Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jaad.2014.09.042 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
AI-Driven Enhancement of Skin Cancer Diagnosis: A Two-Stage Voting Ensemble Approach Using Dermoscopic Data.
Cancers (Basel)
January 2025
Department of Biomedical Sciences and Engineering, National Central University, Taoyuan 320, Taiwan.
Background: Skin cancer is the most common cancer worldwide, with melanoma being the deadliest type, though it accounts for less than 5% of cases. Traditional skin cancer detection methods are effective but are often costly and time-consuming. Recent advances in artificial intelligence have improved skin cancer diagnosis by helping dermatologists identify suspicious lesions.
View Article and Find Full Text PDFDeep Learning for Melanoma Detection: A Deep Learning Approach to Differentiating Malignant Melanoma from Benign Melanocytic Nevi.
Cancers (Basel)
December 2024
65+ Outpatient Clinic, Amalia Fleming General Hospital, 14, 25th Martiou Str., 15127 Melissia, Greece.
: Melanoma, an aggressive form of skin cancer, accounts for a significant proportion of skin-cancer-related deaths worldwide. Early and accurate differentiation between melanoma and benign melanocytic nevi is critical for improving survival rates but remains challenging because of diagnostic variability. Convolutional neural networks (CNNs) have shown promise in automating melanoma detection with accuracy comparable to expert dermatologists.
View Article and Find Full Text PDFDermoscopy of Scabies: Utility of Polarised and Ultraviolet-Induced Fluorescence Examination in Fair and Dark Skin.
Australas J Dermatol
December 2024
Department of Medical Area, Institute of Dermatology, University of Udine, Udine, Italy.
Introduction: Ultraviolet-based dermoscopy may support the recognition of scabies, yet neither accuracy analyses nor data on skin of colour are available. The aim of this multicentric observational retrospective was to investigate the diagnostic accuracy of polarised and ultraviolet-induced fluorescence (UVF) dermoscopic examination in both fair and dark skin, also assessing possible differences according to the skin tone.
Methods: Consecutive patients with a diagnosis of scabies were eligible.
Macro vs Micro Skin Imaging: Finding an Affordable Approach for Dermatological Care Access in Rural/Remote Areas.
Stud Health Technol Inform
November 2024
University Politehnica Timişoara, Romania.
The present study explored alternative methods for photographing skin lesions in the absence of specialized instruments like dermatoscopes, aiming to enhance remote diagnostic capabilities, particularly in light of the increasing incidence of melanoma cases annually. Using two lenses attached to a smartphone camera, one macroscopic and the other microscopic, study images of nevus formations from one individual were captured, and, in the absence of a collaboration with a dermatologist, subsequently labeled as melanoma or non-melanoma using a Convolutional Neural Network (CNN) which was trained, with dermoscopic images of melanoma and non-melanoma formations, to see on which image set better performances would be attained. The CNN demonstrated better performance on microscopic images, with 75% of the dataset being labeled correctly, compared to the macroscopic one, with 63% of the dataset being labeled correctly.
View Article and Find Full Text PDFDeep Learning With Optical Coherence Tomography for Melanoma Identification and Risk Prediction.
J Biophotonics
January 2025
Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei, Taiwan.
Article Synopsis
- Malignant melanoma is a serious skin cancer that is becoming more common, prompting the need for effective early detection methods.
- Previous studies mostly focused on dermoscopic images, but this research uses a convolutional neural network (CNN) to analyze optical coherence tomography (OCT) images of mouse skin for better melanoma identification.
- The CNN shows impressive accuracy with a sensitivity of 0.99 and specificity of 0.98, providing a risk score for melanoma presence that could help improve early diagnosis and treatment in clinical practices.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!