15 Jun 2024

Generative AI in medical technology

Siemens Healthineers shows Potential of Generative AI in Medical Technology

Siemens Healthineers has announced it presented ideas and prototypes for the use of generative AI at the Radiological Society of North America (RSNA) congress.

The company says in recent months, software such as ChatGPT has shown that AI is able not only to analyse existing data sets but can also use them to create new content. Many companies are positioning themselves with generative AI in the areas of text or image generation.

Siemens Healthineers says it does not only focus on image or text applications – it combines them. A chat system loads, links and prepares the appropriate answers, reports and images. This means for example, that by clicking on the medical image, the appropriate area in the report can be highlighted – and vice versa. In addition, reports on diagnostic images are dynamically generated by AI and prioritised according to importance (1).

Siemens Healthineers says it is also working on generative AI for use in customer service and support as well as for training medical staff. This makes generative AI an important part of the so-called “Smart Imaging Value Chain”. It includes intelligent data integration along the entire imaging process – from patient history to reporting.

“We are working with Siemens Healthineers, for example to use AI to scan hundreds of databases for information about the patient or their illness by using natural language with the power of large language models and get a clear picture. In the future, using such applications we will be able to identify possible issues in the course of treatment very easily and will be able to incorporate new findings from research into treatment much faster. Some of it is still a vision, but with large language models, such scenarios become conceivable,” says PD Dr. Johannes Haubold, Senior Physician for Clinical AI Integration at the University Hospital Essen, Germany (2).

André Hartung, Head of Diagnostic Imaging at Siemens Healthineers, says: “Thanks to our products and the extensive image and text data they generate, we are in a unique position: clinicians can focus more on the medical question and the patient. They lose less time searching through the available data sets. This is just the beginning of our journey to generative AI.”

1 The features mentioned are under development and is not commercially available. Future availability cannot be guaranteed.
2 The statements by Siemens Healthineers’ customers described herein are based on results that were achieved in the customer’s unique setting. Because there is no “typical” hospital or laboratory and many variables exist (e.g., hospital size, samples mix, case mix, level of IT and/or automation adoption) there can be no guarantee that other customers will achieve the same results.

Company info: Siemens Healthcare