Radiomics Applications in Esophageal Cancer Prognosis

Radiomics has emerged as a transformative approach in esophageal cancer prognosis by converting routine medical images into high-dimensional, mineable data. Quantitative features extracted from CT, PET or MRI scans characterise tumour phenotypes such as heterogeneity, shape and texture. When coupled with machine-learning algorithms, these features enable non-invasive risk stratification, early prediction of treatment response and personalised survival forecasting. Key applications include predicting pathological complete response after neoadjuvant chemoradiotherapy, estimating risk of postoperative recurrence and forecasting overall survival. Radiomic nomograms integrate selected imaging biomarkers with clinical or molecular variables to generate individualised risk scores, guiding therapeutic decision-making and follow-up strategies. Advances in delta-radiomics capture temporal changes during treatment, while multimodal integration with genomic and haematologic parameters further refines prognostic accuracy. Ongoing efforts focus on standardising image acquisition, ensuring feature reproducibility and conducting large-scale external validations to support clinical translation.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Radiomics Applications in Esophageal Cancer Prognosis publication trend

The graph below shows the total number of articles in radiomics applications in esophageal cancer prognosis across all publications each year (not limited to Nature Index journals).

Technical terms

Radiomics: Extraction of quantitative imaging features to characterise tumour phenotype and microenvironment.

Nomogram: Graphical tool representing a multivariate predictive model to estimate the probability of a clinical outcome.

Delta-radiomics: Analysis of changes in radiomic features between sequential imaging time points to assess treatment effects.

Least absolute shrinkage and selection operator (LASSO): Regularisation method that selects the most predictive features by penalising regression coefficients.

Area under the receiver operating characteristic curve (AUC): Measure of a model’s ability to discriminate between binary outcomes.

Concordance index (C-index): Metric evaluating the predictive accuracy of survival models by assessing concordance between predicted and observed event times.

References

1. Model integrating CT-based radiomics and genomics for survival prediction in esophageal cancer patients receiving definitive chemoradiotherapy. Biomarker Research (2023).
2. CT-based delta-radiomics nomogram to predict pathological complete response after neoadjuvant chemoradiotherapy in esophageal squamous cell carcinoma patients. Journal of Translational Medicine (2024).
3. CT-based radiomics combined with hematologic parameters for survival prediction in locally advanced esophageal cancer patients receiving definitive chemoradiotherapy. Insights into Imaging (2024).
4. Development and Validation of a Radiomics Nomogram Model for Predicting Postoperative Recurrence in Patients With Esophageal Squamous Cell Cancer Who Achieved pCR After Neoadjuvant Chemoradiotherapy Followed by Surgery. Frontiers in Oncology (2020).