Development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with Mohs micrographic surgery.

Background: Real-time review of frozen sections underpins the quality of Mohs surgery. There is an unmet need for low-cost techniques that can improve Mohs surgery by reliably corroborating cancerous regions of interest and surgical margin proximity. Objective: To test that deep learning models can identify nonmelanoma skin cancer regions in Mohs frozen section specimens. Methods: Deep learning models were developed on archival images of focused microscopic views (FMVs) containing regions of annotated, invasive nonmelanoma skin cancer between 2015 and 2018, then validated on prospectively collected images in a temporal cohort (2019-2021). Results: The tile-based classification models were derived using 1423 focused microscopic view images from 154 patients and tested on 374 images from 66 patients. The best models detected basal cell carcinomas with a median average precision of 0.966 and median area under the receiver operating curve of 0.889 at 100x magnification (0.943 and 0.922 at 40x magnification). For invasive squamous cell carcinomas, high median average precision of 0.904 was achieved at 100x magnification. Limitations: Single institution study with limited cases of squamous cell carcinoma and rare nonmelanoma skin cancer. Conclusion: Deep learning appears highly accurate for detecting skin cancers in Mohs frozen sections, supporting its potential for enhancing surgical margin control and increasing operational efficiency.

Optimisation of skin phototype classification.

Understanding individuals' skin pigmentation and photosensitivity is important in judging risk of skin cancer and response to certain treatment modalities. However, individuals with darkly pigmented skin are poorly represented in the widely used Fitzpatrick skin phototype (FST) system. Moreover, the FST system is prone to misuse, as it relies on subjective patient and clinician assessment of skin type, and does not clearly differentiate pigmentation from photosensitivity. By evaluating the key literature surrounding the FST system, its criticisms and proposed alternatives, this review serves to understand how skin phototype classification can be optimised.

Reflectance Confocal Microscopy in the Diagnosis of Onychomycosis: A Systematic Review.

Accurately diagnosing onychomycosis is vital, as therapy is time-consuming and accompanied by multiple adverse effects. Reflectance confocal microscopy (RCM), in contrast to traditional mycological testing, is a noninvasive, point-of-care tool that can rapidly identify fungal lesions. This systematic review aims to understand the utility of RCM in evaluating onychomycosis and follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. A systematic search of four databases was conducted. A total of five articles-three prospective cohort studies and two case reports-which reported RCM findings in nails clinically suspicious for onychomycosis were analyzed. Fungal hyphae or spores were visualized on RCM in 67 (81.7%) of the 82 mycologically confirmed cases of onychomycosis. Terms used to describe hyphae included bright, linear, lengthy, thready-like, branching and filamentous. Spores were described as bright, roundish structures with high reflection. The three cohort studies demonstrated RCM had a sensitivity of 52.9-91.7, a specificity of 57.58-90.2%, a positive predictive value of 61.1-88.6% and a negative predictive value of 68.0-90.5%. In conclusion, existing studies demonstrate how RCM can assist the diagnosis of onychomycosis at the bedside. Larger studies incorporating multiple testing modalities to confirm the diagnosis of onychomycosis are warranted to further explore the diagnostic utility of RCM.

Diagnostic accuracy of dermoscopy for onychomycosis: A systematic review.

Background: Dermoscopy is a non-invasive adjuvant diagnostic tool that allows clinicians to visualize microscopic features of cutaneous disorders. Recent studies have demonstrated that dermoscopy can be used to diagnose onychomycosis. We performed this systematic review to identify the characteristic dermoscopic features of onychomycosis and understand their diagnostic utility. Methods: We searched the Medline, Embase, Scopus, and Cochrane databases from conception until May 2021. Studies on the dermoscopic features of onychomycosis were screened. The exclusion criteria were as follows: fewer than 5 cases of onychomycosis, review articles, and studies including onychomycosis cases that were not mycologically verified. Studies on fungal melanonychia were analyzed separately. We adhered to the MOOSE guidelines. Independent data extraction was performed. Data were pooled using a random effects model to account for study heterogeneity. The primary outcome was the diagnostic accuracy of the dermoscopic features of onychomycosis. This was determined by pooling the sensitivity and specificity values of the dermoscopic features identified during the systematic review using the DerSimonian-Laird method. Meta-DiSc version 1.4 and Review Manager 5.4.1 were used to calculate these values. Results: We analyzed 19 articles on 1693 cases of onychomycosis and 5 articles on 148 cases of fungal melanonychia. Commonly reported dermoscopic features of onychomycosis were spikes or spiked pattern (509, 30.1%), jagged or spiked edges or jagged edge with spikes (188, 11.1%), jagged proximal edge (175, 10.3%), subungual hyperkeratosis (131, 7.7%), ruins appearance, aspect or pattern (573, 33.8%), and longitudinal striae (929, 54.9%). Commonly reported features of fungal melanonychia included multicolor (101, 68.2%), non-longitudinal homogenous pigmentation (75, 50.7%) and longitudinal white or yellow streaks (52, 31.5%). Conclusion: This study highlights the commonly identified dermoscopic features of onychomycosis. Recognizing such characteristic dermoscopic features of onychomycosis can assist clinicians diagnose onychomycosis by the bedside.

Oxygen mediated oxidative couplings of flavones in alkaline water.

Catalyzed oxidative C-C bond coupling reactions play an important role in the chemical synthesis of complex natural products of medicinal importance. However, the poor functional group tolerance renders them unfit for the synthesis of naturally occurring polyphenolic flavones. We find that molecular oxygen in alkaline water acts as a hydrogen atom acceptor and oxidant in catalyst-free (without added catalyst) oxidative coupling of luteolin and other flavones. By this facile method, we achieve the synthesis of a small collection of flavone dimers and trimers including naturally occurring dicranolomin, philonotisflavone, dehydrohegoflavone, distichumtriluteolin, and cyclodistichumtriluteolin. Mechanistic studies using both experimental and computational chemistry uncover the underlying reasons for optimal pH, oxygen availability, and counter-cations that define the success of the reaction. We expect our reaction opens up a green and sustainable way to synthesize flavonoid dimers and oligomers using the readily available monomeric flavonoids isolated from biomass and exploiting their use for health care products and treatment of diseases.

Structure and Anti-Inflammatory Activity Relationship of Ergostanes and Lanostanes in Antrodia cinnamomea.

Antrodia cinnamomea is a precious edible mushroom originating from Taiwan that has been popularly used for adjuvant hepatoprotection and anti-inflammation; however, the chemical principle for its anti-inflammatory activity has not been elucidated, which prevents the quality control of related products. Using the RAW264.7 model for the anti-inflammatory activity assay as a guide, we reported the isolation and structural elucidation of three potent anti-inflammatory compounds from isolated ergostanes (16) and lanostanes (6). Their structures were elucidated on the basis of spectroscopic data analysis including NMR and HR-QTOF-MS. Particularly, the absolute configurations of (25R)-antcin K, (25R)-antcin A, versisponic acid D, and (25R)-antcin C were determined by single crystal X-ray diffraction (XRD). The representative and most promising compound antcin A was shown to suppress pro-inflammatory biomolecule release via the down-regulation of iNOS and COX-2 expression through the NF-κB pathway while the mRNA levels of IL-1ß, TNF-α and IL-6 were also decreased. The high dependency on structural variation and activity suggests that there might be special biological targets for antcin A. Our work makes it possible to develop evidence-based dietary supplements from Antrodia cinnamomea based on anti-inflammatory constituents.

Non-radiologist perception of the use of artificial intelligence (AI) in diagnostic medical imaging reports.

INTRODUCTION: Incorporating artificial intelligence (AI) in diagnostic medical imaging reports has the potential to improve efficiency. Although perception of radiologists, radiographers, medical students and patients on AI use in image reporting has been explored, there is limited literature on non-radiologist clinicians' opinion on this topic. METHOD: Single-centre online survey targeting non-radiologist medical staff conducted from May to August 2021 at a tertiary referral hospital in Melbourne, Australia. Survey questions revolved around clinicians' level of comfort acting on AI-generated reports with varying levels of radiologist involvement and scan complexity, opinion on medicolegal responsibility for erroneous AI-issued reports and perception of data privacy and security. RESULTS: Eighty-eight responses were collected, including 47.9% of consultants. Non-radiologist clinicians across all seniorities and specialties felt significantly less comfortable acting on AI-issued reports compared with radiologist-issued reports (mean comfort radiologist 6.44/7, mean comfort AI 3.35/7, P < 0.001) but felt equally comfortable with an AI-hybrid model of care (mean comfort hybrid 6.38/7, P = 0.676). Non-radiologist clinicians believed that medicolegal responsibility with errors in AI-issued reports mostly lay with hospitals or health service providers (65.9%) and radiologists (54.5%). Regarding data privacy and security, non-radiologist clinicians felt significantly less comfortable with AI issuing image reports instead of radiologists (P < 0.001). CONCLUSION: A hybrid AI-generated radiologist-confirmed method of image reporting may be the ideal way of integrating AI into clinical practice based on the perception of our referring non-radiologist medical colleagues. Formal guidelines on medicolegal responsibility and data privacy should be established prior to utilising AI in the clinical setting.

Dermoscopy for cutaneous fungal infections: A brief review.

BACKGROUND: Fungal dermatological diseases are significant public health issues. Dermoscopy is a useful bedside assessment tool that helps clinicians diagnose various skin neoplasms and general dermatological diseases. AIM: This brief review aims to update clinicians on the dermoscopic features of cutaneous fungal infections such as tinea capitis, tinea corporis, tinea incognito, onychomycosis, and pityrosporum folliculitis. METHODS: The PubMed database was searched using the terms "dermoscopy" or its synonyms, "tinea capitis", "tinea corporis", "tinea incognito", "onychomycosis" and "pityrosporum folliculitis". RESULTS: The diagnostic value of dermoscopy is well-recognised in the evaluation of tinea capitis and onychomycosis. There are fewer studies investigating the dermoscopic features of tinea corporis, tinea incognito and pityrosporum folliculitis, but the current data suggest that dermoscopy can aid clinical evaluation of these diseases. Understanding dermoscopic features of cutaneous fungal infection has the potential to increase diagnostic accuracy. CONCLUSION: Dermoscopy in the evaluation of fungal dermatological diseases has the potential to optimize diagnostic accuracy, reduce unnecessary testing, and, consequently, improve clinical practice.

Dermoscopic Evaluation of Inflammatory Nail Disorders and Their Mimics.

Nail dermoscopy (onychoscopy) is a valuable diagnostic tool for evaluating diseases in the nail apparatus. It is non-invasive, allowing clinicians to prioritize particular nails for biopsy. Thus, it can improve diagnostic accuracy and expedite treatment. Evaluating inflammatory nail disorders using onychoscopy is a relatively new approach to clinical assessment and has the potential to augment clinical care. This review highlights key dermoscopic features of major inflammatory nail disorders, including trachyonychia, nail psoriasis, nail lichen planus, onychotillomania, nail lichen striatus and allergic contact dermatitis due to artificial nails. It also illustrates their management and differential diagnoses, including onychomycosis, onycholysis, nail dystrophy due to systemic amyloidosis and malignant nail tumours. Limitations of this review included the low amount of literature on this topic and non-standardized terminology used among research-ers. As onychoscopy is a relatively new technique, further studies and standardization of terminology are warranted to consolidate the role of dermoscopy in evaluating inflammatory nail disorders.

The Impact of SARS-CoV-2 (COVID-19) Pandemic on International Dermatology Conferences in 2020.

To limit the spread of the SARS-CoV-2 (COVID-19) outbreak, humans have been significantly restricted in their ability to travel and interact with others worldwide. Consequently, dermatology conferences were forced to adapt to such changes. The aim of this study is to investigate the impact of COVID-19 on international dermatology conferences. We retrospectively investigated decisions made for international dermatology conferences scheduled for 2020. Thirty-three major conferences were analyzed. Their data were obtained from their respective websites (data was accessed 2 June 2021). Among 33 conferences analyzed, 13 (39.4%) were conducted as scheduled, nine (27.3%) were canceled, eight (24.3%) were postponed to 2021 or 2022, and three (9.1%) were delayed but conducted in 2020. The number of the cancellation (44.4%) and postponement (75%) was the largest in the second quarter of the year. During the fourth quarter, most conferences were held on schedule (70%) but were run virtually. Eight out of 13 virtual conferences shortened their duration (61.5%). Most (90.9%) conferences have decided on the schedule of their meetings for 2021 or 2022 while three (9.1%) remain undecided. Twelve (40%) are planned to run virtually, eight (26.7%) have opted for a hybrid form, five (16.7%) are planned to run in-person, four (13.3%) have not decided on the format, and one (3.3%) has been canceled. Virtual and hybrid conference formats have facilitated people to share knowledge despite the travel restrictions posed by the COVID-19 pandemic. Such formats are environmentally friendly, are able to attract a large audience, and save delegates time and costs involved in attending. Therefore, virtual platforms should continue to be integrated within conferences in the post-pandemic era.

Diagnosis of Onychomycosis: From Conventional Techniques and Dermoscopy to Artificial Intelligence.

Onychomycosis is a common fungal nail infection. Accurate diagnosis is critical as onychomycosis is transmissible between humans and impacts patients' quality of life. Combining clinical examination with mycological testing ensures accurate diagnosis. Conventional diagnostic techniques, including potassium hydroxide testing, fungal culture and histopathology of nail clippings, detect fungal species within nails. New diagnostic tools have been developed recently which either improve detection of onychomycosis clinically, including dermoscopy, reflectance confocal microscopy and artificial intelligence, or mycologically, such as molecular assays. Dermoscopy is cost-effective and non-invasive, allowing clinicians to discern microscopic features of onychomycosis and fungal melanonychia. Reflectance confocal microscopy enables clinicians to observe bright filamentous septate hyphae at near histologic resolution by the bedside. Artificial intelligence may prompt patients to seek further assessment for nails that are suspicious for onychomycosis. This review evaluates the current landscape of diagnostic techniques for onychomycosis.

Histopathologic findings of idiopathic trachyonychia: An analysis of 30 adult patients.

BACKGROUND: Trachyonychia, a rare inflammatory disease of the nail matrix, has a more chronic course in adults compared with that in children. However, the histopathologic features of the disease have not been sufficiently reported in the literature. METHODS: We retrospectively reviewed the pathologic features of idiopathic trachyonychia in adult cases at our center. RESULTS: A total of 30 cases were included. The median age was 55.5 years (range, 27-77 years). Median disease duration was 84 months (range, 8-384 months). Histopathologic analysis showed upper dermal lymphocytic infiltrates (93.3%), acanthosis (86.7%), exocytosis (63.3%), spongiosis (63.3%), parakeratosis (46.7%), psoriasiform hyperplasia (40%), eosinophilic infiltrates (33.3%), vacuolar degeneration (33.3%), lichenoid pattern (13.3%), Civatte body (6.7%), and collection of neutrophils in the stratum corneum (3.3%). Statistical analysis among pathologic parameters revealed associations of spongiosis with exocytosis (P < 0.001) and lichenoid infiltration with vacuolar degeneration (P = 0.008). Three patients (10%) showed fungal co-infection. CONCLUSION: The majority of cases revealed inflammatory cell infiltration with epidermal changes. Given the inflammation and chronic course of idiopathic trachyonychia in adulthood, active treatment with anti-inflammatory agents should be considered. Additionally, mycological tests should be considered during initial evaluation as there are cases with fungal coinfection.

Acral lentiginous melanoma in situ: dermoscopic features and management strategy.

Diagnosis of acral lentiginous melanoma in situ (ALMIS) is challenging. However, data regarding ALMIS are limited in the literature. The aim of this study was to investigate the clinical and dermoscopic features of ALMIS on palmoplantar surfaces. Patients with ALMIS and available dermoscopic images were retrospectively reviewed at our institution between January 2013 and February 2020. Clinical and dermoscopic features were analysed and compared between small (< 15 mm) and large (≥ 15 mm) ALMIS. Twenty-one patients with ALMIS were included in this study. Mean patient age was 58.5 (range 39-76) years; most lesions were located on the sole (90.5%). The mean maximal diameter was 19.9 ± 13.7 mm (mean ± standard deviation). Statistical analysis of dermoscopic features revealed that parallel ridge patterns (54.5% vs. 100%, P = 0.035), irregular diffuse pigmentation (27.3% vs. 100%, P = 0.001) and grey colour (18.2% vs. 90%, P = 0.002) were significantly less frequent in small lesions than in large lesions. We have also illustrated two unique cases of small ALMIS; their evolution and follow-up dermoscopic examination are provided. In conclusion, this study described detailed dermoscopic findings of ALMIS. Based on the present study and a review of the literature, we proposed a dermoscopic algorithm for the diagnosis of ALMIS.