OpenRegulatory Conference 2021
Astrid Ottosen, Radiobotics
Supplier Evaluation of Medical Annotators for AI SaMD
As a SaMD-manufacturer that develops machine learning based devices, we are heavily reliant on training data including training labels, i.e. image annotations of high quality in order to ensure a good and reliable performance of the medical device in the end.
As we use suppliers for the task of annotating the medical images, this puts weight on the supplier and purchasing process. How do we make sure that the image annotations are of sufficiently high quality?
Astrid Ottosen graduated from the Technical University of Denmark in 2016 with a master’s degree in biomedical engineering. Astrid gained experience within the field of quality assurance and regulatory affairs for SaMD as a Product Quality Engineer at 3Shape, before joining Radiobotics as the 7th employee.
At Radiobotics, Astrid is a leading figure within RA/QA and played a big part in the establishment of Radiobotics’ QMS and achieving ISO 13485 and MDR certification of it.