ArticleQuantitative imaging in medicine and surgery2026
Has computer-aided diagnosis now outperformed radiologists in the accurate localization of lung nodules?-a multicenter retrospective study.
Article in Quantitative imaging in medicine and surgery, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
12 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Background: Globally, lung cancer is one of the most frequently diagnosed cancers and the leading cause of cancer-related death. Manual radiologist (RAD) reading brings inconsistent localization results for subtle nodules, while existing computer-aided diagnosis (CAD) tools lack verified three-dimensional (3D) positioning accuracy compared with human readers. Thus, the aim of this study was to compare 3D localization accuracy of CAD and RAD evaluations for pulmonary nodules on computed tomography (CT) images. Methods: This multicenter retrospective study included 1,275 patients' chest thin-section CT images from 3 centers. CT images were evaluated via a radiologist (RAD) assessment and a CAD tool. The CAD system was developed using a high-precision convolutional neural network (U-Net) for 3D localization of pulmonary nodules. The gold standard for nodule localization was established based on surgical findings, postoperative histopathological confirmation of the resected specimens, and correlation with preoperative CT images. Results: In Center 1 (921 pulmonary nodules), CAD and RAD correctly located 856 and 758 pulmonary nodules, with accuracy rates of 92.9% [95% confidence interval (CI), 91.1-94.4%] and 82.3% (95% CI, 79.7-84.6%), respectively. In Center 2 (145 pulmonary nodules), CAD and RAD correctly located 141 and 112 pulmonary nodules, with accuracy rates of 97.2% (95% CI, 94.54-99.90%) and 77.2% (95% CI, 70.39-84.05%), respectively. In Center 3 (209 pulmonary nodules), CAD and RAD correctly located 196 and 163 pulmonary nodules, with accuracy rates of 93.8% (95% CI, 90.53-97.07%) and 78% (95% CI, 72.38-83.62%), respectively. In all three centers, the accuracy rate using CAD was significantly greater than that using RAD (all P<0.001). Conclusions: Compared with manual detection by radiologists, the use of CAD increased the accuracy rate for 3D localization of pulmonary nodules.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.