Habitat-Based Radiomics Model of Pretreatment CT to Predict Pathological Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoimmunotherapy: A Multicenter Prospective Study
In brief
CT radiomics model predicts chemoimmunotherapy response in esophageal cancer with 93% accuracy
In a prospective multicenter cohort of 215 patients with locally advanced esophageal squamous cell carcinoma, a machine-learning model that combined intratumoral and peritumoral CT habitat features achieved an area under the curve of 0.93, correctly identifying responders 79% of the time and non-responders 93% of the time. The approach could help tailor neoadjuvant therapy, but needs validation in larger, diverse populations before routine use.
- Journal
- Academic radiology (Q1)
- Published
- 10 August 2026
- Study design
- Randomized controlled trial
- Evidence level
- Level 1, High (CEBM 1b)
- Authors
- Xiaolong Yang, Ping Wang, Yingjie Li, Zhubin Wen, Huiting Zhang, Shuang Liang, et al.
- PMID
- 42575807
- DOI
- 10.1016/j.acra.2026.07.028
Why clinicians should know about it
- Picked for Radiology, Radiation Oncology, Nuclear Medicine, Medical Physics and Imaging (top studies of the week, 16 August 2026): CT radiomics predicts response to neoadjuvant chemoimmunotherapy
Abstract
RATIONALE AND OBJECTIVES: Neoadjuvant chemoimmunotherapy (NCIT) has shown promising efficacy in locally advanced esophageal squamous cell carcinoma (LA-ESCC), yet pretreatment predictors for treatment response remain to be identified. This study aimed to evaluate a pretreatment CT-based habitat radiomics model for predicting pathological response in LA-ESCC treated with NCIT. MATERIALS AND METHODS: This prospective multicenter study enrolled 215 patients with LA-ESCC receiving NCIT from three centers. Patients from Center A were randomly allocated to training (n = 110, 70%) and validation (n = 47, 30%) sets, with those from Centers B (n = 33) and C (n = 25) as an external test set. Responders and nonresponders were classified by tumor regression grades. Conventional and habitat radiomics features were extracted from intratumoral and peritumoral regions. Fourteen machine-learning (ML) classifiers were used to build intratumoral, peritumoral, and combined habitat radiomics models, along with corresponding conventional models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). Shapley Additive Explanations (SHAP) analysis was employed for model interpretation. RESULTS: The habitat radiomics models outperformed conventional radiomics models. The combined intratumoral and peritumoral habitat radiomics model achieved an AUC of 0.93 (95% CI: 0.84-0.98), accuracy of 0.83, sensitivity of 0.79, and specificity of 0.93 in the external test set. SHAP analysis revealed that both intratumoral and peritumoral habitat radiomics features contributed significantly to predictive performance. CONCLUSION: The interpretable ML model combining intratumoral and peritumoral habitat radiomics features accurately predicts the response of LA-ESCC to NCIT.
Abstract as published, via PubMed.
For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.