Artificial intelligence contrast algorithm for safer stroke diagnosis

This technology is a method that utilizes artificial intelligence for contrast enhancement in the diagnosis of stroke.

Unmet Need: Simple, safe method for detecting strokes

Current methods for diagnosing strokes include the use of medical imaging techniques, such as computer tomography (CT) and magnetic resonance imaging (MRI), which may employ contrast agents, like gadolinium-based agents, to enhance image quality. However, these methods are associated with exposures to radiation, gadolinium retention toxicities, and high costs.

The Technology: Artificial intelligence contrast for stroke diagnosis

This technology is a safer method for stroke diagnosis that employs a deep learning approach, enabling the reduction of contrast agent dosages. Using a deep contrast algorithm, artificial intelligence can predict regions of contrast enhancement with a lower gadolinium dose than is typically used, thereby reducing potential gadolinium retention and associated toxicities. As such, this technology can enhance methods of stroke diagnosis through the use of artificial intelligence.

Applications:

• Diagnosis of stroke
• Diagnosis of schizophrenia
• Research tool for neurological conditions

Advantages:

• Low cost
• Increased safety
• Decreased hospital time

Lead Inventor:

Scott A. Small, Ph.D.

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.” 2023 Jan.

• Liu D, Xin Z, Ji R, Tsitsos F, Jiménez-Gambín S, Konofagou EE, Ferrera VP, Guo J. “Enhancing transcranial focused ultrasound treatment planning with synthetic CT from ultra-short echo time (UTE) MRI: a multi-task deep learning approach.” Proc IEEE Int Symp Biomed Imaging. 2024 May; 2024.

Tech Ventures Reference:

• IR CU25197

• Licensing Contact: Jerry Kokoshka