Radiomics in Lung Cancer Imaging: A Narrative Review of Current Evidence

Area of Science:

• Quantitative medical imaging analysis
• Radiomics in oncology
• Thoracic imaging applications

Background:

• Lung cancer is a leading cause of cancer mortality, with early diagnosis and stratification posing clinical challenges.
• Radiomics, a quantitative imaging approach, offers potential for lung cancer diagnosis, prognosis, and treatment response assessment.
• Clinical translation of radiomics is hindered by methodological inconsistencies and lack of standardization.

Purpose of the Study:

• To review evidence on radiomics in thoracic imaging for lung cancer.
• To focus on clinical applications, methodological limitations, and translational challenges.
• To synthesize findings from systematic reviews and meta-analyses.

Main Methods:

• Systematic literature search in PubMed and Scopus.
• Inclusion of peer-reviewed systematic reviews and meta-analyses on radiomics in lung cancer.
• Narrative synthesis using a structured approach and an integrative framework.

Main Results:

• Radiomics shows consistent potential in lesion classification, histological differentiation, molecular profiling, prognostic stratification, and treatment response prediction.
• Machine learning and deep learning enhance predictive performance in radiomics.
• Key limitations include imaging protocol heterogeneity, lack of external validation, small datasets, and poor reproducibility.

Conclusions:

• Radiomics in lung cancer imaging holds significant clinical potential.
• Methodological and translational barriers must be overcome for widespread adoption.
• Future progress requires standardization, external validation, multimodal data integration, and improved interpretability.