Skip to content

Development and Validation of a Three-dimensional Convolutional Neural Network for Automated Detection of Lung Nodule from Computed Tomography Images

Development and Validation of a Three-dimensional Convolutional Neural Network for Automated Detection of Lung Nodule from Computed Tomography Images

Status
Active, not recruiting
Phases
Early Phase 1
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR1900023597
Enrollment
Unknown
Registered
2019-06-03
Start date
2019-08-01
Completion date
Unknown
Last updated
2019-06-11

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

Conditions

lung Nodule

Interventions

Gold Standard:Labels of senior chest radiologist without time limitation.
Index test:Labels&#32
of&#32
and&#32
the&#32
detection&#32
results&#32
deep&#32
learning&#32
model&#32

Sponsors

Shanghai Pulmonary Hospital
Lead Sponsor

Eligibility

Sex/Gender
All
Age
19 Years to 70 Years

Inclusion criteria

Inclusion criteria: 1. At least one lung nodule (size of 5-30mm) was found in CT examinations; 2. High-quality image was obtained with layer thickness thinner than 1.25mm; 3. Patients volunteered to participate in this study and signed informed consent.

Exclusion criteria

Exclusion criteria: 1. The number of lung nodules exceeds 20; 2. The quality of CT images is poor, or patients with comorbidities including extensive pulmonary infection, massive pleural effusion, and diffused interstitial pneumonia, etc. 3. Patients with imcomplete clinical information; 4. Patients with a history of malignancy; 5. With a history of thoracic surgery.

Design outcomes

Primary

MeasureTime frame
Lung Nodule;Accuracy;Sensitivity;

Countries

China

Contacts

Public ContactChen Chang

Shanghai Pulmonary Hospital

1831228@tongji.edu.cn+86 15618977421

Outcome results

None listed

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