Philips Introduces AI-Enhanced CT System for High-Volume Radiology Screening Programs
The artificial intelligence (AI)-enabled CT 3500 system reportedly reduces patient positioning time by 23 percent, improves low-contrast detectability by 60 percent and facilitates up to an 80 percent reduction in radiation dosing.
Philips has launched the CT 3500, a new computed tomography (CT) system that offers a variety of artificial intelligence (AI)-powered features for bolstering the efficiency of radiology workflows and enhancing image quality.
Key features of the CT 3500 system for improving radiology workflows include Precise Position, which provides automated determinations of patient orientation. Philips said this feature reduces patient positioning time by up to 23 percent and increases positioning accuracy by 50 percent.
The CT 3500 system also offers AI-based reconstruction via the Precise Image feature, which facilitates up to an 85 percent in noise and an 80 percent reduction in radiation dosing while achieving up to a 60 percent improvement in low-contrast detectability.
“Today, many radiology departments scan hundreds of patients a day. We’ve engineered the Philips CT 3500 to reduce the pain points that these high-volume departments face by developing a versatile, reliable, high-throughput imaging solution. It automates radiographers’ most time-consuming steps so that they can spend more time focusing on the patient,” noted Frans Venker, the general manager of computed tomography at Philips.
(Editor’s note: For related content, see “Study Shows Significant Incidental Findings in Nearly 34 Percent of Lung Screening CT Exams” and “AI-Based Denoising Technique Achieves 76 Percent Reduction in Radiation Dosing for CT Lung Cancer Screening.”)
Considering Breast- and Lesion-Level Assessments with Mammography AI: What New Research Reveals
June 27th 2025While there was a decline of AUC for mammography AI software from breast-level assessments to lesion-level evaluation, the authors of a new study, involving 1,200 women, found that AI offered over a seven percent higher AUC for lesion-level interpretation in comparison to unassisted expert readers.
