Scholarlink

Background <p>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.</p> Methods <p>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.</p> Results <p>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 (<i>p</i> = 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 (<i>p</i> = 0.02), and higher sensitivity for combined models versus radiomics (<i>p</i> &lt; 0.001) without a clear specificity difference (<i>p</i> = 0.41). Prespecified subgroup analyses indicated that models retaining &gt; 10 radiomic features, developed in cohorts restricted to nodules &lt; 3&#xa0;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.</p> Conclusions <p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Diagnostic accuracy of CT-based radiomics models in differentiating lung cancer from tuberculosis in pulmonary lesions: a systematic review and meta-analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月17日

查看全文
  • Hadi Sahrai,
  • Jamal Behnood,
  • Mansoureh Baradaran,
  • Amirreza Khalaji,
  • Ali Norouzi,
  • Farzaneh Shojaeshafiei,
  • Seyedeh Mahdieh Seyed Ebrahimi,
  • Sanam Mohammadzadeh,
  • Zanyar HajiEsmailpoor,
  • Ramin Shahidi

摘要

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.