Edge Technology in Radiology

Good morning ladies and gentlemen. I'm Emma quota from the Freiburg University Medical Center, the Department of Radiology there where I am vice chair of imaging, informatics and quality management. I'm also the President of the European. X and the chair of the ESR, inhalers, and Informatic subcommittee today. I'm going to talk about the benefits and AI of Edge technology and radiology. So I already told you that we are going to talk about edge computing. Also. What is edge computing? Well we can differentiate between on premise computing, which is when you have all the computing hardware and software in hours. Then cloud computing is. I have been showing you where the computing cloud is an at environment that abstracts and pools your data and applications and edge computing is a newer concept which means. That the hardware is located on the edge of the network. The data is processed and collected at the edge of the network. The advantages is that the processing is faster and you get a better handling of large data volumes and those two points are very important in radiology, especially when you consider ctor MRI where we have large data volumes at computing reduces latency. Typically when running an. Algorithm in the cloud for late radiological. Larger theoretical data sets like a CT. This takes up to 10 minutes for the processing and the total turn around time, meaning sending the images into the cloud, processing them and getting them back into your Pex takes up to 30 minutes or something and running the same AI algorithm. Which edge computing in our experience where reduce the processing time by a factor of at least three. And even more, depending on the hardware you're using. And at computing, might reduce discussions with your data protection officer, because with edge computing data don't leave the hospital, and processing occurs in the hospital, no data go to the crowd. So in my place, I had to discuss those cloud systems for more than six months with our data Protection officer and this would have. This discussion would have been much faster or no discussion with an edge system at that time. Yeah, you still have to consider some points which is for add computing. You will have some investment because you need to buy the hardware and infrastructure you have to think about energy consumption. Large computing centers typically are more efficient than smaller ones. Scalability might be a problem where cloud computing is easier to adapt to your needs than edge computing or on premise computing. And also you have to think about a reliability and you might have the need for redundancy when running systems on premise or on the edge. I have already shown you this slide, so that's the typical configuration for cloud computing, and now this is a slide from a Siemens. That's how an ad computing looks like. You still have two possibilities. One is you share and process the data in the cloud. So what we have been doing in the past. But then you have a new option with this Edge device, which is that you store the data only locally and also the processing is local. What still happens in the cloud is that you will get all the updates of your system over the cloud and you don't have to worry about this. So those computing systems, those add computing systems combine. Solutions with the essential capabilities of the cloud with the needs for local data storage and processing. You download the closed environment that will be controlled by Siemens Healthineers via the cloud. So the full management of local applications, like the AI Red Companion and update update of products with AI algorithms can be done within your own regulatory framework. So what could you take home from? This edge computing is a very promising technology, especially when considering data protection. Thank you for your attention.

Edge Technology in Radiology Learn from an expert in a clinical field Prof. Dr. Elmar Kotter, University Hospital Freiburg Part 2 Fracture UNIVERSITATS KLINIKUM FREIBURG Benefits of Al and edge technology in radiology Elmar Kotter Vice Chair, Imaging Informatics & Quality Management, Dept. of Radiology, Freiburg University Medical Center President, European Society of Medical Imaging Informatics (EuSoMII) Chair, ESR eHealth and Informatics Subcommittee SIEMENS Healthineers Prof. Dr. Elmar Kotter, M(H)BA Radiologist, University Hospital Freiburg Department of Radiological Diagnostics and Therapy Clinic for Diagnostic and Interventional Radiology Freiburg, Germany What is edge computing ? On premise computing Cloud computing: a computing cloud is an IT environment that abstracts and pools data and applications. Edge computing: hardware is located on the edge of the network. Data is processed and collected at the edge of the network. Advantages: processing is faster, better handling of large data volumes. Edge computing reduces latency · Typically, running an Al algorithm in the cloud for a large radiological dataset, like a CT, takes up to 10 minutes *, which can result in a turnaround time of 30 minutes Running the same Al algorithm with edge computing will reduce processing time by a factor of at least 3 ... and more depending on the hardware *depending on your internet connection Edge computing might reduce discussions ... with your data protection officer With edge computing, data don't leave the hospital, processing occurs in the hospital, no data go in the cloud To consider Investment - need to buy hardware and infrastructure Energy - large computing centers are more efficient Scalability - cloud computing is easier to adapt to your needs Reliability - need for redundancy Cloud Al computing Freiburg TeamPlay Usage Dose etc. Chest CT CT1 Meta-Daten CT2 Bild-Daten Receiver PACS MR Auswertungen Pseudo- nymisierung Hybrid computing enables data storage and processing in the cloud or locally depending on your use cases and preferences Cloud Share data with the doud via a secured & managed connection Edge device & applications are Local centrally managed from the cloud to ensure up-to-data apps & algorithms and cybersecurity (SaaS) Data transfer from your Edge scanner to the edge device device Option 1: Share & process data in the cloud based on your use case and preferences Option 1 Option 2: Local data storage and processing on the edge device Option 2 How the Edge functionality works Al algorithms require heavy computing power . The Edge functionality allows to process data locally while being connected to and managed from the cloud. At first, gated step to the cloud Our hybrid computing solution combines essential capabilities of the cloud with the needs for local data storage. By activating the Edge functionality on your teamplay Receiver, you download a closed Saas environment that is controlled by Siemens Healthineers via the cloud. Thus, we can fully manage local applications like Al-Rad Companion, update products with Al algorithms within your regulatory framework, and share data relevant for updating the Al based on your preference. A one-way street from the cloud The Edge functionality only allows the cloud to send data into the gated environment to interact with the Al algorithms. The cloud cannot retrieve data, nor can users send data into the cloud . Edge device Algorithm data Algorithm Take Home Edge computing is a promising technology, especially when considering data protection Al helps radiologists whith quantification of parameters which today are not always part or clinical routine Integration of different Al algorithms in one system is key to Siemens Healthcare GmbH, 2021 Al-Rad Companion consists of several products that are (medical) devices in their own right, and products under development. Al-Rad Companion is not commercially available in all countries. Future availability cannot be ensured. 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. Siemens Healthineers are neither the provider nor legal manufacturer of this video. Any claims and statements made in this video and any content shown in the video are under the sole responsibility of the provider. Additionally, the services may not be available in all countries and the content may not be commercially available in all countries. Please contact your local Siemens Healthineers organization for further details Siemens Healthcare GmbH Henkestr. 127 91052 Erlangen, Germany Telephone: +49 9131 84-0 siemens-healthineers.com