AI Article Synopsis
- Timely recognition of malignant melanoma (MM) is crucial for reducing mortality, but traditional dermatologic methods struggle with accuracy due to variability in dermatologist experience.
- A Deep Convolutional Neural Network (DCNN) model, called iDCNN_aMSL, was developed by integrating dermoscopic images and clinical data to improve classification of atypical melanocytic skin lesions (aMSL).
- The iDCNN_aMSL outperformed both another DCNN model and dermatologists in accuracy, demonstrating its potential to assist in decision-making and reduce unnecessary excisions for aMSL management.
Article Abstract
Background: Timely recognition of malignant melanoma (MM) is challenging for dermatologists worldwide and represents the main determinant for mortality. Dermoscopic examination is influenced by dermatologists' experience and fails to achieve adequate accuracy and reproducibility in discriminating atypical nevi (AN) from early melanomas (EM).
Objective: We aimed to develop a Deep Convolutional Neural Network (DCNN) model able to support dermatologists in the classification and management of atypical melanocytic skin lesions (aMSL).
Methods: A training set (630 images), a validation set (135) and a testing set (214) were derived from the idScore dataset of 979 challenging aMSL cases in which the dermoscopic image is integrated with clinical data (age, sex, body site and diameter) and associated with histological data. A DCNN_aMSL architecture was designed and then trained on both dermoscopic images of aMSL and the clinical/anamnestic data, resulting in the integrated "iDCNN_aMSL" model. Responses of 111 dermatologists with different experience levels on both aMSL classification (intuitive diagnosis) and management decisions (no/long follow-up; short follow-up; excision/preventive excision) were compared with the DCNNs models.
Results: In the lesion classification study, the iDCNN_aMSL achieved the best accuracy, reaching an AUC = 90.3 %, SE = 86.5 % and SP = 73.6 %, compared to DCNN_aMSL (SE = 89.2 %, SP = 65.7 %) and intuitive diagnosis of dermatologists (SE = 77.0 %; SP = 61.4 %).
Conclusions: The iDCNN_aMSL proved to be the best support tool for management decisions reducing the ratio of inappropriate excision. The proposed iDCNN_aMSL model can represent a valid support for dermatologists in discriminating AN from EM with high accuracy and for medical decision making by reducing their rates of inappropriate excisions.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jdermsci.2020.11.009 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Diagnostic and Management Challenges in Interferon-γ Release Assay-Positive Patient with Sarcoid Panuveitis from a Non-Endemic Tuberculosis Region.
Ocul Immunol Inflamm
January 2025
Eye Institute, Cleveland Clinic Abu Dhabi, Abu Dhabi, United Arab Emirates.
Purpose: To report a case of biopsy-proven sarcoidosis in a patient with panuveitis and a positive interferon-gamma release assay (IGRA) from a non-endemic tuberculosis (TB) country.
Methods: Case report.
Results: A 26-year-old male from the United Arab Emirates (UAE) presented with granulomatous panuveitis characterized by mutton-fat keratic precipitates, anterior chamber and vitreous cells, and retinal vasculitis.
The assessment of point-of-care ultrasound (POCUS) in residency: the benefits of a four-year longitudinally integrated curriculum.
J Osteopath Med
January 2025
Arizona College of Osteopathic Medicine, Midwestern University, Glendale, AZ, USA.
Context: Point-of-care ultrasound (POCUS) has diverse applications across various clinical specialties, serving as an adjunct to clinical findings and as a tool for increasing the quality of patient care. Owing to its multifunctionality, a growing number of medical schools are increasingly incorporating POCUS training into their curriculum, some offering hands-on training during the first 2 years of didactics and others utilizing a longitudinal exposure model integrated into all 4 years of medical school education. Midwestern University Arizona College of Osteopathic Medicine (MWU-AZCOM) adopted a 4-year longitudinal approach to include POCUS education in 2017.
View Article and Find Full Text PDFComprehensive Non-invasive Versus Invasive Approach to Evaluate Cardiac Allograft Vasculopathy in Heart Transplantation: The CCTA-HTx Study.
Circ Cardiovasc Imaging
January 2025
Cardiovascular Center Aalst, Onze-Lieve-Vrouwziekenhuis (OLV) Clinic, Aalst, Belgium (M. Belmonte, P.P., M.M.V., M. Beles, H.O., R.S., G.E., M.S., R.D., W.H., J.V.K., J.B., M.V.).
Background: Coronary computed tomography angiography (CCTA) is emerging as a valuable tool for noninvasive surveillance of cardiac allograft vasculopathy (CAV) in patients with heart transplant (HTx). We assessed the diagnostic performance of a comprehensive CCTA-based approach compared with the invasive reference, which includes invasive coronary angiography, intravascular ultrasound, and fractional flow reserve, for detecting CAV.
Methods: This was a multicenter prospective study including 37 patients with HTx who underwent CCTA, invasive coronary angiography, intravascular ultrasound, and fractional flow reserve.
Exploring esophagogastric junction morphology and contractile integral: implications for refractory gastroesophageal reflux disease pathophysiology.
Scand J Gastroenterol
January 2025
Department of Gastroenterology and Hepatology, Zhongshan Hospital, Fudan University, Xiamen Branch, Xiamen, China.
Background: Evaluate the clinical significance of esophagogastric junction (EGJ) morphology and esophagogastric junction contractile integral (EGJ-CI) in refractory gastroesophageal reflux disease (RGERD) patients.
Methods: From June 2021 to June 2023, 144 RGERD patients underwent comprehensive evaluation, recording symptom scores, demographic data. GERD classification (NERD or RE, A-D) was based on endoscopic findings.
Innovative Integration of Robotic-Assisted Laparoscopic Telesurgery and Quantum Cryptography Communication in Urology: Clinical Application and Initial Experience.
Int J Med Robot
February 2025
Department of Urology, The Affiliated Hospital of Qingdao University, Qingdao, China.
Background: The emergence of telesurgery has received global interest, with secure network transmission identified as a crucial determinant of its success. This study aimed to evaluate the safety and viability of employing quantum cryptography communication in remote partial nephrectomy.
Methods: The surgeon operated on the patient from a distance of over 260 km using remote control of a surgical robot.
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!