Deep-learning tool to distinguish T1–T2 from T3 renal cell carcinoma on contrast-enhanced CT.

Deep Learning for Automated Discrimination Between Stage T1-T2 and T3 Renal Cell Carcinoma on Contrast-Enhanced CT

Observational Peking University First Hospital · NCT07166445

This project will see if a computer model can tell whether kidney cancer is early (T1–T2) or locally advanced (T3) using contrast-enhanced CT scans before surgery.

Quick facts

Study typeObservational
Enrollment1000 (estimated)
Ages18 Years to 85 Years
SexAll
SponsorPeking University First Hospital Academic / other
Locations1 site (Beijing)
Trial IDNCT07166445 on ClinicalTrials.gov

What this trial studies

Researchers will develop and validate a deep-learning model using preoperative contrast-enhanced CT scans linked to postoperative pathological stage from a single center. The model will be trained on annotated DICOM images with slice thickness ≤1 mm and evaluated on an independent test set to assess generalizability. Performance metrics will include AUC, sensitivity, specificity, positive and negative predictive values, and decision-curve analysis. The final goal is a decision-support tool that can be integrated into clinical PACS to inform preoperative staging and surgical planning.

Who should consider this trial

Good fit: Ideal participants are patients with histopathologically confirmed renal cell carcinoma who had preoperative contrast-enhanced CT performed at Peking University First Hospital with complete DICOM data and slice thickness ≤1 mm.

Not a fit: Patients with non‑RCC histology, CT scans with severe artifacts, scans performed elsewhere without compatible image quality, or without contrast-enhanced thin-slice CT are unlikely to benefit.

Why it matters

Potential benefit: If successful, the tool could reduce staging errors and help surgeons plan the most appropriate operation, potentially improving outcomes and avoiding under- or overtreatment.

How similar studies have performed: Prior small and single-center studies of CT-based deep learning for RCC staging have shown promising accuracy, but large independent validations and clinical integration remain limited.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

1. Histopathologically confirmed renal cell carcinoma on postoperative specimen.
2. Preoperative contrast-enhanced CT performed at our institution with slice thickness ≤ 1 mm and complete DICOM datasets.
3. Postoperative pathologic staging clearly defined as pT1a-T2b or pT3a.
4. CT image quality deemed adequate for analysis.

Exclusion Criteria:

* 1\. Pathologic subtype other than RCC. 2. Images with severe artifacts.

Where this trial is running

Beijing

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Carcinoma, Renal CellDiagnostic ImagingPathologyDeep Learning
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.