Kidney cancer
Conditions
Interventions
Renal-FM diagnosis evaluation group :None
Sponsors
Zhongshan Hospital, Fudan University
Eligibility
Sex/Gender
All
Age
18 Years to 80 Years
Inclusion criteria
Inclusion criteria: 1. Inclusion Criteria for CT Imaging Diagnosis Assessment: (1) Age >= 18 years and = 18 years and <= 80 years; (2) Patients who underwent partial nephrectomy or radical nephrectomy at participating centers (Zhongshan Hospital Affiliated to Fudan University, Qilu Hospital of Shandong University, Linyi People's Hospital, Zhongshan Hospital Xiamen Branch); (3) Postoperative histopathological diagnosis confirmed as renal cell carcinoma; (4) Accessible, quality-standard hematoxylin and eosin (H&E)-stained pathological slides.
Exclusion criteria
Exclusion criteria: 1. Exclusion Criteria for CT Imaging Diagnosis Assessment: (1) Preoperative receipt of targeted therapy, immunotherapy, or chemoradiotherapy; (2) Preoperative receipt of interventional embolization; (3) Metastatic renal carcinoma with primary site not originating in the kidney; (4) CT image quality defects, including motion artifacts, metal artifacts, contrast agent issues, or technical failures; (5) Missing key baseline data (e.g., pathological report) or unclear pathological diagnosis. 2. Exclusion Criteria for Pathological Diagnosis Assessment: (1) Preoperative receipt of targeted therapy, immunotherapy, or chemoradiotherapy; (2) Preoperative receipt of interventional embolization; (3) Metastatic renal carcinoma with primary site not originating in the kidney; (4) Severe technical defects in H&E-stained slides; (5) Failure of digital scanning; (6) Missing key baseline data (e.g., pathological report).
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| The accuracy of Renal-FM in distinguishing benign from malignant and assessing aggressiveness on CT imaging; the accuracy of Renal-FM in determining pathological subtype and nuclear grade.; | — |
Secondary
| Measure | Time frame |
|---|---|
| The difference in accuracy between Renal-FM and conventional deep learning models as well as the non-kidney-specific pathological large model Gigapath in CT imaging and pathological diagnosis;The performance gap between Renal-FM and radiologists and pathologists in corresponding diagnostic tasks.; | — |
Countries
China
Contacts
Public ContactGuo Jianming
Zhongshan Hospital, Fudan University
Outcome results
None listed