FDA Radiology AI Devices

The Aquilion Lightning (TSX-036A/7) V10.2 with AiCE-i is a computed tomography (CT) scanner designed for whole body imaging, including the head. It incorporates an AI-driven image reconstruction algorithm called AiCE-i that reduces image noise and improves image quality by using deep convolutional neural networks. This enhancement supports clinicians by providing clearer, more detailed images with potentially lower radiation dose, facilitating better diagnosis and patient care.

HeartFlow Analysis is a medical software that uses previously acquired coronary CT images to create 3D models and simulate blood flow dynamics in coronary arteries. It helps clinicians assess coronary artery disease by providing detailed functional information derived mathematically from CT scans, supporting diagnosis and treatment planning in stable symptomatic patients.

BriefCase is an AI-based software by Aidoc Medical that helps radiologists and trained medical specialists detect and prioritize urgent cases from CT scans of various body regions including head, chest, abdomen, and cervical spine. It flags images with suspected critical findings like fractures, intracranial hemorrhage, pulmonary embolism, intra-abdominal free gas, and large vessel occlusion, presenting low-quality preview images and notifications to accelerate clinical workflow. The software works in parallel with standard of care and does not alter original medical images, serving as a triage and notification aid but not a diagnostic device.

The Aquilion Exceed LB (TSX-202A/3) V10.6 with AiCE-i is a whole-body multi-slice helical CT scanner that acquires and displays cross-sectional volume images, including the head. It incorporates AiCE, an AI-based noise reduction algorithm using deep convolutional neural networks, to improve image quality and reduce noise in scans of the abdomen, pelvis, lung, extremities, head, and inner ear. This technology helps clinicians obtain clearer images at potentially lower radiation doses, facilitating better diagnostic accuracy.

Deep Learning Image Reconstruction for Gemstone Spectral Imaging by GE Medical Systems is an AI-powered CT image reconstruction method designed to produce high-quality cross-sectional CT images from dual-energy X-ray data. It is intended for whole body, vascular, and contrast-enhanced head CT applications, enhancing image quality with a deep neural network-based algorithm that improves low contrast detectability, noise reduction, and artifact suppression, supporting accurate and reliable diagnosis.

Revolution Ascend is a computed tomography (CT) scanner designed for head, whole body, cardiac and vascular imaging. It produces detailed cross-sectional images using X-ray data taken from multiple angles. The system incorporates advanced AI-enabled features like deep learning-based auto positioning and machine learning-enabled intelligent protocoling to improve workflow and image acquisition. It aids clinicians in diagnosis, treatment planning, and monitoring.

HALO is a cloud-based artificial intelligence software that helps medical specialists by analyzing brain CT angiograms to detect signs of large vessel occlusion, a serious condition associated with stroke. It runs alongside the standard imaging workflow and sends alerts to specialists to expedite patient evaluation and care, improving stroke diagnosis and treatment speed.

FastStroke, CT Perfusion 4D is a software package designed to aid clinicians in analyzing and visualizing CT scans, especially for stroke assessment. It processes and displays vascular and perfusion data from CT scans of the head and neck to help identify collateral vessels and perfusion abnormalities, assisting physicians in stroke evaluation and treatment planning.

AI-Rad Companion Organs RT by Siemens is a post-processing AI software that automatically contours organs at risk on CT images to aid radiation therapy treatment planning. It uses deep learning algorithms to generate organ contours that can be reviewed and accepted by trained medical professionals, helping streamline radiotherapy preparation and ensure accurate targeting of treatment.

AutoContour is a software tool that helps radiation treatment planners automatically contour and review anatomical structures in medical images, primarily CT scans, to prepare for radiation therapy treatment planning. It uses cloud-based machine learning algorithms to produce initial contours, and provides a web interface for review and editing, enhancing efficiency and accuracy for clinicians.