FDA Radiology AI Devices

The Discovery MI Gen2 is a PET/CT imaging system by GE Medical Systems designed to produce detailed attenuation-corrected PET images combined with CT scans. It helps clinicians by providing anatomically localized images of radiopharmaceutical distribution, aiding diagnosis, treatment planning, and monitoring of diseases such as cancer, neurological disorders, and cardiac conditions across various body regions.

aPROMISE is a cloud-based software platform that helps healthcare professionals and researchers manage, review, and analyze PSMA PET/CT medical images. It offers tools to mark and quantify regions of interest, supporting oncology care by providing quantitative analysis and report generation to inform patient management decisions.

HYPER AiR is a software device that enhances PET images by using pre-trained neural networks integrated into the image reconstruction process. It helps radiologists and nuclear medicine physicians by reducing noise and improving image contrast in fluorodeoxyglucose (FDG) PET scans, thereby potentially improving diagnostic confidence.

Cartesion Prime (PCD-1000A/3) V10.8 is a diagnostic imaging system that combines Positron Emission Tomography (PET) and multi-slice Computed Tomography (CT). It provides fused images to help clinicians assess metabolic and functional information for evaluating oncological, cardiovascular, and neurological diseases. The device incorporates an AI algorithm called AiCE-i that improves PET image quality and reduces noise using deep learning methods, facilitating better diagnosis and treatment planning.

HYPER DLR is a software-only device that applies a pre-trained convolutional neural network to reduce noise in fluorodeoxyglucose (FDG) PET images. It improves image quality by distinguishing and removing noise components while preserving image details, aiding radiologists and nuclear medicine physicians in better image interpretation.

The Biograph Vision and Biograph mCT PET/CT systems from Siemens are advanced imaging machines that combine CT and PET technologies to produce high-resolution images showing both anatomical structures and physiological functions. These systems help healthcare professionals detect, localize, diagnose, and stage various diseases including cancer, cardiovascular, and neurological disorders, and also assist with radiotherapy and interventional procedures.

SubtlePET is a software product that uses deep neural network-based AI algorithms to reduce noise and enhance the structural quality of PET images, including PET/CT and PET/MRI scans. It integrates into existing clinical workflows by acting as a DICOM node to process and forward enhanced images, helping radiologists and nuclear medicine physicians better visualize and analyze PET scans for improved diagnostic confidence.