Skip to content

Grants

Current:

UG1CA180830 Lenz/El- Khoueiry/Duddalwar 03/01/2021- 02/28/2026
NIH /NCTN
NCTN – Network Lead Academic Participating Site: USC
Major Goals: The major emphases of the USC team are (a) to provide leadership across the NTCN to design and efficiently perform clinical trials evaluating the safety and efficacy of novel regimens or modifications of existing regimens; (b) to provide leadership in biomarker development and in the integration of new technologies into NCTN trials, taking advantage of a systematic approach to collection, processing, and storage of blood, normal tissue, fresh or frozen tumor tissue, and other relevant biologic samples for molecular and pharmacologic studies; and (c) to evaluate cancer treatment regimens in special patient populations, such as rare cancers, the elderly and ethnic minorities.

1R01CA257610-01 Goldkorn/Triche/Duddalwar (MPI) 09/01/20 – 08/31/25 
NIH/NCI                                                                                 
Integrated Radiomic and liquid biopsy monitoring in SWOG S1802: A phase 3 therapeutic trial for metastatic prostate cancer.
Major Goals: To apply multi-parametric liquid biopsy assays combined with Radiomic analysis to monitor resistance and progression in a large Phase 3 clinical trial for men with de novo metastatic castrate sensitive prostate cancer treated with standard systemic therapy +/- treatment of the primary tumor.

MHI Grant Assad/Duddalwar/Gill (MPI) 07/01/20 – 08/31/22
MHI                                                                                                                 
Novel deep learning techniques for imputing medical images: Application in the clinical management of renal masses.
Major Goals: To propose to develop an image imputation solution based on deep learning to the common missing data problem that plagues most types of medical imagistic modalities.

2UM1CA186717-06 Lenz/Newman (MPI) 04/22/20 – 02/28/26
NIH/NCI                                                                                 
Phase 1 and 2 Molecular and Clinical Pharmacodynamic Trials ETCTN
Major Goals: A group of molecular and clinical pharmacologists, molecular biologists, and clinical scientists from the California Cancer Consortium (CCC) comprised of three NCI-designated Cancer Centers to develop new laboratory-based cancer treatment strategies for application in the early therapeutic trial setting.

2R44EB024438-03 Alger/Wang (MPI)   08/01/20 – 05/31/23
NIH/NIBIB                                                                              
Novel Algorithms for Reducing Radiation Dose of CT Perfusion.
Major Goals: To perform the evaluation and validation of the dose reduction performance of the k-space weighted image average (KWIA) image reconstruction and deep learning (DL) based denoising algorithms using clinical CT perfusion data and animal models.

1R01EB029088-01A1Fan/Yang (MPI) 07/01/20-03/24
NIH/NIBIB                                                                        
 Major Goals: To develop an MR technique for motion-resolved multi-contrast abdominal imaging in abdominal radiation therapy planning

Wright Foundation Transformative Cancer Grant 08/01/22 – 07/31/24
USC Keck School of Medicine                                      
Investigating the Complex Correlation Between Radiomics and Immune Infiltration in Renal Cell Carcinoma
Major Goals: To identify imaging biomarkers in evaluating the tumor microenvironment in ccRCC and the need for better predictive biomarkers for cancer patients with metastatic renal cell carcinoma.

Class action Award– Varghese (PI)  10/01/2021-09/31/26
Krueger vs. Wyeth                                                                                                   
Validating a Hybrid Artificial Intelligence-Based Framework for Characterizing Breast Masses Using Contrast-Enhanced Ultrasound (CEUS)
Major Goals: We will develop and validate a systematic and rigorous framework of combining machine learning (ML)and deep learning (DL)-based approaches (Artificial Intelligence) designed for breast malignancy stratification based on CEUS-derived metrics. The resultant model will be used to reduce the number of unnecessary biopsies in breast cancer patients, particularly the vulnerable, underserved, and lower socio-economic patients treated in county hospitals.

Skip to toolbar