Related Experiment Video
Updated: Jul 7, 2026
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.7K
Artificial intelligence-based CT histogram parameters differentiating bronchiolar adenoma and lung adenocarcinomas: A
Wen Zhao1, Ziqian Zhao1, Yingxia Wang2
1Department of Medical imaging, the First Affiliated Hospital of Kunming Medical University, Yunnan, Kunming, China.
Plos One
|September 8, 2025
Summary
This study developed an AI-powered nomogram to differentiate benign bronchiolar adenoma (BA) from malignant lung adenocarcinoma (LAC). The tool integrates clinical data and AI-derived features, showing potential for improved non-invasive preoperative diagnosis.
Area of Science:
- Pulmonary Medicine
- Radiology
- Artificial Intelligence in Medicine
Background:
- Bronchiolar adenoma (BA) is a rare benign lung neoplasm.
- BA can be radiographically and microscopically mistaken for lung adenocarcinoma (LAC).
- Accurate preoperative distinction between BA and LAC is clinically important.
Purpose of the Study:
- To develop and validate a nomogram for distinguishing BA from LAC.
- To integrate clinical characteristics and AI-derived histogram parameters.
- To assess the diagnostic performance of the AI-based nomogram.
Main Methods:
- Retrospective study of 215 patients with pathologically confirmed BA or LAC.
- Development of a nomogram using clinical data and AI histogram parameters from a training cohort (n=151).
- External validation of the nomogram using a separate cohort (n=64).
Main Results:
- Significant differences in nodule density and various CT-derived parameters (diameters, surface area, volume, entropy) between BA and LAC groups.
- A nomogram incorporating density, 2D short diameter, and CT value variance achieved AUCs of 0.821 (training) and 0.811 (validation).
- AI-derived parameters showed significant differences between BA and LAC.
Conclusions:
- An AI-based nomogram can effectively distinguish between BA and LAC.
- The nomogram serves as a promising non-invasive preoperative diagnostic tool.
- This approach has the potential to improve diagnostic accuracy for pulmonary nodules.
