Artificial Intelligence-assisted HER2 Expression Assessment in Urothelial Carcinoma Based on Imaging-pathology Omics

NCT07454941 | Enrolling By Invitation DMC

• 1 other identifier: NCC5690
• Study Type: observational
• Target: 4,000
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to build upon previous research by using artificial intelligence methods to fuse multimodal data from imaging and pathology to construct a predictive model for HER2 expression in urothelial carcinoma. The model's performance will be validated and optimized using a multicenter cohort study, ultimately achieving accurate and rapid prediction of HER2 expression. This will guide precise decision-making for further HER2-targeted therapy and improve patient prognosis. Big data analysis and deep learning will also assist physicians in more accurately diagnosing the disease and developing personalized treatment plans. The research findings will promote the integration and development of artificial intelligence technology with the healthcare industry in the application of multimodal data from clinical, imaging, and pathology perspectives.

Conditions

Urothelial Carcinoma (UC); HER2; Diagnostic

Keywords

Urothelial Carcinoma; HER2; Artificial Intelligence; Diagnostic Model; Radiomics; Histopathology

Outcome Measures

Primary Outcomes (1)

• Artificial intelligence predicts HER2 expression in urothelial carcinoma

  Based on artificial intelligence (AI) technology, this study aims to establish a predictive model by quantitatively mapping the correlation between annotated whole-section images of urothelial carcinoma and MRI scans, identifying common characteristics, and ultimately building a predictive model. Firstly, this model can accurately assess the HER2 status of bladder cancer, eliminating the need for immunohistochemistry to obtain detailed pathological information. Secondly, the established AI predictive model can accurately diagnose the benign or malignant, invasive, grade, and subtype of bladder cancer by predicting the subject's MRI images before biopsy or surgery.

  Through study completion, an average of 24 months

Study Arms (1)

Patient diagnosed with urothelial carcinoma by pathology.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

We collected imaging and pathological data from patients diagnosed with urothelial carcinoma. Using artificial intelligence, we fused multimodal data from imaging and pathology to construct a predictive model for HER2 expression in urothelial carcinoma. The model's performance was validated and optimized using a multi-center cohort study, ultimately achieving accurate and rapid prediction of HER2 expression. This will guide precise decision-making for further HER2-targeted therapy and improve patient prognosis.

You may qualify if:

• Age ≥ 18 years.
• Patients pathologically diagnosed with urothelial carcinoma.
• Possession of pre-biopsy or pre-operative multiparametric MRI raw data.
• Possession of corresponding paraffin-embedded tissue blocks and digital whole-section images.
• Possession of HER2 status report confirmed by immunohistochemistry.
• Signed informed consent form.

You may not qualify if:

• Contraindications to MRI, such as presence of metallic implants or claustrophobia.
• Patients with missing baseline clinical or pathological information.
• Patients who have received neoadjuvant therapy.
• Patients with a history of other malignant tumors.
• Patients with mixed or non-urothelial carcinoma pathology.

Sponsors & Collaborators

• Cancer Institute and Hospital, Chinese Academy of Medical Sciences: lead
• Shanxi Province Cancer Hospital: collaborator
• Cancer Hospital Chinese Academy of Medical Science, Shenzhen Center: collaborator
• RenJi Hospital: collaborator
• First Hospital of China Medical University: collaborator
• Huadong Hospital: collaborator
• Huaxi Hospital: collaborator
• The First Affiliated Hospital of Anhui Medical University: collaborator
• Xinhua Hospital, Shanghai Jiao Tong University School of Medicine: collaborator

Study Sites (1)

National Cancer Center / Cancer Hospital, Chinese Academy of Medical Sciences Beijing

Beijing, Chaoyang District, 100021, China

Location

MeSH Terms

Conditions

Carcinoma, Transitional Cell; Disease

Condition Hierarchy (Ancestors)

Carcinoma; Neoplasms, Glandular and Epithelial; Neoplasms by Histologic Type; Neoplasms; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: PROSPECTIVE
• Target Duration: 1 Week
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Chief Physician

Study Record Dates

• First Submitted: March 2, 2026
• First Posted: March 6, 2026
• Study Start: March 2, 2026
• Primary Completion (Estimated): June 3, 2028
• Study Completion (Estimated): June 3, 2030
• Last Updated: March 6, 2026

Record last verified: 2026-03

Locations

CN (1)