Related Experiment Video
Updated: Jun 3, 2026
Point-of-Care Lung Ultrasound in Adults: Image Acquisition
Published on: March 3, 2023
Nomogram for predicting malignancy in subpleural pulmonary lesions using clinical and contrast-enhanced ultrasound
Lei Hao1, Lijing Zhu2, Zhuojun Qi3
1Medical Imaging Department of Shanxi Medical University, Departments of Ultrasound, Second Hospital of Shanxi Medical University, Taiyuan.
Aim:
To develop and validate an individualized nomogram for differentiating benign from malignant SPLs based on contrast-enhanced ultrasound (CEUS) imaging features and clinical data.
Materials And Methods:
A total of 407 patients with SPLs from our hospital (201 benign, 206 malignant) were randomly divided into development (n=284) and internal validation (n=123) cohorts using a 7:3 ratio. Candidate variables were selected using Boruta analysis and multivariable logistic regression. Model performance was evaluated with respect to discrimination, calibration, and clinical utility. To further assess generalizability, external validation cohort was performed in 106 patients (51 benign, 55 malignant) from an independent hospital.
Results:
The nomogram, incorporating six variables-age, maximum diameter, homogeneity, vascular sign, AT difference ratio, and visceral pleural invasion-demonstrated high discriminatory performance with area under the curve (AUC) values of 0.949 in the development cohort, 0.908 in the internal validation cohort, and 0.941 in the external validation cohort. Calibration curves indicated good agreement between predicted and observed outcomes. Decision curve analysis (DCA), clinical impact curves (CIC), and net reduction curves (NRC) supported the model's clinical utility.
Conclusion:
The validated nomogram shows strong potential as a practical tool for aiding clinical decision-making in differentiating malignant SPLs.