Chest radiography remains fundamental to population-based health screening, particularly in Japan. However, lung cancer detection on chest radiographs is challenging, especially without thoracic imaging specialists. We retrospectively analyzed 18,810 chest radiographs obtained during routine health screening to evaluate the diagnostic performance and clinical utility of commercially available artificial intelligence (AI)-based computer-aided detection (CAD) systems for lung cancer screening. Two AI-CAD systems, EIRL X-Ray Lung Nodule and EIRL Chest XR, including sensitivity- and specificity-prioritized models, were compared with physician interpretation. Diagnostic metrics included cancer detection rate, sensitivity, specificity, and positive predictive value (PPV). All AI models exceeded the predefined lung cancer detection benchmark of 0.03% and outperformed physicians. EIRL Chest XR achieved higher cancer detection rates than EIRL X-Ray Lung Nodule, while the specificity-prioritized model improved PPV without compromising detection performance. These findings suggest that AI-assisted chest radiography may reduce false-negative assessments and support physician decision-making in routine clinical practice.

Background/Objectives: Despite high sensitivity in deep learning models for identifying candidate locations of unruptured cerebral aneurysms (UCAs), excessive false-positive (FP) findings and insufficient characterization of their anatomical distribution remain barriers to clinical integration. We evaluated a multi-stage deep learning framework for reducing anatomy-specific FPs in TOF-MRA-based UCA screening. Methods: This retrospective multicenter study analyzed TOF-MRA images from 404 scans across seven institutions. A baseline model (Model-A) was compared with an updated model (Model-B) incorporating a secondary cluster-filtering algorithm. Reference standards were established by expert reviewers. Aneurysm-wise sensitivity was compared using McNemar’s test, FPs per case using the Wilcoxon signed-rank test, and FP distributions by vascular location. Results: Aneurysm-wise sensitivity was 94.3% (231/245) for Model-A and 93.9% (230/245) for Model-B, with 1.16 and 0.879 FPs per case, respectively, representing a significant 24% FP reduction (p < 0.001). Per-aneurysm sensitivity did not differ significantly (McNemar’s test, p = 1.00). Model-B suppressed mimics in the internal carotid artery (ICA) and middle cerebral artery (MCA). Aneurysms were most frequent in the ICA (29%) and MCA (22%). Setting Model-A FPs as 100%, ICA and MCA accounted for 47.1% and 11.3% in Model-A and decreased to 34.5% and 7.7% in Model-B. In an exploratory regional analysis with Holm adjustment, FP reductions remained significant in the ICA (adjusted p < 0.001) and MCA (adjusted p = 0.003). Conclusions: A secondary cluster-filtering algorithm reduced FP candidate findings by 24% with similar sensitivity point estimates (paired difference −0.4 percentage points, 95% CI −3.1 to +2.1). Region-specific error analysis revealed the anatomical dependency of FP reduction. The impact on reading workflow and patient outcomes requires prospective evaluation.