Skip to content

Multicenter Clinical Study of Explainable AI-Assisted Diagnosis Based on Ultrasound Imaging of Breast Diseases

Multicenter Clinical Study of Explainable AI-Assisted Diagnosis Based on Ultrasound Imaging of Breast Diseases

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600129212
Enrollment
Unknown
Registered
2026-08-01
Start date
2026-08-01
Completion date
Unknown
Last updated
2026-08-03

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

Conditions

Breast disorders

Interventions

Gold Standard:Postoperative histopathology or biopsy pathology.
Index test:The detection rate of various types of breast lumps and the accuracy of their classification by AI-assisted diagnostic systems are the most critical evaluation metrics, including sensitivit

Sponsors

Xi'an Jiaotong University Second Affiliated Hospital
Lead Sponsor

Eligibility

Sex/Gender
Female
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. Patients with breast masses identified by conventional ultrasound, including solid masses (fibroadenoma, breast cancer, intraductal papilloma, adenosis nodules, etc.), mixed cystic-solid masses, and complex cysts, etc. 2. Female patients aged 18 years or older; 3. Patients who have not received any related breast clinical interventions (surgery, biopsy, radiotherapy, chemotherapy, etc.) before ultrasound examination; 4. Patients have given informed consent to participate in this study.

Exclusion criteria

Exclusion criteria: 1. Patients with a history of previous breast surgery, radiotherapy, or those currently undergoing breast-related systemic treatment (chemotherapy, endocrine therapy, targeted therapy); 2. Patients with extensive calcification (coarse calcification or eggshell-like calcification) in the mass that seriously affects the quality of ultrasound images; 3.Patients with contraindications to contrast-enhanced ultrasound (history of contrast agent allergy, severe cardiac or pulmonary dysfunction, etc.); 4. Pregnant or lactating women; 5.Patients with poor image quality (not meeting the diagnostic criteria) or lacking complete clinical data and pathological results.

Design outcomes

Primary

MeasureTime frame
Sensitivity, specificity, positive predictive value, negative predictive value, accuracy, composite evaluation metrics, and the area under the curve;Interpretability;Multimodal ultrasound data of breast disorders;

Secondary

MeasureTime frame
Model generalization ability;

Countries

China

Contacts

Public ContactWang Juan

Xi'an Jiaotong University Second Affiliated Hospital

wangjuan_optimism@163.com+86 13997580365

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Aug 10, 2026