A deep learning substitute for Gadolinium contrast detects focused ultrasound-induced blood-brain barrier (BBB) opening

This technology is a deep-contrast AI-enabled algorithm to predict blood-brain barrier (BBB) openings from T1 MRI sequences using low doses of gadolinium-based contrast agents (GBCA).

Unmet Need: Detection of ultrasound-induced BBB-opening with lower gadolinium-based contrast agent (GBCA) exposure

Focused ultrasound is a promising technique for non-invasive drug delivery, by creating microbubbles in the BBB to temporarily expose the central nervous system (CNS). However, the detection of these openings requires repeated T1-weighted MRI sequences using gadolinium-based contrast agents (GBCAs), which with repeated use can accumulate and be retained by body tissues, including the brain. This is a significant concern for patient safety and comfort, and there remains a need for MRI detection of BBB openings for FUS with decreased exposure to GBCAs.

The Technology: Deep-contrast AI prediction of BBB openings using low-dose GBCA

This technology uses a deep learning algorithm to predict focused ultrasound blood-brain barrier (BBB) openings from low-dose gadolinium-based contrast agents (GBCAs) T1 sequences. This includes the development of a refined imaging protocol for acquiring Deep Contrast Enhancement (DCE)-MRI images and construction of a deep learning model (ST-Net) to predict full-dose GBCA BBB-opening from low-dose DCE-MRI images. Compared to existing technologies, this method allows for decreased exposure to harmful GBCAs and minimizes scan times, thereby increasing patient safety.

This technology has been validated with in vivo testing in mice.

Applications:

• Clinical drug delivery
• Drug dose monitoring
• Research for drug and therapeutic discovery
• Measurement and tracking of neurological function

Advantages:

• Decreased exposure to gadolinium-based contrast agents (GBCAs) to increase patient safety
• Enables prediction of blood-brain barrier (BBB)-openings to optimize CNS drug delivery
• Minimizes MRI scanning time and costs
• Decreased patient discomfort and movement/motion artifacts

Lead Inventor:

Jia Guo, Ph.D.

Patent Information:

Patent Pending

Related Publications:

• Lee PY, Wei HJ, Pouliopoulos AN, Forsyth BT, Yang Y, Zhang C, Laine AF, Konofagou EE, Wu CC, Guo J. “Deep Learning Enables Reduced Gadolinium Dose for Contrast-Enhanced Blood-Brain Barrier Opening” arXiv. 2023 Jan.

• Liu C, Zhu N, Sun H, Zhang J, Feng X, Gjerswold-Selleck S, Sikka D, Zhu X, Liu X, Nuriel T, Wei H-J, Wu C-C, Vaughan JT, Laine AF, Provenzano FA, Small SA and Guo J. “Deep learning of MRI contrast enhancement for mapping cerebral blood volume from single-modal non-contrast scans of aging and Alzheimer's disease brains” Front. Aging Neurosci. 2022 Aug.

Tech Ventures Reference:

• IR CU23205

• Licensing Contact: Jerry Kokoshka