IMPORTANCE A high proportion of suspicious pigmented skin lesions referred for investigation are benign. Techniques to improve the accuracy of melanoma diagnoses throughout the patient pathway are needed to reduce the pressure on secondary care and pathology services. OBJECTIVE To determine the accuracy of an artificial intelligence algorithm in identifying melanoma in dermoscopic images of lesions taken with smartphone and digital single-lens reflex (DSLR) cameras. DESIGN, SETTING, AND PARTICIPANTS This prospective, multicenter, single-arm, masked diagnostic trial took place in dermatology and plastic surgery clinics in 7 UK hospitals. Dermoscopic images of suspicious and control skin lesions from 514 patients with at least 1 suspicious pigmented skin lesion scheduled for biopsy were captured on 3 different cameras. Data were collected from January 2017 to July 2018. Clinicians and the Deep Ensemble for Recognition of Malignancy, a deterministic artificial intelligence algorithm trained to identify melanoma in dermoscopic images of pigmented skin lesions using deep learning techniques, assessed the likelihood of melanoma. Initial data analysis was conducted in September 2018; further analysis was conducted from February 2019 to August 2019. INTERVENTIONS Clinician and algorithmic assessment of melanoma.MAIN OUTCOMES AND MEASURES Area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of the algorithmic and specialist assessment, determined using histopathology diagnosis as the criterion standard. RESULTSThe study population of 514 patients included 279 women (55.7%) and 484 white patients (96.8%), with a mean (SD) age of 52.1 (18.6) years. A total of 1550 images of skin lesions were included in the analysis (551 [35.6%] biopsied lesions; 999 [64.4%] control lesions); 286 images (18.6%) were used to train the algorithm, and a further 849 (54.8%) images were missing or unsuitable for analysis. Of the biopsied lesions that were assessed by the algorithm and specialists, 125 (22.7%) were diagnosed as melanoma. Of these, 77 (16.7%) were used for the primary analysis.The algorithm achieved an AUROC of 90.1% (95% CI, 86.3%-94.0%) for biopsied lesions and 95.8% (95% CI, 94.1%-97.6%) for all lesions using iPhone 6s images; an AUROC of 85.8% (95% CI, 81.0%-90.7%) for biopsied lesions and 93.8% (95% CI, 91.4%-96.2%) for all lesions using Galaxy S6 images; and an AUROC of 86.9% (95% CI, 80.8%-93.0%) for biopsied lesions and 91.8% (95% CI, 87.5%-96.1%) for all lesions using DSLR camera images. At 100% sensitivity, the algorithm achieved (continued) Key Points Question How accurate is an artificial intelligence-based melanoma detection algorithm, which analyzes dermoscopic images taken by smartphone and digital single-lens reflex cameras, compared with clinical assessment and histopathological diagnosis? Findings In this diagnostic study, 1550 images of suspicious and benign skin lesions were analyzed by an artificial intelligence algorithm. When compared with histopathological diagnosis, ...
This set of guidelines has been developed using the BAD's recommended methodology 1 (Appendix J; see Supporting Information) with reference to the AGREE II instrument 2 and GRADE. 3 Recommendations were developed for implementation in the UK National Health Service (NHS).
The rash in PEP typically begins in the abdominal striae with sparing of the umbilicus. Spreading to the trunk and extremities may occur over a period of days but the face, palms and soles are usually unaffected. The pruritic papules may coalesce to form urticated plaques. Subepidermal vesicle formation has been described in PEP, 5 but not frank bullae. The condition is most unlikely to recur 6 and is not associated with an adverse outcome for either the mother or the infant. 1,6 Treatment 7 involves reassurance of the mother of the benign nature of the condition and the use of topical, moderately potent steroids and soothing emollients. A short course of systemic steroids may be required for severe cases.The histology of the condition is relatively characteristic but not specific. Several other conditions can give similar histological appearances including PG, allergic contact dermatitis, and drug or arthropod reactions. Therefore clinicopathological correlation is essential. The clinical differential diagnosis of PEP includes viral exanthemas, drug eruption, erythema multiforme, urticaria, contact dermatitis and early PG. At the time of their onset PEP and PG may be difficult to distinguish on clinical and histological grounds. 7 The development of bullous lesions has previously been considered diagnostic of PG. However, apart from the development of bullous lesions, this case had all of the hallmarks of PEP. The two disorders can be confidently differentiated by direct immunofluorescence of perilesional skin which demonstrates complement deposition at the basement membrane zone in all cases of PG and is consistently negative in PEP. The absence of complement deposition at the basement membrane has been confirmed by immunoelectron microscopy. 8 Others have reported unusually florid cases of PEP with features that also raised the possibility of PG, such as the presence of vesicles, involvement of palms and soles and continuation of the rash into the postpartum period. 9 The development of frankly bullous lesions would, until now, have been regarded as indicative of PG. However, this patient demonstrates that bullous lesions can also occur in PEP. Therefore this case redefines our clinical criteria for the diagnosis of pregnancy eruptions and highlights the crucial role of immunofluorescence studies in their accurate diagnosis.
The advice given in dermatology postoperative PILs across England and Wales is highly variable. A nationally agreed template or set of postoperative advice should be considered to improve consistency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.