Deep Learning-Powered Super Resolution Reconstruction Improves 2D T2-Weighted Turbo Spin Echo MRI of the Hippocampus

Purpose: To assess the performance of 2D T2-weighted (w) Turbo Spin Echo (TSE) MRI reconstructed with a deep learning (DL)-powered super resolution reconstruction (SRR) algorithm combining compressed sensing (CS) denoising and resolution upscaling for high-resolution hippocampal imaging in patients with (epileptic) seizures and suspected hippocampal pathology. Methods: A 2D T2w TSE coronal hippocampal sequence with compressed sense (CS) factor 1 (scan time 270 s) and a CS-accelerated sequence with a CS factor of 3 (scan time 103 s) were acquired in 28 patients. Reconstructions using the SRR algorithm (CS 1-SSR-s and CS 3-SSR-s) were additionally obtained in real time. Two readers graded the images twice, based on several metrics (image quality; artifacts; visualization of anatomical details of the internal hippocampal architecture (HIA); visibility of dentate gyrus/pes hippocampi/fornix/mammillary bodies; delineation of gray and white matter). Results: Inter-readout agreement was almost perfect (Krippendorff’s alpha coefficient = 0.933). Compared to the CS 1 sequence, the CS 3 sequence significantly underperformed in all 11 metrics (p < 0.001-p = 0.04), while the CS 1-SRR-s sequence outperformed in terms of overall image quality and visualization of the left HIA and right pes hippocampi (p < 0.001-p < 0.04) but underperformed in terms of presence of artifacts (p < 0.01). Lastly, relative to the CS 1 sequence, the CS 3-SRR-s sequence was graded worse in terms of presence of artifacts (p < 0.003) but with improved visualization of the right pes hippocampi (p = 0.02). Conclusion: DL-powered SSR demonstrates its capacity to enhance imaging performance by introducing flexibility in T2w hippocampal imaging; it either improves image quality for non-accelerated imaging or preserves acceptable quality in accelerated imaging, with the additional benefit of a reduced scan time.