Establishment and verification of a prediction model based on clinical characteristics and computed tomography radiomics parameters for distinguishing benign and malignant pulmonary nodules

Q: What was the study objective?

To establish and verify a clinical-radiomics nomogram that combines clinical characteristics and CT radiomics parameters to distinguish benign from malignant pulmonary nodules before surgery or biopsy.

Q: How were radiomics features selected for the model?

The study extracted a large set of tumor characteristics from segmented CT images, removed features with poor reproducibility and high redundancy, then used LASSO logistic regression with 10-fold cross-validation followed by multivariate logistic regression to identify independent predictors.

Q: Which predictors were found to be independently associated with malignancy?

Independent influencing factors included carcinoembryonic antigen (CEA), CT radiomics score, and cytokeratin-19-fragment (CYFRA21-1), along with four selected radiomic features used in the nomogram.

Sep 21, 2026

Upload by Ava Thompson

A retrospective clinical-radiomics study develops and verifies a CT-based prediction approach to differentiate benign versus malignant pulmonary nodules using both clinical biomarkers and radiomics features. Patients underwent high-resolution CT, with lesion segmentation and feature reduction to remove poor-reproducibility and high-redundancy variables. LASSO logistic regression and multivariate logistic regression identified key predictors, followed by construction of a radiomics nomogram. Model performance was assessed through ROC, calibration curves, and decision curve analysis, showing strong discrimination and clinical utility.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Methods

Results

Conclusions

Keywords and Study Timeline

Highlight Box

Establishment and verification of a prediction model based on clinical characteristics and computed tomography radiomics parameters for distinguishing benign and malignant pulmonary nodules Xiaohui Hou 1,2, Meng Wu3, Jingjing Chen 1, Rui Zhang1, Yan Wang3, Shuwen Zhang1, Zaixin Yuan 1,4, Jian Feng1, Liqin Xu1 1Department of Respiratory and Critical Care Medicine, Affiliated Hospital of Nantong University, Nantong, China; 2Department of Geriatric Medicine, Province Veterans Hospital, Wuxi, China; 3Department of Pathology, Affiliated Hospital of Nantong University, Nantong, China; 4Respiratory and Severe Disease, Nantong University, Nantong, China Contributions: (I) Conception and design: X Hou, L Xu; (II) Administrative support: L Xu; (III) Provision of study materials or patients: M Wu, J Chen; (IV) Collection and assembly of data: R Zhang, Y Wang; (V) Data analysis and interpretation: S Zhang, J Feng, Z Yuan; (VI) Manuscript writing: All authors; (VII) Final approval of manuscript: All authors. Correspondence to: Liqin Xu, MD. Department of Respiratory and Critical Care Medicine, Affiliated Hospital of Nantong University, 20 Xi-Si Road, Nantong 226001, China. Email: [chongzi05@163.com](chongzi05@163.com). Background: The radiographic classification of pulmonary nodules into benign versus malignant categories is a pivotal component of early lung cancer diagnosis. The present study aimed to investigate clinical and computed tomography (CT) clinical-radiomics nomogram for preoperative differentiation of benign and malignant pulmonary nodules. Methods: This retrospective study included 342 patients with pulmonary nodules who underwent highresolution CT (HRCT) examination. We assigned them to a training dataset (n=239) and a validation dataset (n=103) . There are 1781 tumor characteristics quantified by extracted features from the lesion segmented from patients’CT images. The features with poor reproducibility and high redundancy were removed. Then a least absolute shrinkage and selection operator (LASSO) logistic regression model with 10-fold cross-validation was used to further select features and build radiomics signatures. The independent predictive factors were identified by multivariate logistic regression. A radiomics nomogram was developed to predict the malignant probability. The performance and clinical utility of the clinical-radiomics nomogram was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) . Results: After dimension reduction by the LASSO algorithm and multivariate logistic regression, four radiomic features were selected, including original_shape_Sphericity, exponential_glcm_Maximum Probability, log_sigma_2_0_mm_ 3D_glcm_Maximum Probability, and ogarithm_firstorder_ 90Percentile. Multivariate logistic regression showed that carcinoembryonic antigen (CEA) [odds ratio (OR) 95% confidence interval (CI): 1.40 (1.09–1.88)], CT rad score [OR (95% CI): 2.74 (2.03–3.85)], and cytokeratin- 19-fragment (CYFRA21-1) [OR (95% CI): 1.80 (1.14–2.94)] were independent influencing factors of malignant pulmonary nodule (all P<0.05) . The clinical-radiomics nomogram combining CEA, CYFRA21-1 and radiomics features achieved an area of curve (AUC) of 0.85 and 0.76 in the training group and verification group for the prediction of malignant pulmonary nodules. The clinical-radiomics nomogram demonstrated excellent agreement and practicality, as evidenced by the calibration curve and DCA. Conclusions: The clinical-radiomics nomogram combined of CT-based radiomics signature, along with CYFRA21-1 and CEA, demonstrated strong predictive ability, calibration, and clinical usefulness in distinguishing between benign and malignant pulmonary nodules. The use of CT-based radiomics has the potential to assist clinicians in making informed decisions prior to biopsy or surgery while avoiding unnecessary treatment for non-cancerous lesions. © Journal of Thor

FAQs

What was the study objective?

To establish and verify a clinical-radiomics nomogram that combines clinical characteristics and CT radiomics parameters to distinguish benign from malignant pulmonary nodules before surgery or biopsy.

How were radiomics features selected for the model?

The study extracted a large set of tumor characteristics from segmented CT images, removed features with poor reproducibility and high redundancy, then used LASSO logistic regression with 10-fold cross-validation followed by multivariate logistic regression to identify independent predictors.

Which predictors were found to be independently associated with malignancy?

Independent influencing factors included carcinoembryonic antigen (CEA), CT radiomics score, and cytokeratin-19-fragment (CYFRA21-1), along with four selected radiomic features used in the nomogram.

Sep 21, 2026

Upload by Ava Thompson