Multimodal Prediction of Postoperative Prognosis After Partial Nephrectomy for Endophytic Renal Cell Carcinoma

This retrospective observational cohort study aims to develop and externally validate an imaging-clinical multimodal fusion model for predicting postoperative prognosis in patients with endophytic renal cell carcinoma undergoing partial nephrectomy. Preoperative computed tomography imaging features, three-dimensional reconstruction-derived tumor characteristics, radiomics features, and clinical variables will be integrated using machine learning and deep learning approaches. The primary objective is to evaluate whether the multimodal model improves prediction of postoperative prognostic outcomes compared with single-modality models based on clinical or imaging features alone.

Inclusion Criteria: * Patients diagnosed with renal cell carcinoma. Patients with endophytic renal tumors based on preoperative imaging assessment. Patients who underwent partial nephrectomy. Available preoperative contrast-enhanced computed tomography images. Available clinical, pathological, perioperative, and postoperative follow-up data. Age 18 years or older at the time of surgery. Exclusion Criteria: * Patients who underwent radical nephrectomy as the primary surgical treatment. Patients with missing or poor-quality preoperative imaging data. Patients with incomplete key clinical, pathological, or follow-up information. Patients with hereditary renal cancer syndromes. Patients with bilateral renal tumors or solitary kidney. Patients who received neoadjuvant systemic therapy before partial nephrectomy.