Lunit Insight CXR ranked top for lung nodule detection in independent study

In an independent study published in Radiology¹, researchers from Radboud University in the Netherlands assessed the stand-alone performance of commercially-available AI software for lung nodule detection. Out of the 14 vendors of CE-marked AI software for chest x-rays (CXR) invited to participate, seven accepted the challenge. Results were measured in AUC, sensitivity and specificity.

RESULTS: Lunit Insight CXR ranked #1 for overall lung nodule detection. Lunit reports “It outperformed all other participating AI vendors for all categories of nodule conspicuity and size. This study provides valuable insights to assist healthcare professionals in their choice of chest x-ray AI solutions.”

Lunit Insight CXR is designed to streamline CXR readings, detecting and locating the presence of the most clinically-significant abnormalities with precision. Its unique auto-comparison feature facilitates the comparison of lesion sizes between current and prior CXRs, highlighting changes in pleural effusion, consolidation, and pneumothorax. Designed for versatility, its intended use covers paediatric applications. Its performance on a paediatric population was presented during ECR 2024² in Vienna, Austria.

Lunit will be showcasing its portfolio of AI solutions for radiology at UKIO, including its chest x-ray AI, breast AI suite and MSK AI offering.

Visit Lunit on stand B34 for hands-on demonstrations and to discover how Lunit can help you optimise diagnostics workflow. A Lunit-sponsored session takes place on June 11 at 12:55 in the Service Hub, where Dr Nisha Sharma and Dr Sarim Ather will be presenting.

Contact the Lunit team if you would like to secure your appointment: marketing.uk@lunit.io.

This news story has been sponsored by the companies concerned and does not represent the views or opinions of RAD Magazine.  Visit our dedicated UKIO conference page to find out more.

References

1. van Leeuwen, Kicky G et al. “Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction.” Radiology vol. 310,1 (2024): e230981
2. Helen. Ngo, et al., “Deep Learning for Chest Radiograph Evaluation in Children: Repurposed Use of a Commercially Available AI Tool Developed for Adults” In: European Congress of Radiology; 2024 Feb 28 – March 3; Vienna, Austria: ESR 2024. EPOS