Deep learning in medical device manufacturing

In the August issue of ONdrugDelivery magazine, SHL’s Frederick Gertz, Manager of Data Process and Innovation, and Gilbert Fluetsch, Director of Automation Systems, discusses how deep learning can boost the manufacturing landscape in the medical device industry.  

In this article, the authors shed light on the development of deep learning, explaining its evolution from machine learning, and bringing attention to how it can be applied to optimize SHL’s production processes. Drawing from SHL’s own experience with vision inspection systems, Gertz and Fluetsch detail the technical implementations behind deep learning applications on existing automation machinery. In leveraging SHL’s wealth of data generated over years of camera vision inspection on sub-assembly parts during production, the data innovation team shows an example of how to deploy deep learning models for detecting component defects with historical data and within a shorter amount of time. According to the authors, “With 30 minutes of work and a relatively small amount of data, the algorithm was able to provide a very high degree of confidence in its ability to segregate good images from bad.”  

Download the full article

Demonstrations from real-world examples cited in the article allow readers to have a clearer understanding of how deep learning is applied in SHL’s manufacturing environment.  

This article was originally published by SHL Medical and has been updated to reflect SHL Advantec's independent operations.