Diagnostic Accuracy of Ct-Based Radiomics Models in Differentiating Lung Cancer From Tuberculosis in Pulmonary Lesions: A Systematic Review and Meta-Analysis Publisher Pubmed



Sahrai H ; Behnood J ; Baradaran M ; Khalaji A ; Norouzi A ; Shojaeshafiei F ; Seyed Ebrahimi SM ; Mohammadzadeh S ; Hajiesmailpoor Z ; Shahidi R
Source: BMC Cancer Published:2026

Abstract

Background: Distinguishing lung cancer (LC) from pulmonary tuberculosis (TB) on CT is difficult. We synthesized evidence on radiomics, clinical, and combined models for LC–TB discrimination. Methods: PubMed, Web of Science, Embase, and Scopus were searched to August 2025 following PRISMA. Metrics were harmonized to LC-positive/TB-negative and pooled with a bivariate random-effects model. Study quality was assessed with QUADAS-2 and METRICS. Results: Fourteen retrospective studies (4281 participants) were included. Radiomics models (11 validations cohorts) achieved pooled sensitivity 0.80 (95% CI 0.74–0.86) and specificity 0.83 (0.75–0.88); SROC AUC 0.88 (0.85–0.91). At a 25% pre-test probability, radiomics models corresponded to post-test probabilities of 61% and 7%. Deeks’ funnel asymmetry test showed no small-study effects (p = 0.88). Clinical-only models performed more modestly (sensitivity 0.60, specificity 0.80, AUC 0.77). Combined radiomics + clinical models performed best (sensitivity 0.82, specificity 0.93, AUC 0.90). Head-to-head comparison showed higher specificity for radiomics versus clinical models (p = 0.02), and higher sensitivity for combined models versus radiomics (p < 0.001) without a clear specificity difference (p = 0.41). Prespecified subgroup analyses indicated that models retaining > 10 radiomic features, developed in cohorts restricted to nodules < 3 cm, and using non-contrast CT tended to perform better, whereas externally validated cohorts showed lower accuracy than internal test sets, and both nodule-size spectrum and CT acquisition phase emerged as major contributors to between-study heterogeneity. Conclusions: CT-based radiomics adds discriminative value beyond clinical variables, and integrating clinical information with radiomics yields the most favorable overall accuracy while highlighting the importance of broader external validation. © The Author(s) 2025.