FDA Radiology AI Devices

Aquilion Serve (TSX-307A/1) V1.3 is a whole-body multi-slice helical CT scanner that captures detailed cross-sectional volume images including the head. It incorporates AiCE, an AI-powered noise reduction algorithm using deep convolutional neural networks to improve image quality and reduce noise. This helps clinicians obtain clearer images for specialized studies across multiple anatomical regions, aiding diagnosis and treatment planning while potentially reducing radiation dose.

Spine Auto Views is a software tool that automatically processes CT images of the spine to create anatomically focused reformatted views and labels vertebrae and disc spaces, facilitating quick and consistent review for clinicians. It utilizes deep learning algorithms to generate multiple reformatted image planes without user interaction and exports the results automatically for radiologist reading.

CAC Software by Imbio, Inc. is a machine learning-based post-processing tool that analyzes non-contrast CT images of the chest to assess calcified plaques in the coronary arteries. It quantifies the calcification burden by producing scores and metrics that help clinicians evaluate coronary artery disease risk. The software outputs annotated images and a detailed report, integrating into the standard DICOM workflow to assist physicians without making standalone diagnoses.

The iCAC Device is a software tool that analyzes routine chest CT scans to automatically detect and quantify coronary artery calcium, which helps physicians assess cardiovascular risk. It provides outputs such as calcium segmentation visualizations and quantitative calcium scores during standard clinical workflows, assisting physicians without replacing original reports or scans.

Deep Learning Image Reconstruction by GE Healthcare Japan Corporation is a deep learning based software integrated into CT scanners to reconstruct high-quality cross-sectional images of the head, whole body, cardiac, and vascular systems. It uses a trained deep neural network to reduce image noise and artifacts while maintaining spatial resolution, aiding clinicians in obtaining clearer diagnostic images with routine CT throughput.

AI-Rad Companion (Cardiovascular) is a software product that uses AI and deep learning to analyze previously acquired chest CT images, providing quantitative and qualitative assessments of cardiovascular structures like the heart and aorta. It helps clinicians by automating segmentation, volume measurement, calcium quantification in coronary arteries, and diameter measurements of the aorta, thus supporting accurate and efficient cardiovascular disease evaluation.

Spectral Bone Marrow is an automated deep learning-based software designed for spectral CT images of the body and extremities. It segments bone regions and creates enhanced, color-coded images to help radiologists better visualize bone marrow. This assists in diagnosing traumatic and non-traumatic bone conditions more efficiently by providing improved image visualization and an automated clinical workflow.

The Aquilion Precision (TSX-304A/4) V10.14 with AiCE is an advanced whole-body CT scanner that leverages AI through deep convolutional neural networks to reduce image noise and improve image quality. It also uses an iterative reconstruction algorithm to reduce radiation dose while enhancing spatial resolution. This helps clinicians obtain clearer and more detailed images to support diagnosis and treatment planning across various body regions, including abdomen, chest, brain, and extremities.

The Aquilion Serve (TSX-307A/1) V1.2 with AiCE-i is a whole-body multi-slice helical CT scanner enhanced with AiCE, an AI-based noise reduction algorithm using deep convolutional neural networks. It improves image quality and reduces noise for abdomen, pelvis, lung, cardiac, extremities, head, and inner ear scans, helping clinicians obtain clearer diagnostic images faster and with potentially reduced radiation dose.

The uCT ATLAS Astound with uWS-CT-Dual Energy Analysis is an advanced CT scanner designed to produce cross-sectional images of various body regions, including head, whole body, cardiac, and vascular areas. It integrates deep learning for image reconstruction to enhance image quality and reduce noise, and includes software for dual energy analysis to differentiate tissue types based on their chemical composition. This aids clinicians in lung cancer screening and detailed anatomical evaluation, supporting early diagnosis and treatment.