CT image of the lungs with AI-supported automatic highlighting, quantification and measurement of anatomy and deviations.
Image courtesy of Siemens Healthineers
AI-Rad Companion Chest CT, an intelligent software assistant for radiology, has recently received the CE mark, which means Siemens Healthineers can start marketing this artificial intelligence (AI)-based software as a medical product in Europe effective immediately. AI- Rad Companion Chest CT helps radiologists interpret CT images of the thorax faster and more precisely, and to document the findings in less time with the help of automatic measurements.
AI-Rad Companion Chest CT is the first AI-based application on the new AI-Rad Companion platform, and is vendor-neutral, which means the software can evaluate image data from many CT systems from different manufacturers. Siemens Healthineers plans to expand this platform so that more and more intelligent algorithms will be available for additional organs and modalities. This will enable the company to consistently expand its portfolio of effective solutions for AI-based clinical decision support.
“We introduced the first AI-based assistant in our AI-Rad Companion product line, AI-Rad Companion Chest CT, at RSNA 2018 in November last year,” says Dr. Razvan Ionasec, director in charge of AI-Rad Companion at Siemens Healthineers. “We are pleased to be able to offer our customers in Europe this first AI-based assistant for use in clinical practice effective immediately. I can see huge potential in this new product line for growth in key areas of medicine and to provide support for physicians in their clinical decision-making processes.”
Heart with coronary arteries recognized and segmented from thoracic CT images highlighted in green by AI-Rad Companion Chest CT including measurements of calcifications of the coronary arteries.
Image courtesy Siemens Healthineers
“Results delivered by radiologists can vary by some 10-20 percent, depending on the investigator,” comments Dr. Bram Stieltjes, Head, Research Coordination Radiology and Nuclear Medicine, University Hospital Basel. “Algorithm-based diagnostics completely obviate this variability, generating constant results. That alone is a huge advantage of AI platforms like AI-Rad Companion.”
Using CT images of the thorax, the software can differentiate between the various structures of the chest, highlight them individually, and mark and measure potential abnormalities automatically. This applies equally to organs such as the heart and lungs, aorta, and vertebral bodies. The software automatically turns the findings into a quantitative report, which can be called up via the image viewing system used by the radiologist in the clinical routine. In certain circumstances, the intelligent assistant also alerts physicians to potential abnormalities that would otherwise have been missed because they were not the focus of the original examination, e.g. chance discoveries of pathological dilations of the aorta (aneurysms).
“Examination using a chest CT is a procedure often used in everyday clinical practice,” says André Hartung, head of CT at Siemens Healthineers.
“For radiologists, this means more examinations in a limited amount of time and usually for low reimbursement rates. AI-Rad Companion Chest CT is a tool that can actually simultaneously increase productivity and quality in diagnostic radiology. This is a big step on our way to becoming a leader in clinical decision making”.
AI-Rad Companion Chest CT is a cloud-based solution and uses certified, secure teamplay infrastructure that complies with the Health Information Portability and Accountability Act (HIPAA) in the U.S., and with the General Data Protection Regulation (GDPR) in the EU. The software conforms to Digital Imaging and Communications in Medicine (DICOM) standards. The images and all supporting information can be made automatically available in the picture archiving and communication system (PACS) in line with the radiologist’s individual requirements.