Accuracy of mobile digital teledermoscopy for skin self-examinations in adults at high risk of skin cancer: an open-label, randomised controlled trial

Janda, Monika; Horsham, Caitlin; Vagenas, Dimitrios; Loescher, Lois J.; Gillespie, Nicole; Koh, Uyen; Curiel‐Lewandrowski, Clara; Hofmann‐Wellenhof, Rainer; Halpern, Allan C.; Whiteman, David C.; Whitty, Jennifer A.; Smithers, B. Mark; Soyer, H. Peter

doi:10.1016/s2589-7500(20)30001-7

Cited by 45 publications

(41 citation statements)

References 26 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the teledermoscopy group, no melanoma was overlooked by the subjects. 15 According to the NCCN, telemedicine evaluation should be preferred for new patients if possible; complete history and physical examination can be postponed for up to the day of surgery. 11…”

Section: Teledermatology and Melanoma In The Era Of Covid-19mentioning

confidence: 99%

Melanoma and COVID ‐19: A narrative review focused on treatment

Elmas

Demirbaş

Düzayak

et al. 2020

Dermatologic Therapy

View full text Add to dashboard Cite

Melanoma is the most severe form of skin cancer and its incidence has increased over the past few decades. COVID-19 pandemic affected the diagnosis and management of many diseases including melanoma. In this study, we aimed to provide a review focused on the diagnosis and management of melanoma in the era of COVID-19. A comprehensive search was conducted on PubMed, Web of Science, and Google Scholar databases using the keywords "melanoma," "coronavirus," "COVID 19," and "SARS-CoV-2." The relevant guidelines published by the European Society for Medical Oncology and the National Comprehensive Cancer Network were also included. The current guidelines recommend that surgical interventions for new diagnosis of invasive primary melanoma, patients with postoperative complications, wide resection and sentinel lymph node biopsy for newly diagnosed T3-T4 melanoma, and planned surgical procedures for patients in neo-adjuvant trials should be prioritized. Surgical treatment of T3/T4 melanomas should be prioritized over T1/T2 melanomas except for any melanoma in which large clinical residual lesion is visible. Adjuvant therapies can be postponed for up to 12 weeks depending on the local center circumstances. PD-1 inhibitor monotherapy is recommended for patients starting immunologic therapy. Combination immunotherapy is still considered suitable for patients with higher-risk disease. Encorafenib and binimetinib should be prioritized for patients requiring BRAF-targeted therapy due to the lower chance of symptoms mimicking COVID-19 infection.

show abstract

Section: Teledermatology and Melanoma In The Era Of Covid-19mentioning

confidence: 99%

Melanoma and COVID ‐19: A narrative review focused on treatment

Elmas

Demirbaş

Düzayak

et al. 2020

Dermatologic Therapy

View full text Add to dashboard Cite

show abstract

“…The basic concept of our framework is throat examination using a self-taken smartphone image with computer-aided diagnosis system, which is similar to the previous dermatology study [ 12 ]. This study was performed using publicly accessible self-taken throat images on the web.…”

Section: Methodsmentioning

confidence: 99%

Toward automated severe pharyngitis detection with smartphone camera using deep learning networks

Yoo

Choi

Jang³

et al. 2020

Computers in Biology and Medicine

View full text Add to dashboard Cite

Purpose Severe pharyngitis is frequently associated with inflammations caused by streptococcal pharyngitis, which can cause immune-mediated and post-infectious complications. The recent global pandemic of coronavirus disease (COVID-19) encourages the use of telemedicine for patients with respiratory symptoms. This study, therefore, purposes automated detection of severe pharyngitis using a deep learning framework with self-taken throat images. Methods A dataset composed of two classes of 131 throat images with pharyngitis and 208 normal throat images was collected. Before the training classifier, we constructed a cycle consistency generative adversarial network (CycleGAN) to augment the training dataset. The ResNet50, Inception-v3, and MobileNet-v2 architectures were trained with transfer learning and validated using a randomly selected test dataset. The performance of the models was evaluated based on the accuracy and area under the receiver operating characteristic curve (ROC-AUC). Results The CycleGAN-based synthetic images reflected the pragmatic characteristic features of pharyngitis. Using the synthetic throat images, the deep learning model demonstrated a significant improvement in the accuracy of the pharyngitis diagnosis. ResNet50 with GAN-based augmentation showed the best ROC-AUC of 0.988 for pharyngitis detection in the test dataset. In the 4-fold cross-validation using the ResNet50, the highest detection accuracy and ROC-AUC achieved were 95.3% and 0.992, respectively. Conclusion The deep learning model for smartphone-based pharyngitis screening allows fast identification of severe pharyngitis with a potential of the timely diagnosis of pharyngitis. In the recent pandemic of COVID-19, this framework will help patients with upper respiratory symptoms to improve convenience in diagnosis and reduce transmission.

show abstract

“…We recently conducted a randomized controlled trial (RCT) comparing patients using skin self‐examination (SSE) with or without using a mobile dermatoscope at home. Both groups had a high degree of sensitivity (> 75%) and specificity (> 87%) in detecting suspicious lesions that the dermatologist also thought were worthwhile checking, and in the mobile teledermoscopy group no melanoma was overlooked by the patients …”

Section: Guide To Taking Standardized Photos For Consumer‐based Skin mentioning

confidence: 98%

“…Both groups had a high degree of sensitivity (> 75%) and specificity (> 87%) in detecting suspicious lesions that the dermatologist also thought were worthwhile checking, and in the mobile teledermoscopy group no melanoma was overlooked by the patients. 4 Based on these findings, during the SARS-CoV-2 crisis we propose a two-step process for consumer-based SSE. Firstly, we recommend that a person conduct whole-body naked-eye SSE.…”

mentioning

confidence: 99%