Breadcrumb
Radiomics for Lung Cancer Risk Assessment
Radiomics for Lung Cancer Risk Assessment

We aim to increase the efficacy of lung cancer screening with low dose computed tomography (LDCT) by developing methods to accurately predict risk of lung cancer and/or progressive obstructive lung disease at the time of screening. Our approach will focus on objective biomarkers: LDCT derived radiomic biomarkers of lung structure and an epigenetic biomarker of smoking exposure.
We have generated very promising preliminary results indicating radiomic features from CT combined with machine learning can inform non-invasive cancer risk assessment.
Dilger SK, Uthoff J, Judisch A, Hammond E, Mott SL, Smith BJ, Newell JD, Jr., Hoffman EA, Sieren JC. Improved pulmonary nodule classification utilizing quantitative lung parenchyma features. Journal of medical imaging (Bellingham, Wash). 2015;2(4):041004. Epub 2016/02/13. doi: 10.1117/1.Jmi.2.4.041004. PubMed PMID: 26870744; PMCID: PMC4748146.
J Uthoff, MJ Stephens, J Larson, N Koehn, FA De Stefano, C Lusk, AS Wenzlaff, D Watza, C Neslund-Dudas, DA Lynch, JD Newell Jr., AG Schwartz, J.C. Sieren. ‘Machine learning approach for distinguishing malignant and benign lung nodules utilizing standardized perinodular parenchymal features from CT’. Medical Physics Jul;46(7):3207-3216 (2019) PMC6945763.
J Uthoff, P Nagpal, R Sanchez, T Gross, C Lee, J.C. Sieren. ‘Differentiation of non-small cell lung cancer and histoplasmosis pulmonary nodules: Insights from radiomics model performance compared with clinician observers.’ Translational Lung Cancer Research Dec 8(6): 979-988 (2019) PMC6976371
Uthoff JM, Mott SL, Larson J, Neslund-Dudas CM, Schwartz AG, Sieren JC; and the COPDGene Investigators. Computed Tomography Features of Lung Structure Have Utility for Differentiating Malignant and Benign Pulmonary Nodules. Chronic Obstr Pulm Dis. 2022 Apr 29;9(2):154-164. doi: 10.15326/jcopdf.2021.0271. PMID: 35021316.
Philibert R, Dawes K, Moody J, Hoffman R, Sieren JC, Long J. Using Cg05575921 methylation to predict lung cancer risk: a potentially bias-free precision epigenetics approach. Epigenetics. 2022 Aug 3:1-13. doi: 10.1080/15592294.2022.2108082. Epub ahead of print. PMID: 35920547.