Artificial intelligence for better diagnostics: LMU University Hospital Munich chooses deepc as AI platform partner

The broad clinical adoption of artificial intelligence (AI) in medicine is rapidly increasing worldwide. The Munich-based LMU University Hospital has been working on AI solutions for clinical practice and research applications to continuously improve clinical workflows and patient care. For their Department of Radiology, the LMU University Hospital has now entered a close strategic partnership with the Munich-based MedTech company deepc to apply AI in clinical practice on a broader scale systematically. Through the innovative AI platform deepcOS, radiologists gain effortless access to numerous globally leading and regulatory-cleared AI solutions. Medical workflows can thus become more efficient, and patient treatment quality can be further increased.

With its two sites, the LMU University Hospital Munich is one of the largest university hospitals in Europe, treating over 500,000 patients annually. The Department of Radiology at the LMU Hospital pursues a clearly defined strategy to personalize and optimize diagnostics-guided therapy. The central pillar of this is the use of artificial intelligence in daily practice. Recently, the radiologists at the Department of Radiology have been working on routine diagnostic operations with the AI platform deepcOS from the Munich-based MedTech company deepc. 

Many carefully selected AI applications from leading AI partners worldwide are fully integrated into the department's existing IT infrastructure with a one-time installation in compliance with the GDPR. All AI solutions are regulatory-cleared and approved medical products. The necessary data protection is also a top priority:  The pseudonymization of the patient's diagnostic data takes place on-site (on-premise), the processing of the data on secure cloud servers, and the re-identification again on-premise. Already implemented algorithms for fracture recognition, orthopedic applications and detection of intracranial hemorrhage will be continuously supplemented by further AI applications in close collaboration with the clinical partners at the LMU University Hospital.

Prof. Jens Ricke, Director of the Department of Radiology at LMU University Hospital Munich, on the use of deepcOS in his department: "We have already gained clinical experience with AI in reporting for orthopedics and in scientific collaborations in the areas of brain MRI and thorax CT. We also develop our own AI prototypes in various research groups in the department for Clinical Data Science, headed by Prof. Michael Ingrisch. With deepc's AI platform, we are now positioning ourselves more broadly in clinical routine. We expect this to significantly advance diagnostics to be even more accurate and faster and make work easier for our team."

Boj Friedrich Hoppe, radiologist and chief medical advisor in the Digital Agenda Group at LMU University Hospital, on the cooperation with deepc: "We are convinced that using deepcOS is the right solution. Instead of integrating individual AI solutions in a resource-intensive and unique way, we have uncomplicated access to many AI solutions via a single gate and with a uniform technical and legal framework. We particularly like that deepc independently selects which AI solutions should process the image data. It couldn't be simpler!"

Physician and data scientist Dr. Franz Pfister, co-founder and CEO of deepc, adds: "I am very pleased about the partnership with LMU University Hospital. As our experience shows, the interplay of medical expertise and competence with AI enables us to focus on complex cases and thus improve the quality of treatment. As a company, we are very proud that a renowned institution like the LMU University Hospital relies on deepcOS, and that we can comprehensively support the radiologists in clinical routine with our platform."

‍Prof. Clemens Cyran, Vice Chair at the Department of Radiology, is already planning further with deepc: "In the future, we would like our colleagues to be alerted in real-time to critical emergency findings that the AI detects in the image data to support prompt patient care. We will also focus on the deep integration of various solutions into the existing clinical workflows, such as the automatic transfer of results into report texts or integration with the RIS/PACS within the framework of worklist prioritization".