Optimising Renal Tumour Management Through Artificial Intelligence Modules

In this study, AI model will explore and clarify features in renal tumor CT images and pathological images that are difficult to detect manually, and then correlate them with clinical outcomes, thereby improving the diagnosis and treatment process for renal tumors. Firstly, the model can accurately distinguish renal tumor subtypes and predict stage, grade, and complexity so as to svoid misdiagnosis and assist clinicians in formulating treatment plans. Secondly, by learning from surgical videos, the model can provide additional information during surgerys, such as important anatomical landmarks, location of tumors. Finally, combining radiomics and pathomics, the model can differentiate between high-risk and low-risk patients after surgery, thus providing personalized prognostic guidance.

Inclusion criteria

• Patients with renal tumor which can be treated by surgery;
• Complete CECT within 30 days before surgery;
• Patients who fully understand this study and sign the informed consent;

Exclusion criteria

• Patients with any item missing from the baseline clinical and pathological information;
• Patients who has already metastasized by the time the tumor is discovered;
• Previous treatment in any form, including surgery, targeted therapy and immunotherapy;