ABSTRACT
Background: Delays due to COVID-19 impacted dermatology. Two Italian studies found significant decreases in melanoma diagnosis (MM) during the lockdowns, while a predicted growth model of cutaneous squamous cell carcinoma (cSCC) found delaying excision results in significant tumor upstaging. Objective: We hypothesized that the COVID-19 lockdown increased tumor severity and postoperative morbidity of MM and cSCC. Methods: This was a retrospective analysis of all newly diagnosed MM and cSCC treated with Mohs surgery during 2019 (pre-lockdown) and 2020 (post-lockdown) period. We collected data on the number of cases, tumor characteristics, extent of surgery, and time to treatment. Results: Our analysis (n = 554) found no significant difference in the number of cases of cSCC or MM between the 2 years (P =.675), the preoperative size of cSCCs or MMs (P =.68, P =.786), cSCC cases with flap or graft repairs (P =.076), or cSCC cases with aggressive histologic features (P =.243). There were significantly fewer days from biopsy to surgery in 2020 for MM (27.6 days compared with 23.8 days;P =.041) and cSCC (41.5 days compared with 33 days;P =.037);however, there were significantly more multistage Mohs surgeries for cSCC in 2020 (39 versus 69;P =.005). Conclusion: The COVID-19 lockdown resulted in a significantly increased number of multistage Mohs surgeries for the treatment of cSCC. For both cSCC and MM, the lockdown did not impact the number of cancers treated, the size of the tumors, the complexity of the repairs, or the presence of aggressive histology, while it did positively impact time to treatment.
ABSTRACT
During these difficult times of COVID-19, people are struggling to return to their normal routines, including going back to schools and workspaces. To prevent the spread of the disease, wearing face masks is essential for everyone to protect themselves and the ones around them. However, challenges arise in regard to enforcement of wearing masks in large crowds such as at educational centres and public transportation. This paper proposes a robust automatic system for face mask detection using transfer learning kits from NVIDIA. Based on the backbone of Resnet-18, the model results in high accuracy in the distinguishing of persons who do and do not wear masks. Leveraged by the NVIDIA edge accelerator, the system can run in real-time environments, making it applicable in various venues. Its feasibility was demonstrated by deploying the approach in an education centre in Hong Kong. © 2022, Hong Kong Institution of Engineers. All rights reserved.