Research on Machine Learning Based on Multi-modal Radiomics for Diagnostic Decision-Making and Risk Stratification of Breast Cancer

Status

Active, not recruiting

Phases

Early Phase 1

Study type

Observational

Source

ChiCTR

Registry ID

ChiCTR2600119290

Enrollment

Unknown

Registered

2026-02-25

Start date

2025-01-01

Completion date

Unknown

Last updated

2026-05-25

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:The gold standard is the postoperative or core needle biopsy pathological diagnosis. All patients were pathologically confirmed as having either breast cancer or benign breast lesions, w

Index test:The index test is a machine learning diagnostic model based on multi-modal radiomics features (including ultrasound, mammography, CT, and MRI), designed for differentiating benign and malig

Eligibility

Sex/Gender

All

Age

18 Years to 80 Years

Inclusion criteria

Inclusion criteria: 1. Patients with breast lesions detected by imaging examinations (ultrasound, mammography, CT, or MRI); 2. Complete preoperative imaging data available; 3. Histopathological confirmation of either benign breast lesions or breast cancer by surgery or core needle biopsy; 4. Age >=18 years; 5. Complete clinical and follow-up information.

Exclusion criteria

Exclusion criteria: 1. Pathologically undiagnosed; 2. The pathological type cannot be clearly defined; 3. It cannot be confirmed that the primary lesion is the breast; 4. Accompanied by other tumors.

Design outcomes

Primary

Measure	Time frame
Area under the receiver operating characteristic curve (AUC);sensitivity;specificity;accuracy;positive predictive value;Negative Predictive Value;	—

Countries

China

Contacts

Public ContactHuang Jiangsheng

Second Xiangya Hospital of CSU

hjs13907313501@csu.edu.cn+86 731 85295164

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: May 30, 2026