FDA Radiology AI Devices

Koios DS is a web-based AI software that helps trained physicians analyze ultrasound images of breast lesions and thyroid nodules suspicious for cancer. It automatically selects regions of interest, classifies lesions using standardized lexicons like BI-RADS and TI-RADS, provides cancer risk assessments, and generates structured reports to aid in clinical decision-making, improving diagnostic accuracy and reducing variability.

VBrain is a software tool that helps medical professionals in planning radiation therapy for brain tumors. It uses artificial intelligence, specifically deep learning neural networks, to automatically outline brain tumors and organs at risk on MRI scans of the brain. This assists clinicians by providing initial contours that they can review and adjust, improving workflow efficiency and accuracy in treatment planning.

HealthPPT is an AI-powered software tool that helps radiologists by automatically detecting signs of pneumoperitoneum in adult frontal chest X-rays. It prioritizes urgent cases by notifying the radiology workstation with a low-resolution preview image, enabling faster review of potentially critical findings. The device works alongside standard workflows without altering original images and does not itself diagnose the condition, but aids clinical assessment by highlighting suspicious cases for prompt review.

RT-Mind-AI is a software tool designed to automatically segment organs-at-risk in non-contrast CT images for patients undergoing radiation therapy. It helps radiation oncologists by providing accurate anatomical contours that support treatment planning and evaluation, improving workflow and precision.

LVivo Seamless is an AI-powered software application that analyzes ultrasound (echocardiogram) images to automatically detect heart structures, measure ejection fraction (EF), and calculate global longitudinal strain (GLS), aiding clinicians in assessing cardiac function efficiently and accurately. It runs offline on a server in healthcare settings, accepts DICOM-format ultrasound clips from various vendors, and sends results to PACS for professional review.

Al-Rad Companion (Pulmonary) is an AI-powered software by Siemens that processes CT images of the lungs to assist clinicians in quantitatively and qualitatively analyzing lung diseases. It segments lungs and lobes, detects lung lesions and areas of abnormal tissue density, and provides measurements to support radiologists and physicians in emergency, specialty, and general care settings. This helps streamline and improve lung disease evaluation.

The Vantage Fortian 1.5T, MRT-1550, V8.0 with AiCE Reconstruction Processing Unit for MR is a 1.5 Tesla MRI system that produces detailed cross-sectional images of the body or head. It incorporates AI-based reconstruction and machine learning technologies to enhance image quality and assist in planning scans, improving diagnostic accuracy and patient comfort.

MammoScreen 2.0 is an AI-based software tool designed to assist physicians by automatically analyzing standard screening mammograms including FFDM and DBT images. It marks suspicious soft tissue lesions or calcifications on breast images and provides a level of suspicion score to help radiologists improve detection and characterization of breast cancer findings. This tool acts as a concurrent reading aid to improve diagnostic accuracy but does not replace physician judgment.

OnQ Neuro is an automated software device designed to analyze neurological MRI images, specifically for brain tumors. It performs automatic segmentation and quantification of tumor volumes and diffusion-weighted imaging data, helping clinicians assess tumor progression and treatment response more efficiently by providing quantitative and graphical image data that can be integrated into clinical workflows.

The Swoop Point-of-Care Magnetic Resonance Imaging (POC MRI) System by Hyperfine, Inc. is a portable MRI device designed to provide bedside imaging of the brain. It uses advanced deep learning for image reconstruction to reduce noise and blurring, enabling clinicians to view internal head structures more clearly. This system facilitates quicker and more accessible brain imaging in various care settings, aiding in diagnosis without the need to transport patients to traditional MRI suites.