Clinical Validation of an Explainable AI Model for Breast Benign and Malignant Lesion Classification

Status

Recruiting

Phases

Early Phase 1

Study type

Observational

Source

ChiCTR

Registry ID

ChiCTR2500103426

Enrollment

Unknown

Registered

2025-05-29

Start date

2025-06-01

Completion date

Unknown

Last updated

2025-06-02

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

Conditions

breast cancer

Interventions

Gold Standard:Preoperative puncture pathology, intraoperative rapid freezing pathology or postoperative paraffin pathology

Index test:An AI Model (CBM) for the Classification of Benign and Malignant Breast Lesions

Eligibility

Sex/Gender

Female

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: (1) Patients aged >=18 years who underwent preoperative MRI for breast lesions. (2) Availability of complete clinical and surgical pathological records. (3) No history of any anti-tumor therapy prior to MRI examination.

Exclusion criteria

Exclusion criteria: (1) Inadequate MRI image quality for analysis. (2) Absence of surgical pathology or follow-up results of at least 12 months. (3) Pathological findings indeterminate for benign/malignant differentiation. (4) History of prior treatment for breast malignancy.

Design outcomes

Primary

Measure	Time frame
Sensitivity of the CBM;Specificity of the CBM;Accuracy of the CBM;The time of CBM output report;	—

Countries

China

Contacts

Public ContactSu Lyu

West China Hospital, Sichuan University

lusuwcums@hotmail.com+86 189 8060 2270

Outcome results

None listed

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