D-Lung: An Analytics Platform for Lung Cancer Based on Deep Learning Technology

• Sponsor: Chinese University of Hong Kong (Other)
• Overall Status: Recruiting
• CT.gov ID: NCT04036903
• Collaborator: Department of Computer Science & Engineering, CUHK (Other)
• Enrollment: 500
• Location: 1
• Anticipated Duration (Months): 53
• Patients Per Site Per Month: 9.4

Study Details

Study Description

Brief Summary

Lung cancer is one of main cause of cancer death in worldwide, characterized of low 5-year survival rate of less than 20%. Pulmonary nodule is considered as the typical imaging manifestation in early stage of lung cancer. The National Lung Screen Trial has demonstrated that the mortality rates could decline greatly, by the utility of low-dose helical computed tomography for screen of pulmonary nodules. Thus, automatic detection, diagnosis and management of pulmonary nodules, play the vital roles in computer-aided lung cancer screening and early intervention.

Condition or Disease	Intervention/Treatment	Phase
Lung Cancer	Radiation: computed tomography

Study Design

• Study Type: Observational
• Anticipated Enrollment: 500 participants
• Observational Model: Case-Only
• Time Perspective: Retrospective
• Official Title: D-Lung: An Analytics Platform for Primary Lung Cancer Screening, Diagnosis and Management Based on Deep Learning Technology
• Actual Study Start Date: Jul 1, 2018
• Actual Primary Completion Date: Jun 30, 2020
• Anticipated Study Completion Date: Dec 1, 2022

Outcome Measures

Primary Outcome Measures

1. accuracy [2 years]

   proportion of true results(both true positives and true negatives) among whole instances

2. sensitivity [2 years]

   true positive rate in percentage(%) derived by ROC analysis

3. specificity [2 years]

   true negative rate in percentage (%) derived by ROC analysis

4. area under curve (AUC) [2 years]

   area under ROC curve in percentage (%)

Secondary Outcome Measures

1. average number of false positives per scan (FPs/scan) [2 years]

   FPs/scan in number (N) based on free-response receiver operating characteristic (FROC) analysis

2. competition performance metric (CPM) [2 years]

   Competitive performance metric (CPM) is a criterion used for CAD system evaluation. Based on FROC paradigm, CPM score is computed as an average sensitivity at seven predefined average false positive rates. CPM score ranges from 0 to 1, with higher CPM score indicating better CAD performance.

Eligibility Criteria

Criteria

• Ages Eligible for Study: N/A and Older
• Sexes Eligible for Study: All

Inclusion Criteria:

• Subjects with suspicious lung nodules.

• Thin-layer thoracic CT and pathology examination have been performed for suspicious lung nodules.

Exclusion Criteria:

• Subjects with accompanied lesions on CT images that may interfere to lung nodules analysis

Contacts and Locations

Locations

	Site	City	State	Country	Postal Code
1	The Chinese University of Hong Kong, Prince of Wale Hospital	Hong Kong	Shatin	Hong Kong

Sponsors and Collaborators

• Chinese University of Hong Kong
• Department of Computer Science & Engineering, CUHK

Investigators

None specified.

Study Documents (Full-Text)

None provided.

More Information

Publications

None provided.

• Responsible Party: Professor Winnie W.C. Chu, Professor, Chinese University of Hong Kong
• ClinicalTrials.gov Identifier: NCT04036903
• Other Study ID Numbers: 2019.316
• First Posted: Jul 30, 2019
• Last Update Posted: Jul 28, 2021
• Last Verified: Jul 1, 2021

• Individual Participant Data (IPD) Sharing Statement: No
• Plan to Share IPD: No
• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No
• Keywords provided by Professor Winnie W.C. Chu, Professor, Chinese University of Hong Kong: Lung nodules; Deep learning
• Additional relevant MeSH terms: Lung Neoplasms

Study Results

No Results Posted as of Jul 28, 2021