Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

AI in MedTech Production. Visual Inspection for Quality Assurance

Presentation held at T4M meet2match, 6.-7. July 2021
: Roscher, Karsten

presentation urn:nbn:de:0011-n-6386095 (1.1 MByte PDF)
MD5 Fingerprint: 2c4f134d4b16d8e9e92c888802ac2bf2
Created on: 10.8.2021

2021, 20 Folien
Netzwerk-Format "T4M meet2match" <2021, Online>
Presentation, Electronic Publication
Fraunhofer IKS ()
artificial intelligence; AI; safety; Safe Artificial Intelligence; Safe Intelligence; machine learning; ML; deep learning; computer vision; quality assurance; uncertainty estimation; Active Learning; medical technology

Automated visual inspection based on machine learning and computer vision algorithms is a promising approach to ensure the quality of critical medical implants and equipments. However, limited availability of data and potentially unpredictable deep learning models pose major challenges to bring such solutions to life and to the market. This talk addresses the open challenges as well as current research directions for dependable visual inspection in quality assurance of medical products.