Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Digital pathology in Latin America
6
Zitationen
10
Autoren
2023
Jahr
Abstract
Abstract Digital pathology (DP) adoption in Latin America has expanded slower than in developed regions, probably due to many barriers not seen in the latter areas. This article aims to present the current scenario in the region, highlighting barriers and possible solutions to encourage its adoption in Latin American countries. Methods An expert panel of 9 Latin American medical pathologists and 1 information technology specialist participated in an online modified Delphi panel, utilizing a third-party platform (iAdvise, Within3, USA). Thirteen pre-prepared questions were answered interactively. Results Experts' observations confirm the paucity of labs in the region that utilize digital pathology technology. The panel ranked obtaining second opinions and presenting images remotely as the main benefit of a digital pathology system, although many others were cited as well. Cost of implantation was the main barrier mentioned by the experts. Payers' and decision makers' lack of awareness of benefits ranked second as a barrier to DP implementation. Internet infrastructure was also mentioned as a concerning issue in the region. Besides diagnostic pathology services, proposed revenue incomes included commercialization of digital services to other institutions, loan agreements of equipment and software, and organizing courses for pathologists or residents. The need for alternative reimbursement methods for diagnostic services was also mentioned. A regional network of collaborating institutions was also suggested as a viable solution to reach distant areas and laboratories lacking the technology. Conclusions The benefits of DP are clear to the expert panel, but cost and lack of awareness of its benefit may be hampering its widespread adoption in Latin America.
Ähnliche Arbeiten
A survey on deep learning in medical image analysis
2017 · 13.514 Zit.
Dermatologist-level classification of skin cancer with deep neural networks
2017 · 13.137 Zit.
A survey on Image Data Augmentation for Deep Learning
2019 · 11.743 Zit.
QuPath: Open source software for digital pathology image analysis
2017 · 8.113 Zit.
Radiomics: Images Are More than Pictures, They Are Data
2015 · 7.988 Zit.