Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Update on the current opinion, status and future development of digital pathology in Switzerland in light of COVID-19
18
Zitationen
4
Autoren
2021
Jahr
Abstract
AIMS: The transition from analogue to digital pathology (DP) in Switzerland has coincided with the COVID-19 crisis. The Swiss Digital Pathology Consortium conducted a national survey to assess the experience of pathologists in dealing with the challenges of the pandemic and how this has influenced the outlook and adoption of DP. METHODS: A survey containing 20 questions relating to DP, personal experiences and challenges during the pandemic was addressed to Swiss pathologists at different experience stages in private practice, community and university hospitals. RESULTS: All 74 respondents were pathologists, with 81.1% reporting more than 5 years of diagnostic service experience. 32.5% reported having read 100 digital slides or more in a diagnostic context. 39.2% reported using whole slide imaging systems at their primary workplace. Key DP use cases before the COVID-19 lockdown were tumour boards (39.2%), education (60.8%) and research (44.6%), with DP used for primary diagnosis in 13.5%. During the COVID-19 crisis, the use of DP for primary diagnostics more than doubled (30% vs 13.5%), with internal consults as important drivers (22.5% vs 16.5%), while research use (25% vs 44.6%) and external consults (17.5% vs 41.9%) strongly decreased. Key challenges identified included a lack of established standard operating procedures and availability of specialised hardware and software. CONCLUSIONS: This survey indicates that the crisis acted as a catalyst in promoting DP adoption in centres where basic workflows were already established while posing major technical and organisational challenges in institutions that were at an early stage of DP implementation.
Ähnliche Arbeiten
A survey on deep learning in medical image analysis
2017 · 13.959 Zit.
pROC: an open-source package for R and S+ to analyze and compare ROC curves
2011 · 13.781 Zit.
Dermatologist-level classification of skin cancer with deep neural networks
2017 · 13.499 Zit.
A survey on Image Data Augmentation for Deep Learning
2019 · 12.096 Zit.
QuPath: Open source software for digital pathology image analysis
2017 · 8.413 Zit.