Imaging-based Deep Learning for Lung Cancer Diagnosis and Staging
The Role of CNN Architecture-based Transfer Learning of Medical Imaging in Lung Cancer Diagnosis and Staging
1 other identifier
observational
500
1 country
1
Brief Summary
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.
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P75+ for all trials
Started May 2018
Longer than P75 for all trials
1 active site
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
Study Start
First participant enrolled
May 1, 2018
CompletedFirst Submitted
Initial submission to the registry
June 24, 2019
CompletedFirst Posted
Study publicly available on registry
June 27, 2019
CompletedPrimary Completion
Last participant's last visit for primary outcome
December 30, 2021
CompletedStudy Completion
Last participant's last visit for all outcomes
May 1, 2024
CompletedNovember 16, 2021
November 1, 2021
3.7 years
June 24, 2019
November 15, 2021
Conditions
Outcome Measures
Primary Outcomes (1)
pathologic result revealed cancer cell involvement in lesion
1 month after the pathologic test
Study Arms (2)
cancer cell involvement predicted by deep learning
the participants with lesions of lung, lymph node or other sites predicted as positive for cancer cell involvement by imaging based deep learning.
no cancer cell involvement predicted by deep learning
the participants with lesions of lung, lymph node or other sites predicted as negative for cancer cell involvement by imaging based deep learning.
Interventions
Eligibility Criteria
Lung cancer patients with PET/CT or CT examination before any cancer-specific treatment
You may qualify if:
- Pathological diagnosis of lung cancer
- PET/CT or CT examination before any cancer-specific treatment
You may not qualify if:
- A history of other malignancies
Contact the study team to confirm eligibility.
Sponsors & Collaborators
Study Sites (1)
Wuhan Union Hospital
Wuhan, Hubei, 430000, China
MeSH Terms
Conditions
Interventions
Condition Hierarchy (Ancestors)
Central Study Contacts
Study Design
- Study Type
- observational
- Observational Model
- COHORT
- Time Perspective
- PROSPECTIVE
- Sponsor Type
- OTHER
- Responsible Party
- PRINCIPAL INVESTIGATOR
- PI Title
- Professor
Study Record Dates
First Submitted
June 24, 2019
First Posted
June 27, 2019
Study Start
May 1, 2018
Primary Completion
December 30, 2021
Study Completion
May 1, 2024
Last Updated
November 16, 2021
Record last verified: 2021-11