteria, infections, gut microbiota, and disease.

Conclusion

The skin microbiome is an area of research that requires continuous analysis, and even with much-achieved progress, future research will further be aided as technology develops.

Artificial Intelligence in microbiomes analysis: A review of applications in dermatology

Microorganisms are closely related to skin diseases, and microbiological imbalances or invasions of exogenous pathogens can be a source of various skin diseases. The development and prognosis of such skin diseases are also closely related to the type and composition ratio of microorganisms present. Therefore, through detection of the characteristics and changes in microorganisms, the possibility for diagnosis and prediction of skin diseases can be markedly improved. The abundance of microorganisms and an understanding of the vast amount of biological information associated with these microorganisms has been a formidable task. However, with advances in large-scale sequencing, artificial intelligence (AI)-related machine learning can serve as a means to analyze large-scales of data related to microorganisms along with determinations regarding the type and status of diseases. In this review, we describe some uses of this exciting, new emerging field. In specific, we described the recognition of fungi with convolutional neural networks (CNN), the combined application of microbial genome sequencing and machine learning and applications of AI in the diagnosis of skin diseases as related to the gut-skin axis.

Strategies to improve the diagnosis and clinical treatment of dermatophyte infections

INTRODUCTION

Significant problems are associated with the diagnosis and treatment of dermatophyte infections, which constitute the most common fungal infections of the skin. Although this is a common problem in the community, there are no adequate guidelines for the management of all forms of dermatophyte infections. Even if dermatophytes are correctly diagnosed, they sometimes exhibit poor susceptibility to several antifungal compounds. Therefore, long-term treatment may be needed, especially in immunosuppressed patients, for whom antifungal pharmacotherapy may be inconvenient owing to allergies and undesirable drug interaction-related effects.

AREAS COVERED

In this review article, problems related to the diagnosis and treatment of dermatophyte infections have been discussed, and suggestions to resolve these problems have been presented.

EXPERT OPINION

Pretreatment microscopic or mycological examinations should be performed for dermatophyte infections. In treatment-refractory cases, antifungal-resistant strains should be determined using antifungal susceptibility testing or via molecular methods. Natural herbal, laser, and photodynamic treatments can be used as alternative treatments in patients who cannot tolerate topical and systemic antifungal treatments.

MobileSkin: Classification of Skin Lesion Images Acquired Using Mobile Phone-Attached Hand-Held Dermoscopes

Dermoscopy is the visual examination of the skin under a polarized or non-polarized light source. By using dermoscopic equipment, many lesion patterns that are invisible under visible light can be clearly distinguished. Thus, more accurate decisions can be made regarding the treatment of skin lesions. The use of images collected from a dermoscope has both increased the performance of human examiners and allowed the development of deep learning models. The availability of large-scale dermoscopic datasets has allowed the development of deep learning models that can classify skin lesions with high accuracy. However, most dermoscopic datasets contain images that were collected from digital dermoscopic devices, as these devices are frequently used for clinical examination. However, dermatologists also often use non-digital hand-held (optomechanical) dermoscopes. This study presents a dataset consisting of dermoscopic images taken using a mobile phone-attached hand-held dermoscope. Four deep learning models based on the MobileNetV1, MobileNetV2, NASNetMobile, and Xception architectures have been developed to classify eight different lesion types using this dataset. The number of images in the dataset was increased with different data augmentation methods. The models were initialized with weights that were pre-trained on the ImageNet dataset, and then they were further fine-tuned using the presented dataset. The most successful models on the unseen test data, MobileNetV2 and Xception, had performances of 89.18% and 89.64%. The results were evaluated with the 5-fold cross-validation method and compared. Our method allows for automated examination of dermoscopic images taken with mobile phone-attached hand-held dermoscopes.