Diagnostic Accuracy of Deep Learning and Radiomics in Lung Cancer Staging: A Systematic Review and Meta-Analysis

Abstract

Background: Artificial intelligence has far surpassed previous related technologies in image recognition and is increasingly used in medical image analysis. We aimed to explore the diagnostic accuracy of the models based on deep learning or radiomics for lung cancer staging.

Methods: Studies were systematically reviewed using literature searches from PubMed, EMBASE, Web of Science, and Wanfang Database, according to PRISMA guidelines. Studies about the diagnostic accuracy of radiomics and deep learning, including the identifications of lung cancer, tumor types, malignant lung nodules and lymph node metastase, were included. After identifying the articles, the methodological quality was assessed using the QUADAS-2 checklist. We extracted the characteristic of each study; the sensitivity, specificity, and AUROC for lung cancer diagnosis were summarized for subgroup analysis.

Results: The systematic review identified 19 eligible studies, of which 14 used radiomics models and 5 used deep learning models. The pooled AUROC of 7 studies to determine whether patients had lung cancer was 0.83 (95% CI 0.78-0.88). The pooled AUROC of 9 studies to determine whether patients had NSCLC was 0.78 (95% CI 0.73-0.83). The pooled AUROC of the 6 studies that determined patients had malignant lung nodules was 0.79 (95% CI 0.77-0.82). The pooled AUROC of the other 6 studies that determined whether patients had lymph node metastases was 0.74 (95% CI 0.66-0.82).

Conclusion: The models based on deep learning or radiomics have the potential to improve diagnostic accuracy for lung cancer staging.

Systematic review registration: https://inplasy.com/inplasy-2022-3-0167/, identifier: INPLASY202230167.

Keywords: deep learning; diagnostic accuracy; lung cancer; lymph node metastasis; meta-analysis; radiomics.