A radiomics and machine learning-based method for dynamic assessment of tumor burden after neoadjuvant therapy in esophageal cancer

Conventional response evaluation criteria primarily rely on tumor size reduction to assess the efficacy of neoadjuvant therapy (NAT) in esophageal cancer. However, these morphological assessments often fail to capture the underlying biological changes, as some patients achieve substantial pathological response without marked tumor shrinkage. To address this limitation, we introduced the concept of tumor burden (TB), integrating both tumor volume (TV) and tumor regression grade (TRG), and proposed four novel parameters—TV change ratio (TVCR), pre-NAT mean cross-sectional area (Pre-NT MCSA), post-NAT MCSA (Post-NT MCSA), and post-NAT mean cross-sectional TB (Post-NT MCTB)—to better quantify residual disease. We conducted a retrospective study of 204 esophageal cancer patients who underwent NAT followed by minimally invasive esophagectomy between September 2019 and September 2024. The relationships between the four novel parameters and resection status were evaluated. Subsequently, a radiomics-based random forest model was developed to predict post-NAT TB (Post-NT TB) from pre- and post-NAT CT images. Among the four parameters, only Post-NT MCTB showed a significant association with resection status (p < 0.01), confirming its clinical relevance in reflecting residual TB. The radiomics-based model demonstrated robust predictive performance, achieving a coefficient of determination (R²) of 0.85 in the test set. Post-NT MCTB serves as a clinically relevant indicator of residual TB after NAT, surpassing traditional volume-based assessment. This radiomics-based framework enables dynamic and quantitative evaluation that may assist preoperative planning in esophageal cancer.