Improving FLAIR MRI Quality with Super-Resolution Deep Learning Reconstruction

Motivation: FLAIR is valuable for detecting brain abnormalities but often has low SNR, resulting in longer scan-times. A novel approach is needed to enhance image quality without extending scan-time, particularly for detecting white-matter hyperintensities(WMH). Goal(s): This study assesses super-resolution deep-learning reconstruction(SR-DLR) to improve FLAIR image sharpness, SNR, CNR, and WMH segmentation accuracy, comparing it to DLR and conventional methods. Approach: Fourteen-subjects underwent FLAIR, reconstructed using conventional, DLR, and SR-DLR. We assessed image-noise, SNR, CNR, sharpness, and WMH segmentation in a case with moderate hyperintensity. Results: SR-DLR outperformed conventional and DLR methods in SNR, CNR, and sharpness, improving WMH segmentation precision and overall diagnostic utility. Impact: The SR-DLR method could transform FLAIR MRI, enabling improved detection and quantification of white matter lesions without extended scan times. This advancement may influence imaging standards for brain pathology and drive new insights into neuro-degenerative disease diagnosis.