RPI ID: 2018-029-401

Innovation Summary:
This invention introduces a synergized pulsing-imaging network (SPIN) that jointly optimizes MRI pulse sequences and image reconstruction. The system uses a deep learning framework to co-train the pulse generation and image reconstruction modules, improving image quality and acquisition efficiency. It adapts to different imaging tasks and patient conditions, enabling personalized MRI protocols. The approach significantly reduces scan time while maintaining diagnostic accuracy.

Challenges / Opportunities:
MRI scans are time-consuming and often require manual tuning of pulse sequences, which can limit throughput and consistency. Traditional optimization methods treat pulse design and image reconstruction separately. This invention addresses these inefficiencies by integrating both processes into a unified AI-driven framework. It opens opportunities for faster, more adaptive MRI systems.

Key Benefits / Advantages:
✔ Joint optimization enhances both pulse design and image quality
✔ Reduced scan time improves patient comfort and throughput
✔ Personalized imaging adapts to individual anatomy and conditions
✔ AI integration enables intelligent, task-specific MRI protocols

Applications:
• Clinical MRI diagnostics
• Neurological and cardiovascular imaging
• Pediatric and motion-sensitive imaging
• MRI research and development

Keywords:
#MRIoptimization #pulsesequencedesign #deeplearning #SPINnetwork #medicalimagingAI

Intellectual Property:
US Issued Patent 11,454,690 B2