FDA Radiology AI Devices

AccuContour is a software for radiation oncology departments that uses AI-based deep learning to automatically register multi-modality medical images and segment non-contrast CT images. It assists clinicians in treatment planning, evaluation, and adaptation by generating critical imaging information, thus improving workflow efficiency and patient care in radiation therapy.

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.

BoneView 1.1-US is an AI-powered software designed to assist clinicians by analyzing X-ray radiographs to identify and highlight fractures. It works as a concurrent reading aid, helping improve the accuracy and speed of fracture diagnosis across multiple anatomical regions including limbs, pelvis, ribs, and spine for both adults and pediatric patients. The software integrates seamlessly with imaging systems like PACS and can be deployed on-premise or in the cloud, enhancing radiologists' ability to detect subtle and definite fractures.

Rapid NCCT Stroke is software that uses artificial intelligence to analyze non-contrast head CT scans and quickly notify clinicians about suspected areas of brain hemorrhage or large vessel blockage. This helps prioritize urgent cases and speeds up patient care, but it is intended to assist—not replace—clinical judgment and diagnosis.

The Xeleris V Processing and Review System by GE Healthcare is a software platform designed for processing, reviewing, and analyzing nuclear medicine and PET imaging data. It supports various clinical applications including brain, lung, cardiac, liver, and bone imaging analyses, aiding physicians in diagnosis and treatment planning by providing enhanced image visualization, quantification, and monitoring of patient radiation doses.

AVIEW Lung Nodule CAD is an AI-powered software designed to help radiologists detect lung nodules on chest CT scans. It automatically identifies nodules between 3 to 20 mm in diameter, providing an additional review layer to ensure suspicious nodules are not overlooked. This tool integrates with medical imaging systems and has been clinically tested to improve detection accuracy and reduce the time radiologists spend reviewing CT scans, ultimately aiding early diagnosis of lung conditions.

Brainomix 360 e-ASPECTS is an AI-powered software that analyzes non-contrast CT brain scans to assist clinicians in detecting and characterizing ischemic brain tissue injuries, particularly in cases of acute stroke caused by MCA or ICA occlusions. It automatically provides an ASPECTS score, highlights affected brain regions, and visualizes voxel contributions to the score, helping clinicians make timely and more accurate assessments to guide stroke treatment.

The Swoop Portable MR Imaging System by Hyperfine is a bedside portable MRI device designed to produce images of the internal structure of the head. It uses magnetic resonance imaging with advanced image reconstruction algorithms that include deep learning to enhance image quality by reducing noise and blurring. This helps clinicians obtain diagnostic images even when full diagnostic examination is not practical, aiding diagnosis at the point of care in facilities such as emergency and critical care units.