We propose to establish the Moffitt Imaging Biomarker Validation Center (MIBVAC) focused on imaging biomarker validations for early cancer detection and accurate risk assessments by leveraging our team of strong experts, resources, planned imaging biomarker validation studies, and analysis and network collaboration structures. In previous studies we have demonstrated that various measurements from breast images quantify breast cancer risk. The large cooperative National Lung Screening Trial (NLST) also showed a significant survival improvement for individuals screened by low dose CT compared to those screened with conventional radiography. Additionally, we have recently shown that CT image analysis (radiomics) can improve classification in this data set. However, due to difficulties in obtaining accurate and reproducible measurements and high false-positive rates of current imaging, cancer imaging biomarkers have not been routinely incorporated into clinical risk assessment. If these imaging biomarkers can be accurately tailored at the individual level, their impact will be significantly improved for early cancer detection and intervention. MIBVAC plans to achieve this challenging yet quite achievable goal by rigorously evaluating and validating these imaging biomarkers for rapid translation into clinical and practical applications. We have four specific aims:
(Aim 1) Establish breast imaging resources for EDRN both with our existing and new case-control datasets of breast images and to evaluate and validate breast imaging biomarkers based on newly-established case-control dataset of digital breast tomosynthesis (TS) images, (Aim 2) Evaluate and validate lung imaging biomarkers for early detection of cancer first based on NLST low-dose CT (LDCT) cohorts and then expanding with a newly-established case-control cohort of higher resolution LDCT, (Aim 3) Conduct validation studies with imaging biomarkers for EDRN partners and others for other malignancies, and (Aim 4) Refine and validate imaging biomarkers analytically for early detection of breast, lung, and other cancers and to construct MIBVAC imaging data and specimen resources for EDRN collaborations and sharing.

Public Health Relevance

We propose to establish the Moffitt Imaging Biomarker Validation Center (MIBVAC) focused on imaging biomarker validations for early cancer detection and accurate risk assessments by leveraging our team of strong experts, resources, planned imaging biomarker validation studies, and analysis & network collaboration structures. In our previous studies we have demonstrated that measurements from breast images can quantify breast cancer risk. The large cooperative National Lung Screening Trial (NLST) also showed a significant survival improvement for individuals screened by low dose CT compared to those screened with conventional radiography. Additionally, we have recently shown that CT image analysis (radiomics) can improve classification in this data set. However, due to difficulties in obtaining accurate and reproducible measurements and high false-positive rates of current imaging, cancer imaging biomarkers have not been routinely incorporated into clinical risk assessment. If these imaging biomarkers can be accurately tailored at the individual level, their impact will be significantly improved for early cancer detection and intervention. MIBVAC plans to achieve this challenging yet quite achievable goal by rigorously evaluating and validating these imaging biomarkers for rapid translation into clinical and practical applications within the Center as well as with the EDRN partners.

Agency
National Institute of Health (NIH)
Institute
National Cancer Institute (NCI)
Type
Research Project--Cooperative Agreements (U01)
Project #
3U01CA200464-01S1
Application #
9337978
Study Section
Special Emphasis Panel (ZCA1-RPRB-B (A1))
Program Officer
Mazurchuk, Richard V
Project Start
2016-07-01
Project End
2021-03-31
Budget Start
2016-07-01
Budget End
2017-03-31
Support Year
1
Fiscal Year
2016
Total Cost
$29,974
Indirect Cost
$12,547
Name
H. Lee Moffitt Cancer Center & Research Institute
Department
Type
DUNS #
139301956
City
Tampa
State
FL
Country
United States
Zip Code
33612
Cherezov, Dmitry; Hawkins, Samuel H; Goldgof, Dmitry B et al. (2018) Delta radiomic features improve prediction for lung cancer incidence: A nested case-control analysis of the National Lung Screening Trial. Cancer Med 7:6340-6356
Paul, Rahul; Liu, Ying; Li, Qian et al. (2018) Representation of Deep Features using Radiologist defined Semantic Features. Proc Int Jt Conf Neural Netw 2018:
Liu, Ying; Wang, Hua; Li, Qian et al. (2018) Radiologic Features of Small Pulmonary Nodules and Lung Cancer Risk in the National Lung Screening Trial: A Nested Case-Control Study. Radiology 286:298-306
Alahmari, Saeed S; Cherezov, Dmitry; Goldgof, Dmitry et al. (2018) Delta Radiomics Improves Pulmonary Nodule Malignancy Prediction in Lung Cancer Screening. IEEE Access 6:77796-77806
Fowler, E; Smallwood, A; Khan, N et al. (2018) Technical Challenges in Generalizing Calibration Techniques for Breast Density Measurements. Med Phys :
Paul, Rahul; Hall, Lawrence; Goldgof, Dmitry et al. (2018) Predicting Nodule Malignancy using a CNN Ensemble Approach. Proc Int Jt Conf Neural Netw 2018:
Li, Qian; Balagurunathan, Yoganand; Liu, Ying et al. (2018) Comparison Between Radiological Semantic Features and Lung-RADS in Predicting Malignancy of Screen-Detected Lung Nodules in the National Lung Screening Trial. Clin Lung Cancer 19:148-156.e3
Paul, Rahul; Hawkins, Samuel H; Schabath, Matthew B et al. (2018) Predicting malignant nodules by fusing deep features with classical radiomics features. J Med Imaging (Bellingham) 5:011021
Tunali, Ilke; Stringfield, Olya; Guvenis, Albert et al. (2017) Radial gradient and radial deviation radiomic features from pre-surgical CT scans are associated with survival among lung adenocarcinoma patients. Oncotarget 8:96013-96026
Beichel, Reinhard R; Smith, Brian J; Bauer, Christian et al. (2017) Multi-site quality and variability analysis of 3D FDG PET segmentations based on phantom and clinical image data. Med Phys 44:479-496

Showing the most recent 10 out of 12 publications