What question did this study set out to answer?

This study investigates how well an AI-based detection system identifies lung cancer on cardiac CT scans compared to radiologists.

May 16, 2026Open Access

Retrospective Evaluation of an AI-Based Computer-Aided Detection Algorithm for Lung Cancer Detection on Cardiac CT: A Multicenter Study

Key Points

This study investigates how well an AI-based detection system identifies lung cancer on cardiac CT scans compared to radiologists.
Retrospective multicenter analysis of 652 cardiac CT scans from 581 patients diagnosed with lung cancer.
Comparison of detection rates between AI-CAD and radiologists, including combined evaluations of both.
Characteristics of lesions detected and missed by each method were analyzed.
Radiologists had a detection rate of 76.2%, while AI-CAD had 77.4% (P = 0.551).
The combination of AI-CAD and radiologists improved the overall detection rate to 90.4% (P < 0.001).
AI-CAD showed higher detection rates for small, peripheral, and part-solid lesions and for limited-stage lung cancer (80.3% vs. 74.7%, P = 0.006).

Abstract

Background: To investigate the effectiveness of an artificial intelligence (AI)-based computer-aided detection (CAD) system in identifying incidental lung cancer on cardiac computed tomography (CT) scans and to compare its performance with that of radiologists.Methods: In this retrospective, multicenter study, 652 cardiac CT scans from 581 patients subsequently diagnosed with lung cancer were analyzed.A commercial AI-CAD system was employed to detect pulmonary lesions on cardiac CT.The detection rate of AI-CAD was compared to that of the radiologist, based on the radiology report, as well as to the detection rate when combining AI-CAD and the radiologist.The characteristics of the lesions detected and missed by the radiologist and AI-CAD were compared.Results: Radiologists and AI-CAD demonstrated similar detection rates for lung cancer (76.2% vs. 77.4%,P = 0.551).However, combining radiologists and AI-CAD significantly improved the detection rate to 90.4% (P 100 days, with 78.2% leading to stage progression.AI-CAD identified 58.5% of these diagnostic delays.Conclusion: AI-CAD demonstrated the potential to improve the detection rate of incidental lung cancer by identifying a subset of lesions that were initially overlooked by radiologists on cardiac CT.It exhibited particular strength in identifying early-stage cancers and small, subsolid lesions.

AI에게 질문

Bookmark

View Full Paper