Skip to content

Application of ultrasound image analysis based on deep learning in breast tumor diagnosis and evaluation of neoadjuvant chemotherapy

Application of multi-modal ultrasound image analysis based on deep learning in breast tumor diagnosis and evaluation of neoadjuvant chemotherapy

Status
Recruiting
Phases
Early Phase 1
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2100044910
Enrollment
Unknown
Registered
2021-03-31
Start date
2021-05-01
Completion date
Unknown
Last updated
2021-11-02

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

Conditions

breast cancer

Interventions

Sponsors

NO
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: 1. Deep learning-based breast tumor assisted diagnosis model: (1) Patients aged between 18 and 80 years old who underwent breast ultrasound examination in our hospital. (2) Patients diagnosed as 3-5 type of breast tumor by ultrasound, underwent surgery in our hospital and obtained postoperative pathological results. 2: Efficacy evaluation model of neoadjuvant chemotherapy based on deep learning: (1) Patients who received neoadjuvant chemotherapy in our hospital and obtained pathological results, and underwent ultrasound examination before and during chemotherapy with retained ultrasound images. (2) Aged between 18 and 80 years.

Exclusion criteria

Exclusion criteria: 1. Pregnant and lactating patients were not included in this study; 2. Patients with a prior history of breast tumor surgery, radiotherapy, or chemotherapy.

Design outcomes

Primary

MeasureTime frame
Ultrasonic image features;SEN, SPE, ACC, AUC of ROC;

Countries

China

Contacts

Public ContactWan Caifeng

Renji Hospital Affiliated to Shanghai Jiao Tong University,School of Medicine

wancaifengky@sina.com+86 15921863320

Outcome results

None listed

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