Precision, pulmonary disease evaluation and lung cancer detection using quantitative low-dose CT

Period of Performance: 08/11/2016 - 07/31/2017

$300K

Phase 1 STTR

Recipient Firm

Vida Diagnostics, Inc.
CORALVILLE, IA 52241
Principal Investigator

Abstract

? DESCRIPTION (provided by applicant): Lung cancer is responsible for more cancer deaths than breast, prostate, and colon cancers combined. Minimal improvements in the five-year survival rate for lung cancer have occurred over the past thirty years. Recently, a mortality benefit has been demonstrated for lung cancer screening using low dose computed tomography (LDCT) in people with high cancer risk. The clinical challenge for lung cancer screening is that the majority of lung nodules detected are not cancer. An approach that extracts quantitative measurements from the LDCT data at the time of screening and contributes to a reduction in the false positive rate without additional testing is urgently needed. The VIDA software system processes high resolution CT (HRCT) data to automatically identify and measure the major anatomical structures within the lungs (lobes, airways, vessels) while also providing a regional assessment of lung tissue integrity. These quantitative CT measurements can be used to identify and characterize the spatial distribution, severity, and longitudinal progression of lung diseases, such as chronic obstructive pulmonary disease (COPD). The risk of lung cancer is 2 to 3-fold higher in people with COPD, thus quantitative CT metrics of COPD may contribute insight to lung cancer risk in the lung cancer screening population. It is the goal of this application to evaluate the performance of VIDA's existing HRCT analysis tools for application to optimized LDCT data and expand the analysis toolkit to include pulmonary nodule segmentation. Nodule segmentation in CT data is not a new technology; however, nodule detection with simultaneous co-morbid lung disease assessment can provide a predictive and risk-based evaluation for lung cancer and represents a new form of precision medicine based on imaging analytics. Increased confidence in the risk of lung cancer for indeterminate LDCT detected lung nodules will result in rapid treatment for malignant cases while reducing emotional stress and invasive testing in those with benign lesions. The systematic evaluation of COPD over annual lung cancer screening time-points will also increase the value for subjects in which no lung nodules that are detected by quantitatively tracking disease progression. We propose developing a commercial lung nodule detection and risk stratification software (VIDA software analysis) utilizing the clinically collected LDCT data to non-invasively and cost-efficiently aid i the early stratification of patients to the appropriate clinical course of action.