Vantage Orian 1.5T, MRT-1550, V6.0

The Vantage Orian 1.5T, MRT-1550, V6.0 system is a diagnostic MRI device employing a 1.5 Tesla magnet and nuclear magnetic resonance principles to visualize diverse anatomical structures. It integrates the AiCE deep learning reconstruction processing unit to enhance image quality, with this update certifying its expanded utility across a broader range of anatomical regions, validated by performance testing that confirmed maintained or improved image detectability.

The Vantage Orian 1.5T, MRT-1550, V6.0, is a 1.5 Tesla Magnetic Resonance Imaging (MRI) system designed for diagnostic imaging. It produces cross-sectional transaxial, coronal, sagittal, and oblique images that display anatomical structures of the head or body, and is also capable of non-contrast enhanced imaging such as Magnetic Resonance Angiography (MRA). The system operates based on the principles of nuclear magnetic resonance (NMR), imaging the spatial distribution of protons and their inherent properties like proton density, T1 and T2 relaxation times, flow dynamics, and chemical shift. The use of contrast agents is optional, depending on the specific region of interest, and the images produced are intended to provide diagnostic information when interpreted by a trained physician. This MRI system incorporates the AiCE (Advanced intelligent Clear-IQ Engine) Reconstruction Processing Unit, which utilizes deep learning algorithms for image processing. This submission specifically details the expansion of AiCE's application to additional anatomical regions, including the spine (cervical, lumbar, thoracic), various musculoskeletal areas (shoulder, hip, elbow, wrist/hand, foot/ankle), pelvis (female, soft tissue, prostate), abdomen (liver, renal, pancreas), breast, and cardiac imaging, supplementing its prior use for head and knee imaging. The system features a 1.4m short, 3.8-ton magnet, Pianissimo™ scan noise reduction technology, and a gradient coil enabling a maximum field of view of 55x55x50 cm. Performance and bench testing, including model observer studies for low contrast detectability and a human observer study with 6 board-certified radiologists involving 55 studies, indicated that AiCE maintained or improved image quality and was statistically preferred over other filters, performing at a level comparable to or exceeding that of predicate devices.

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 AiCE deep learning reconstruction algorithm specifically impact quantitative image metrics such as Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR) across the newly added anatomical regions?; What were the specific criteria and scale used in the human observer study that led to the 'statistical preference' for AiCE images, and were inter-observer variabilities assessed?; Can the AiCE reconstruction processing be customized or tuned by the operator for different clinical scenarios or patient types within the approved anatomical regions?; What is the computational time difference for image reconstruction with AiCE compared to standard methods, especially for complex datasets from the newly added regions like cardiac MRI?; Beyond low contrast detectability, were other aspects of image quality, such as edge sharpness or artifact reduction, specifically evaluated in the performance testing for the expanded anatomical applications of AiCE?