syngo Application Software

The syngo Application Software is engineered to enhance medical image visualization and provide advanced guidance for diagnostic and interventional procedures. Its "syngo TrueFusion" feature achieves this by integrating real-time transesophageal ultrasound with live fluoroscopy, employing automated machine learning-based co-registration and anatomical modeling to improve procedural navigation and decision-making.

The syngo Application Software (VD20) is a medical software platform designed for comprehensive medical image management, including real-time viewing, diagnostic review, post-processing, 3D visualization, communication, and storage. It supports a wide range of clinical applications, facilitating diagnostic image viewing and providing image-guided solutions for interventional procedures across specialties such as cardiology, electrophysiology, oncology, radiology, and neuroradiology. The software can be deployed on standalone workstations or integrated within Siemens Angiography, fluoroscopy, or radiographic systems, assisting physicians in diagnosis, treatment planning, and control, particularly for minimally invasive surgical procedures and tumor treatments. A key enhancement to this platform is the "syngo TrueFusion" feature, which enables the fusion of transesophageal ultrasound (TEE) information with live 2D fluoroscopic images. This is achieved through automated co-registration ("eSie Sync"), which incorporates machine learning for probe detection, and "eSie Valves" for anatomical modeling of heart valves. The system aims to improve anatomical orientation, streamline TEE guidance, and reduce complexity in challenging procedures. Non-clinical performance testing on phantom datasets for syngo TrueFusion demonstrated mean deviations in measurements between 2.13mm and 2.92mm with standard deviations between 1.29mm and 1.69mm, which were deemed clinically acceptable.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the machine learning algorithm for "eSie Sync" probe detection perform with diverse patient anatomies and challenging imaging conditions not fully represented by phantom data?; What is the documented impact of "syngo TrueFusion" on clinical outcomes, such as procedure duration, radiation dose, and contrast agent volume, in specific interventional cardiology or radiology procedures?; Are there plans to expand "syngo TrueFusion" to integrate other imaging modalities beyond TEE and fluoroscopy, or to support different types of ultrasound probes?; What are the accuracy limitations and validation details of the "eSie Valves" modeling feature, especially in cases of severe valvular disease or post-surgical anatomy?; What mechanisms are in place within the "syngo TrueFusion" workflow to detect and alert users to potential misregistration events, and what are the recommended protocols for correction?