Skip to content

Deep Feature Matching of CT Images for Predicting Pathological Indices in Renal Cell Carcinoma: A Multicenter Prospective Observational Study

Deep Feature Matching of CT Images for Predicting Pathological Indices in Renal Cell Carcinoma: A Multicenter Prospective Observational Study

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500115538
Enrollment
Unknown
Registered
2025-12-28
Start date
2026-01-01
Completion date
Unknown
Last updated
2026-01-05

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Kidney Cancer

Interventions

Gold Standard:The gold standard in this study is postoperative pathological diagnosis. All enrolled patients undergo partial nephrectomy, radical nephrectomy, or renal biopsy to obtain tissue specimen
Index test:The index test under evaluation in this study is the "Deep Feature Matching-based CT Retrieval Technology Model". This model is an artificial intelligence diagnostic software. Its core prin

Sponsors

Zhongshan Hospital, Fudan University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 80 Years

Inclusion criteria

Inclusion criteria: 1.Age >= 18 years and <= 80 years (inclusive) 2. Patients with renal masses who undergo the following procedures at the participating centers (Zhongshan Hospital Affiliated to Fudan University, Qilu Hospital of Shandong University, Linyi People's Hospital, Zhongshan Hospital Affiliated to Fudan University Xiamen Branch): partial nephrectomy, radical nephrectomy, or renal biopsy 3. Having a definitive postoperative pathological diagnosis, including key indicators such as pathological subtypes 4. Availability of preoperative CT images of the renal mass

Exclusion criteria

Exclusion criteria: 1. Preoperative neoadjuvant therapy such as targeted therapy, immunotherapy, radiotherapy, or chemotherapy 2. Preoperative interventional embolization therapy 3. Metastatic renal cell carcinoma with non-renal primary lesions 4. Defects in CT quality, including motion artifacts, metal artifacts, contrast agent issues, and technical failure 5. Missing key baseline data (e.g., pathological reports) or unclear pathological diagnosis

Design outcomes

Primary

MeasureTime frame
Area Under the Receiver Operating Characteristic Curve of the CT Retrieval Model in Diagnosing Renal Mass Benignity and Malignancy;

Secondary

MeasureTime frame
Area Under the Receiver Operating Characteristic Curveof the CT Retrieval Model for Key Pathological Features;

Countries

China

Contacts

Public ContactJianming Guo

Zhongshan Hospital, Fudan University

guo.jianming@zs-hospital.sh.cn+86 21 5879 2346

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026