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.
AI-Rad Companion (Pulmonary) is image processing software that provides quantitative and qualitative analysis from previously acquired Computed Tomography DICOM images to support radiologists and physicians from emergency medicine, specialty care, urgent care, and general practice in the evaluation and assessment of disease of the lungs.
AI-Rad Companion (Pulmonary) is a software extension operating on the AI-Rad Companion (Engine) platform, using machine-learning and deep-learning algorithms to post-process CT DICOM images. Core functionalities include segmentation of lungs and lobes, opacity region detection via AI and thresholding, lesion segmentation and measurements, and producing results in image and DICOM Structured Report formats. The software integrates with external medical devices like syngo.CT Lung CAD and supports cloud and edge deployments.
Non-clinical integration and functional tests demonstrated the device performs as intended. Clinical validation included evaluation of lung lobe segmentation with average DICE scores between 0.94 and 0.96 on 250 datasets and opacity detection validated on 150 datasets with 93.0% agreement within human reader variability limits. Performance was consistent across various subgroups and datasets. Risk analysis and standards compliance support safety and effectiveness.
No predicate devices specified
Submission
9/24/2021
FDA Approval
12/6/2021
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.