DIN SPEC 13288 - Guideline for the development of deep learning image recognition systems in medicine

This document gives the requirements, under which image recognition problems in medicine can be addressed using a Deep Learning image recognition system. It allows decision makers to gain knowledge about the application possibilities of a Deep Learning image recognition system in medicine and its structure. With the help of this document, the estimation of the effort and benefit of a Deep Learning image recognition system can be supported and a more accurate forecast of success can be made. This document provides guidelines for the practical development of a Deep Learning image recognition system in medicine, from the procedure of data collection to the structuring of data for learning AI image recognition and the procedural structure of learning experiments, especially with regard to the increased quality standards and regulatory requirements in medicine. This document is particularly for producers of DL systems and those participating in research and development projects for the application of Deep Learning image recognition systems in medicine. This document does not address specific information about active learning, mental learning, automatic continuous learning and the intended use of the DL System in practice. © 2023 Beuth Verlag GmbH

The information about this standard has been compiled by the AI Standards Hub, an initiative dedicated to knowledge sharing, capacity building, research, and international collaboration in the field of AI standards. You can find more information and interactive community features related to this standard by visiting the Hub’s AI standards database here. To access the standard directly, please visit the developing organisation’s website.