An artificial intelligence‐accelerated 2‐minute multi‐shot echo planar imaging protocol for comprehensive high‐quality clinical brain imaging. Issue 5 (31st December 2021)

• Record Type: Journal Article
• Authors: Clifford, Bryan; Conklin, John; Huang, Susie Y.; Feiweier, Thorsten; Hosseini, Zahra; Goncalves Filho, Augusto Lio M.; Tabari, Azadeh; Demir, Serdest; Lo, Wei‐Ching; Longo, Maria Gabriela Figueiro; Lev, Michael; Schaefer, Pam; Rapalino, Otto; Setsompop, Kawin; Bilgic, Berkin; Cauley, Stephen
• Is Part Of: Magnetic resonance in medicine. Volume 87:Issue 5(2022)
• Page Start: 2453
• Page End: 2463
• Publication Date: 2021-12-31
• Subjects: brain -- clinical applications -- machine learning/artificial intelligence; Nuclear magnetic resonance -- Periodicals; Electron paramagnetic resonance -- Periodicals; 616.07548
• DOI: 10.1002/mrm.29117
• Languages: English
• ISSNs: 0740-3194

Abstract

Abstract : Purpose: We introduce and validate an artificial intelligence (AI)‐accelerated multi‐shot echo‐planar imaging (msEPI)‐based method that provides T1w, T2w, T 2 ∗, T2‐FLAIR, and DWI images with high SNR, high tissue contrast, low specific absorption rates (SAR), and minimal distortion in 2 minutes. Methods: The rapid imaging technique combines a novel machine learning (ML) scheme to limit g‐factor noise amplification and improve SNR, a magnetization transfer preparation module to provide clinically desirable contrast, and high per‐shot EPI undersampling factors to reduce distortion. The ML training and image reconstruction incorporates a tunable parameter for controlling the level of denoising/smoothness. The performance of the reconstruction method is evaluated across various acceleration factors, contrasts, and SNR conditions. The 2‐minute protocol is directly compared to a 10‐minute clinical reference protocol through deployment in a clinical setting, where five representative cases with pathology are examined. Results: Optimization of custom msEPI sequences and protocols was performed to balance acquisition efficiency and image quality compared to the five‐fold longer clinical reference. Training data from 16 healthy subjects across multiple contrasts and orientations were used to produce ML networks at various acceleration levels. The flexibility of the ML reconstruction was demonstrated across SNR levels, and an optimized regularization was determined through radiological review. Network generalization toward novel pathology, unobserved during training, was illustrated in five clinical case studies with clinical reference images provided for comparison. Conclusion: The rapid 2‐minute msEPI‐based protocol with tunable ML reconstruction allows for advantageous trade‐offs between acquisition speed, SNR, and tissue contrast when compared to the five‐fold slower standard clinical reference exam.