Lung cancer is the leading cancer killer in both men and women in the U.S. Early detection is the most effective way to fight against this deadly disease. In recent years, an imaging method known as low-dose CT (LDCT) scan has been studied in people at higher risk of getting lung cancer. LDCT scans can help find nodules in the lungs that may be cancer. However, majority of those nodules are actually benign, yet exposing many of those patients to a needle biopsy or other invasive procedures. Hence, there is an urgent and unmet need for an accurate and non-invasive approach to distinguish those nodules that are malignant from those that are not. In this proposal, we will develop and validate a novel method to integrate a blood test and the LDCT imaging for the early detection of lung cancer. Specifically, from blood we extract cell-free DNA, from which we develop an ultra-sensitive assay to profiles the epigenome of cell-free DNA, therefore to detect even a trace amount of tumor DNA. Using advanced machine learning algorithms on the integrated genomics and imaging data, we aim to significantly improve the accuracy of the cancer detection. For those patients with nodules identified from LDCT, we will integrate the two sources of information to determine whether the nodules are malignant or benign.
Jasmine Zhou, PhD
Location: Jonsson Comprehensive Cancer Center - California
Proposal: Integrating cell-free DNA methylome and CT imaging to determine the malignancy of lung nodules