Imaging-based Deep Learning for Lung Cancer Diagnosis and Staging

Huazhong University of Science and Technology

Status: Unknown

Conditions: Lung Cancer

Treatments: Procedure: punture; Procedure: surgery

Study type: Observational

Funder types: Other

Identifiers

NCT04000620

AFDSFA

Details and patient eligibility

About

Lung cancer diagnosis and staging are two fundamental and critical issue in clinical lung cancer management and therapeutic decision-making. Invasive procedures for pathologic analysis are gold standard for diagnosis and staging, however, invasive procedures related-complications are inevitable. Noninvasive medical imaging is a powerful tool, however there is almost no room for improvement just according to the experience of radiologist and clinician. The researchers will investigate the role of computer based deep learning of medical imaging in the diagnosis of lesion of lung, lymph node and other sites suspected with metastasis.

Full description

Radiologist

Enrollment: 500 estimated patients

Sex: All

Ages: 18 to 75 years old

Volunteers: No Healthy Volunteers

Inclusion criteria

• Pathological diagnosis of lung cancer
• PET/CT or CT examination before any cancer-specific treatment

Exclusion criteria

• A history of other malignancies

Trial design

500 participants in 2 patient groups

cancer cell involvement predicted by deep learning

Description:

the participants with lesions of lung, lymph node or other sites predicted as positive for cancer cell involvement by imaging based deep learning.

Treatment:

Procedure: punture

Procedure: surgery

no cancer cell involvement predicted by deep learning

Description:

the participants with lesions of lung, lymph node or other sites predicted as negative for cancer cell involvement by imaging based deep learning.

Treatment:

Procedure: punture

Procedure: surgery