Radiomics in predicting treatment response in non-small-cell lung cancer: current status, challenges and future...

Area of Science:

• Quantitative medical imaging analysis in oncology.
• Development of predictive models for personalized medicine.

Background:

• Radiomics extracts quantitative data from medical images to characterize tumor phenotypes.
• Predictive models for treatment response are crucial for personalized medicine.

Purpose of the Study:

• To review the current status of radiomics research in predicting non-small-cell lung cancer (NSCLC) treatment response.
• To evaluate the scientific and reporting quality of this research.

Main Methods:

• A comprehensive literature search of the PubMed database was performed.
• 14 peer-reviewed articles were included after screening 178 articles.
• The Radiomics Quality Score (RQS) was used to assess study quality.

Main Results:

• Studies identified various predictive radiomic markers (e.g., kurtosis, grey-level uniformity, wavelet features, PET parameters).
• Quality assessment revealed a low median RQS (2.5), indicating poor reproducibility and clinical evaluation.
• Significant heterogeneity existed across studies regarding patient populations, cancer stages, treatments, and methodologies.

Conclusions:

• Radiomics has not yet been translated into clinical practice for NSCLC treatment response prediction.
• Standardization, collaboration, and external validation are essential for developing reproducible radiomic predictors.
• Clinical pathway evaluation is necessary before implementing radiomics as a decision-making tool for personalized NSCLC treatment.