R01CA260705

Virtual Biopsy with Tissue-Level Accuracy in Glioma - Project Summary

This is a Bioengineering Research Grant (BRG) proposal in response to PAR-19-158. The objective of this proposal is to further develop and validate a non-invasive panel of the most critical glioma molecular markers (IDH, 1P/19Q, MGMT) using standard clinical MRI T2-weighted images and deep learning. The aim is to extend the performance to tissue-level accuracies.

Currently, the only reliable way to obtain molecular marker status is through direct tissue sampling of the tumor, which requires invasive procedures such as craniotomy and stereotactic biopsy or large open surgical resection. Noninvasive determination of molecular markers with tissue-level accuracy would be transformative in the management of gliomas. It would reduce or eliminate the risks and costs associated with neurosurgical procedures, accelerate the time to definitive treatment, improve patient experience, and ultimately enhance patient outcomes and survival time.

Artificial intelligence, specifically deep learning, has emerged as a powerful method for classifying imaging data that can surpass human performance. Preliminary work using our novel voxel-wise classification-segmentation approach with the NIH/NCI TCIA glioma database has outperformed any prior noninvasive methods for determining IDH, 1P/19Q, and MGMT methylation, achieving accuracies of 97%, 93%, and 95%, respectively. However, this approach needs validation beyond the TCIA, and accuracies need to be extended to achieve tissue-level performance.

To accomplish this, we will utilize our top-performing voxel-wise classification framework, leverage marker-specific targeted sample sizes, and gain a final boost from deep-learning artifact correction networks. In Aim 1, we will curate a database of over 2000 gliomas, including 500 subjects from our institution, 1200 subjects from our external collaborators, and over 300 subjects from the TCIA. We will train our voxel-wise deep learning classifiers to determine molecular status based on clinical T2-weighted MR images with target accuracies of 97%.

In Aim 2, we will rigorously evaluate the motion and noise sensitivity of the networks and create an artifact correction network with the goals of recovering accuracies in the presence of large amounts of motion/noise and further boosting accuracy to tissue-level performance even in the absence of visible artifact.

In Aim 3, we will deploy a complete end-to-end clinical workflow and evaluate the real-world live performance of the AI tool on 300 prospectively acquired brain tumor cases and 300 subjects from our external collaborators. The AI tool will be made available for deployment at other medical centers. Additionally, the developed framework can be extended to include additional markers in a straightforward manner.

In summary, this BRG proposal aims to further develop, refine, and validate a non-invasive MRI-based method for determining the most critical glioma molecular markers, rivaling tissue-level accuracies. This method has the potential to significantly reduce and, in many cases, eliminate the need for stereotactic biopsy.

The University Of Texas Southwestern Medical Center

TO IMPROVE SCREENING AND EARLY DETECTION STRATEGIES AND TO DEVELOP ACCURATE DIAGNOSTIC TECHNIQUES AND METHODS FOR PREDICTING THE COURSE OF DISEASE IN CANCER PATIENTS. SCREENING AND EARLY DETECTION RESEARCH INCLUDES DEVELOPMENT OF STRATEGIES TO DECREASE CANCER MORTALITY BY FINDING TUMORS EARLY WHEN THEY ARE MORE AMENABLE TO TREATMENT. DIAGNOSIS RESEARCH FOCUSES ON METHODS TO DETERMINE THE PRESENCE OF A SPECIFIC TYPE OF CANCER, TO PREDICT ITS COURSE AND RESPONSE TO THERAPY, BOTH A PARTICULAR THERAPY OR A CLASS OF AGENTS, AND TO MONITOR THE EFFECT OF THE THERAPY AND THE APPEARANCE OF DISEASE RECURRENCE. THESE METHODS INCLUDE DIAGNOSTIC IMAGING AND DIRECT ANALYSES OF SPECIMENS FROM TUMOR OR OTHER TISSUES. SUPPORT IS ALSO PROVIDED FOR ESTABLISHING AND MAINTAINING RESOURCES OF HUMAN TISSUE TO FACILITATE RESEARCH. SMALL BUSINESS INNOVATION RESEARCH (SBIR) PROGRAM: TO EXPAND AND IMPROVE THE SBIR PROGRAM, TO INCREASE PRIVATE SECTOR COMMERCIALIZATION OF INNOVATIONS DERIVED FROM FEDERAL RESEARCH AND DEVELOPMENT, TO INCREASE SMALL BUSINESS PARTICIPATION IN FEDERAL RESEARCH AND DEVELOPMENT, AND TO FOSTER AND ENCOURAGE PARTICIPATION OF SOCIALLY AND ECONOMICALLY DISADVANTAGED SMALL BUSINESS CONCERNS AND WOMEN-OWNED SMALL BUSINESS CONCERNS IN TECHNOLOGICAL INNOVATION. SMALL BUSINESS TECHNOLOGY TRANSFER (STTR) PROGRAM: TO STIMULATE AND FOSTER SCIENTIFIC AND TECHNOLOGICAL INNOVATION THROUGH COOPERATIVE RESEARCH AND DEVELOPMENT CARRIED OUT BETWEEN SMALL BUSINESS CONCERNS AND RESEARCH INSTITUTIONS, TO FOSTER TECHNOLOGY TRANSFER BETWEEN SMALL BUSINESS CONCERNS AND RESEARCH INSTITUTIONS, TO INCREASE PRIVATE SECTOR COMMERCIALIZATION OF INNOVATIONS DERIVED FROM FEDERAL RESEARCH AND DEVELOPMENT, AND TO FOSTER AND ENCOURAGE PARTICIPATION OF SOCIALLY AND ECONOMICALLY DISADVANTAGED SMALL BUSINESS CONCERNS AND WOMEN-OWNED SMALL BUSINESS CONCERNS IN TECHNOLOGICAL INNOVATION.

93.394 - Cancer Detection and Diagnosis Research

National Cancer Institute (NCI) [HHS - NIH]

Dallas, Texas 753907208 United States

Single Zip Code

Bioengineering Research Grants (BRG) (R01 Clinical Trial Not Allowed) (PAR-19-158)

Amendment Since initial award the total obligations have increased 373% from $655,597 to $3,099,979.