-
Scientific Data Jun 2024Advancements in dermatological artificial intelligence research require high-quality and comprehensive datasets that mirror real-world clinical scenarios. We introduce a...
Advancements in dermatological artificial intelligence research require high-quality and comprehensive datasets that mirror real-world clinical scenarios. We introduce a collection of 18,946 dermoscopic images spanning from 2010 to 2016, collated at the Hospital Clínic in Barcelona, Spain. The BCN20000 dataset aims to address the problem of unconstrained classification of dermoscopic images of skin cancer, including lesions in hard-to-diagnose locations such as those found in nails and mucosa, large lesions which do not fit in the aperture of the dermoscopy device, and hypo-pigmented lesions. Our dataset covers eight key diagnostic categories in dermoscopy, providing a diverse range of lesions for artificial intelligence model training. Furthermore, a ninth out-of-distribution (OOD) class is also present on the test set, comprised of lesions which could not be distinctively classified as any of the others. By providing a comprehensive collection of varied images, BCN20000 helps bridge the gap between the training data for machine learning models and the day-to-day practice of medical practitioners. Additionally, we present a set of baseline classifiers based on state-of-the-art neural networks, which can be extended by other researchers for further experimentation.
Topics: Dermoscopy; Humans; Skin Neoplasms; Spain; Neural Networks, Computer; Artificial Intelligence; Machine Learning
PubMed: 38886204
DOI: 10.1038/s41597-024-03387-w -
Journal of Pharmacy & Bioallied Sciences Apr 2024Dermoscopy particularly could be helpful in patients with steroid damaged face to assess and look for the damage caused by the steroid creams as also in cases where the...
BACKGROUND AND OBJECTIVES
Dermoscopy particularly could be helpful in patients with steroid damaged face to assess and look for the damage caused by the steroid creams as also in cases where the patient provides improper history.
MATERIALS AND METHODS
Patients attending to dermatology OPD with suspected/diagnosed TSDF between the ages of 18 and 60 years were enrolled and assessed on the basis of age, gender, residence, duration, potency, brand of application topical steroid creams, clinical and dermoscopic features.
RESULTS
Majority abusing the topical steroid creams were females (n-14) with mean age with SD of 34 ± 11 and were from rural areas (57.8%). Red raised lesions were the most common clinical presentation (n-15) with telangiectasias as the most common dermoscopic feature (n-26). Triple combination creams containing hydroquinone 2%, tretinoin 0.025%, and 0.1% mometasone were on the top of the list (n-20).
CONCLUSION
In this study, the importance of dermoscopy in assessing the features of topical steroid damaged face and preventing further damage is highlighted. Various factors causing topical steroid creams misuse and the easy availability of the creams is to be kept on check.
PubMed: 38882848
DOI: 10.4103/jpbs.jpbs_1191_23 -
Skin Research and Technology : Official... Jun 2024Melanoma is one of the most malignant forms of skin cancer, with a high mortality rate in the advanced stages. Therefore, early and accurate detection of melanoma plays...
BACKGROUND
Melanoma is one of the most malignant forms of skin cancer, with a high mortality rate in the advanced stages. Therefore, early and accurate detection of melanoma plays an important role in improving patients' prognosis. Biopsy is the traditional method for melanoma diagnosis, but this method lacks reliability. Therefore, it is important to apply new methods to diagnose melanoma effectively.
AIM
This study presents a new approach to classify melanoma using deep neural networks (DNNs) with combined multiple modal imaging and genomic data, which could potentially provide more reliable diagnosis than current medical methods for melanoma.
METHOD
We built a dataset of dermoscopic images, histopathological slides and genomic profiles. We developed a custom framework composed of two widely established types of neural networks for analysing image data Convolutional Neural Networks (CNNs) and networks that can learn graph structure for analysing genomic data-Graph Neural Networks. We trained and evaluated the proposed framework on this dataset.
RESULTS
The developed multi-modal DNN achieved higher accuracy than traditional medical approaches. The mean accuracy of the proposed model was 92.5% with an area under the receiver operating characteristic curve of 0.96, suggesting that the multi-modal DNN approach can detect critical morphologic and molecular features of melanoma beyond the limitations of traditional AI and traditional machine learning approaches. The combination of cutting-edge AI may allow access to a broader range of diagnostic data, which can allow dermatologists to make more accurate decisions and refine treatment strategies. However, the application of the framework will have to be validated at a larger scale and more clinical trials need to be conducted to establish whether this novel diagnostic approach will be more effective and feasible.
Topics: Humans; Melanoma; Deep Learning; Skin Neoplasms; Dermoscopy; Neural Networks, Computer; Reproducibility of Results; Genomics; Female; Male; Middle Aged; Adult; Aged
PubMed: 38881051
DOI: 10.1111/srt.13770 -
Archives of Dermatological Research Jun 2024There are many therapeutic modalities for plantar warts, however treating it remains challenging. Intralesional injection of 5-fluorouarcil and combined digoxin and... (Randomized Controlled Trial)
Randomized Controlled Trial Comparative Study
There are many therapeutic modalities for plantar warts, however treating it remains challenging. Intralesional injection of 5-fluorouarcil and combined digoxin and furosemide were observed to be effective and safe, however no comparison study between them was done. Our study was conducted to evaluate the efficacy of both therapies in the treatment of plantar warts. 90 adult patients with multiple recalcitrant plantar warts were included in our study. They were randomly allocated to one of three groups; combined digoxin and furosemide, 5-fluorouarcil, or normal saline group. Fortnightly injections were done into all studied warts till complete clearance or up to 5 sessions. Warts were evaluated clinically and dermoscopically. Clinical response was reported in 24 patients (80%) of the combined digoxin and furosemide group with 40% complete response and in 24 patients (80%) of the 5-fluorouarcil group with 33.3% complete response. No statistically significant difference was observed between the two groups concerning efficacy and safety. Intralesional injection of 5-fluorouarcil and combined digoxin and furosemide are nearly equivalent in efficacy and safety for plantar wart treatment. Dermoscopy helps to take the truthful judgment about complete clearance of warts.
Topics: Humans; Furosemide; Male; Female; Adult; Warts; Digoxin; Injections, Intralesional; Treatment Outcome; Prospective Studies; Young Adult; Middle Aged; Drug Therapy, Combination; Adolescent; Dermoscopy; Flucytosine
PubMed: 38878078
DOI: 10.1007/s00403-024-03014-z -
JAAD Case Reports Jul 2024
PubMed: 38873248
DOI: 10.1016/j.jdcr.2024.04.031 -
Cureus May 2024Background Acquired palmoplantar keratodermas (PPKs) pose diagnostic and therapeutic challenges due to their varied clinical presentations and overlapping features. This...
Background Acquired palmoplantar keratodermas (PPKs) pose diagnostic and therapeutic challenges due to their varied clinical presentations and overlapping features. This study aims to elucidate diagnostic criteria; assess correlations between clinical, dermoscopic, and histopathological features; and evaluate treatment outcomes for acquired PPKs, particularly palmoplantar psoriasis. Methods A prospective, cross-sectional study will be conducted at the Department of Dermatology, Venereology, and Leprosy, Acharya Vinoba Bhave Rural Hospital (AVBRH), Wardha, Maharashtra. Patients with acquired PPKs will undergo comprehensive clinical, dermoscopic, and histopathological evaluations. Treatment outcomes for palmoplantar psoriasis will be assessed following standard therapy. Statistical analysis will include descriptive statistics, diagnostic accuracy assessments, correlation analyses, and treatment outcome evaluations. Results The study is anticipated to establish reliable diagnostic criteria for acquired PPKs, identify correlations between features, and demonstrate the effectiveness of standard therapies for palmoplantar psoriasis. The findings are expected to inform evidence-based guidelines and protocols for diagnosing and managing acquired PPKs. Conclusion This study aims to advance the understanding and management of acquired PPKs by providing insights into diagnostic accuracy, correlations between features, and treatment outcomes. The study seeks to enhance patient care and outcomes for individuals affected by acquired PPKs by improving diagnostic precision and guiding therapeutic interventions.
PubMed: 38872653
DOI: 10.7759/cureus.60262 -
JAAD International Sep 2024Dermatoscopy is a noninvasive method of examining skin lesions under high magnification, gradually replacing the need for invasive biopsies. Training is required to gain...
BACKGROUND
Dermatoscopy is a noninvasive method of examining skin lesions under high magnification, gradually replacing the need for invasive biopsies. Training is required to gain clinical competency. Gamification employs game-like elements to enhance education engagement and is an engaging means of delivering medical education. We sought to use gamification and a mobile-based platform to deliver dermatoscopy education to physicians.
METHODS
We developed SKIN@GoPRIME, an interactive smartphone platform. Thirty physician participants were randomly assigned to watch an online dermatoscopy lecture or to use SKIN@GoPRIME. Twenty-eight participants completed prelearning and postlearning quizzes and provided feedback on SKIN@GoPRIME.
RESULTS
Users of SKIN@GoPRIME demonstrated a significant 1.71-point mean score improvement ( = .0018). The group that watched the online dermatoscopy lecture had a higher 2.36-point mean score improvement ( = .00021). Both family medicine and internal medicine physicians demonstrated a significant mean score increase of 1.29 ( = .049) and 2.14 ( = .023), respectively, after using SKIN@GoPRIME. Based on feedback, 83% believed that SKIN@GoPRIME can be used to acquire the applied competencies required for their job scope.
DISCUSSION AND CONCLUSION
SKIN@GoPRIME, a novel learning tool via gamification effectively delivers dermatoscopy education, although it is not shown to be more effective than lectures. Larger studies are required to further validate the effectiveness of gamified learning techniques in dermatoscopy education. Future studies should involve the optimization of SKIN@GoPRIME to more effectively deliver dermatoscopy education.
PubMed: 38868401
DOI: 10.1016/j.jdin.2024.03.008 -
Acta Dermato-venereologica Jun 2024
Whorled Scarring Alopecia: A Rare Cutaneous Finding in Incontinentia Pigmenti or Overlooked Phenomenon? A Case Report of Incontinentia Pigmenti with Trichoscopic and Dermoscopic Findings.
Topics: Humans; Incontinentia Pigmenti; Dermoscopy; Female; Alopecia; Cicatrix; Predictive Value of Tests
PubMed: 38860626
DOI: 10.2340/actadv.v104.40270 -
Cureus May 2024Lichen planopilaris (LPP) restricted to the face is extremely rare. This case series includes five unique LPP cases that presented with a varied degree of pigmentation...
Lichen planopilaris (LPP) restricted to the face is extremely rare. This case series includes five unique LPP cases that presented with a varied degree of pigmentation and scarring alopecia restricted to the face. We herein describe the clinical characteristics, dermoscopy, and treatment of these histopathologically confirmed facial LPP cases. None of them had lesions anywhere else on the body.
PubMed: 38854167
DOI: 10.7759/cureus.59987 -
Anais Brasileiros de Dermatologia Jun 2024
PubMed: 38851896
DOI: 10.1016/j.abd.2023.01.009