Overview
This study aims to develop and validate a deep learning model to predict pathological complete response (pCR) in patients with esophageal squamous cell carcinoma who have undergone neoadjuvant immunochemotherapy. Clinical, imaging, and pathological data from previously treated patients will be collected and analyzed. The model is expected to assist in predicting treatment outcomes and guide personalized therapeutic strategies.
Description
This multicenter retrospective study will collect chest CT images and clinical data from patients with esophageal squamous cell carcinoma (ESCC) who underwent surgery following neoadjuvant immunochemotherapy between January 2019 and July 2025. Deep learning features will be extracted from the CT images to develop a predictive model of pathological complete response (pCR). The model's performance will be evaluated using metrics including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Additionally, SHapley Additive exPlanations (SHAP) analysis will be employed to quantify the contribution of CT imaging features to the model's predictions. This study aims to improve early identification of responders to neoadjuvant immunochemotherapy and support personalized treatment strategies for ESCC patients.
Eligibility
Inclusion Criteria:
- Pathologically confirmed esophageal squamous cell carcinoma (ESCC).
- Received at least one cycle of neoadjuvant chemotherapy combined with immunotherapy.
- Underwent contrast-enhanced chest CT before initiation of neoadjuvant treatment.
- Underwent contrast-enhanced chest CT after completion of neoadjuvant treatment and prior to surgery.
Exclusion Criteria:
- Diagnosis of other malignancies.
- Received other anti-tumor therapies before or during neoadjuvant chemo-immunotherapy.
- Incomplete clinical data.
- Poor-quality CT imaging.