Skip to content

Research on the efficacy of deep learning model for mediastinal lesion detection and classification

Research on the efficacy of deep learning model for mediastinal lesion detection and classification

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2100053002
Enrollment
Unknown
Registered
2021-11-07
Start date
2021-12-01
Completion date
Unknown
Last updated
2022-08-30

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

Conditions

mediastinal lesion

Interventions

Gold Standard:Pathological results
Index test:The&#32
of&#32
deep&#32
learning&#32
model&#32

Sponsors

Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 75 Years

Inclusion criteria

Inclusion criteria: 1. Surgical patients aged >= 18 years who were treated in the Department of Thoracic Surgery of Shanghai Pulmonary Hospital; 2. Preoperative chest CT showed mediastinal lesions, the images were obtained from CT image data of the Imaging Department of Shanghai Pulmonary Hospital, and there were complete CT imaging examination images and reports; 3. The case has complete intraoperative frozen pathological results and postoperative paraffin pathological results; 4. Patients participated voluntarily and signed informed consent.

Exclusion criteria

Exclusion criteria: 1. Patients who have received targeted therapy, radiotherapy and chemotherapy in the past; 2. The patient voluntarily withdrew midway.

Design outcomes

Primary

MeasureTime frame
Area under receiver operating curve (AUC);

Secondary

MeasureTime frame
Accuracy;Sensitivity;Specificity;

Countries

China

Contacts

Public ContactShe Yyunlang

Shanghai Pulmonary Hospital Affiliated to Tongji University

1151697503@qq.com+86 19916941894

Outcome results

None listed

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