September 17, 2025

Initial Clinical Evaluation of Motion-Informed Deep Learning Reconstruction for 3D MPRAGE and FLAIR Brain MRI

Puntos clave

Motion-informed deep learning reconstruction improved signal-to-noise ratio in clinical scans, ensuring better image quality.
Out of 20 patients, the technique demonstrated reduced motion artifacts compared to conventional methods, emphasizing its clinical applicability.
Two neuro-radiologists rated the images using a 5-point scale, providing a reliable evaluation of the technique's effectiveness.
The study indicates that motion-corrected deep learning could enhance MRI scanning for acutely ill patients, aiding faster diagnoses.

Resumen

Motivation: Fast and motion-robust 3D acquisition is challenging but desirable in clinical scans. Goal(s): To validate a motion correction-integrated 3D DL reconstruction technique on patient cohort to evaluate their effectiveness and reliability in a clinical setting. Approach: This prospective study included 20 patients from inpatient care settings at an academic hospital scanned with 3D MPRAGE and 3D SPACE FLAIR at 3T. Two neuro-radiologists performed blinded ratings of the images based on 5-point Likert scale. Results: Of the 20 cases, 4 cases were post-contrast enhanced exams. DL+MoCo demonstrated higher SNR compared to conventional reconstruction. DL+MoCo reduced motion artifacts compared to SENSE in cases with motion. Impact: This initial evaluation of motion-informed DL reconstruction on various pathologies demonstrated the effectiveness of the technique in acutely ill patients.

Me gusta

Guardar