uCT Orion Extra
The uCT Orion Extra integrates AI with CT technology to provide efficient, patient-focused scanning experience and exceptional image clarity. Beyond intelligent scanning, its robust hardware provides the power and reliability to meet diverse clinical needs. As a forward-looking investment, uCT Orion Extra is built for today's demands and tomorrow's value.
Contact our experts
Contact usBrochure
Download brochureuCT Orion Extra Keeps Image Quality on Track
Quality Check for Chest
During chest scans, the AI-empowered quality check monitors the patient's breath-hold status. If the patient fails to hold the breath as required, the system triggers real-time prompts, which helps technologists efficiently confirm chest image quality and reduce patient recalls.
uCT Orion Extra Guards Every Patient
uAI Vision for Monitoring
The uCT Orion Extra's uAI Vision features two cameras, enabling real-time patient monitoring from two distinct views: top-down and close-up. It continuously monitors the patien's status throughout the scan, helping technologists quickly identify issues.
AI-Supported Streamlined Workflow
Pre-scan: AI-based Automatic Patient Positioning
Based on uAI Vision's detection of 21 anatomical landmarks, the uCT Orion Extra can automatically identify the appropriate scan range based on the selected protocol. The technologist only needs a single click to position the patient for the scout scan, improving preparation efficiency.
DELTA elevates image quality across all dimensions
Deep learning trained algorithm (DELTA) leverages an extensive training dataset and a sophisticated 3D neural network to deliver images that are both more defined and detailed at lower radiation dose, setting a new standard in imaging excellence.
Up to 80%* radiation dose reduction at the same low contrast detectability (LCD).
Up to 98%* image noise reduction at the same dose.
Up to 155%* LCD improvement at the same dose.
*DELTA images compared with FBP based on phantom tests. Data on file.
3D modelling of the motion pattern to restore the real clinical situation
Patient head movement typically involves multiple motion patterns, which makes it challenging to obtain large datasets of head motion artifacts for training deep learning algorithms. To construct the training dataset, the Motion Freeze algorithm generates simulated artifacts on gold-standard images along the X, Y, and Z axes, encompassing rotation, translation, oscillation, and mixed motion patterns. By introducing diverse motion artifacts, this approach enables the trained network model to handle a broad spectrum of motion conditions.