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

Chinese University of Hong Kong130 enrolled

Overview

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.

Study Type

OBSERVATIONAL

Enrollment

130

Conditions

Lung Cancer

Interventions

computed tomographyRADIATION

thoracic CT examinations for diagnosis, and/or follow-up.

Eligibility

Sex: ALL

Medical Language ↔ Plain English

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

Locations (1)

The Chinese University of Hong Kong, Prince of Wale Hospital

Hong Kong, Shatin, Hong Kong

Outcomes

Primary Outcomes

accuracy

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

Time frame: 2 years

sensitivity

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

Time frame: 2 years

specificity

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

Time frame: 2 years

area under curve (AUC)

area under ROC curve in percentage (%)

Time frame: 2 years

Secondary Outcomes

average number of false positives per scan (FPs/scan)

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

Time frame: 2 years

competition performance metric (CPM)

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.

Time frame: 2 years

Data from ClinicalTrials.gov

This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.