Abstract
The LuCED test for early stage lung cancer detects rare abnormal cells that are exfoliated from tumors into sputum and promotes cancer case detection with >92% sensitivity and >95% specificity. Additionally, the LuCED test detects endobronchial lung dysplasia to triage patients with pre-cancer to chemoprevention therapy involving drugs such as Iloprost that show potential for reversing dysplasia. This test is complementary to lung cancer screening methods such as LDCT that do not detect dysplasia. We discuss the performance of the LuCED test for the non-invasive detection of endobronchial dysplasia. We analyzed 23,188 normal, 690 cancer, and 65 moderate/severe dysplasia cells from patient sputum. Each individual cell was imaged in 3D using the Cell-CT. Cells were analyzed to measure 594 3D structural biomarkers. Classifiers were developed with cytopathology as the gold standard to predict stages of carcinogenesis, from normal to dysplasia and cancer. The classifier output was binned into two diagnostic indications: 1) cancer vs. all other cell types; and 2) moderate/severe dysplasia vs. all other cell types. Areas under ROC curves for the two diagnostic bins were both = 0.993. Thresholds were chosen to yield case specificity >95%. Using these thresholds, cell classification sensitivity of 75% was measured for cancer and dysplasia detection. Since abnormal sputum typically contains at least three abnormal cells the cancer case detection sensitivity is at least {100% × [1 – (1 - 0.75)3]} = 98%. This study demonstrates the feasibility of using the LuCED test to detect endobronchial dysplasia in the lung, achieving an estimated 98% case sensitivity and 95% case specificity. Future efforts will include testing on independent sets. Importantly, the non-invasive detection of dysplasia by LuCED testing may enable chemoprevention of lung cancer using drugs such as Iloprost.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.