Siemens Healthineers’ AI-Based Chest CT Software Receives US FDA Clearance

By HospiMedica International staff writers

[15 Oct 2019]
Image: The AI-Rad Companion Chest CT automatically generates standardized, reproducible, and quantitative reports in DICOM SC format (Photo courtesy of Siemens Healthineers).

The US Food and Drug Administration (FDA) has cleared three modules of AI-Rad Companion Chest CT, an intelligent software assistant from Siemens Healthineers (Erlangen, Germany) that brings artificial intelligence (AI) to computed tomography (CT). Representing the first intelligent assistant of the new AI-Rad Companion platform, AI-Rad Companion Chest CT helps radiologists interpret images of the thorax (chest) quickly with desired accuracy and precision, and automatically documents these findings as structured reports.

The algorithms in AI-Rad Companion Chest CT have been trained on extensive datasets and annotated by qualified clinical specialists to provide segmentation, measurement, and highlighting of key anatomical structures, to support quantitative and qualitative analysis. Using CT images of the chest, AI-Rad Companion Chest CT differentiates among various structures in that region, including the lungs, heart, and aorta, highlights them individually, and marks and measures potential abnormalities, such as coronary calcifications.

It supports a variety of tasks, including automated detection of lesions, localization of abnormalities, and measurement of lung lesions; quantification of per-lobe low-attenuation parenchyma; enhanced visualization of lung lesions; automated segmentation of lung lobes and enhanced visualization of low-attenuation parenchyma; segmentation and measurement of maximum diameters of the thoracic aorta; quantification of the total calcium volume in the coronary arteries; and detection of nine anatomical landmarks as identified by American Heart Association (AHA) guidelines.

Based on the AI-supported analysis, AI-Rad Companion Chest CT automatically generates standardized, reproducible, and quantitative reports in Digital Imaging and Communications in Medicine (DICOM) SC format. In addition to reducing time spent on manual results documentation, these reports can be accessed by radiologists on the picture archiving and communication system (PACS) in the clinical routine. AI-Rad Companion Chest CT also highlights potentially clinically relevant changes that might otherwise remain unnoticed because they were not the primary indication for the exam.

“AI-Rad Companion Chest CT builds on our decades-long expertise in AI and machine learning, digitalizing healthcare and helping providers perform multi-organ image interpretation of the chest with enhanced detection, accuracy, and precision, which can potentially improve outcomes,” said David Pacitti, President and Head of the Americas at Siemens Healthineers.