Compressed sensing (CS) is a rapidly developing technique for reducing scanning times while maintaining image contrast and quality. CS theory affirms that certain images can be recovered from highly compressed k-space data with an appropriate reconstruction algorithm. This article reviews the fundamentals of CS, its methods, pulse sequence designs, the reconstruction algorithm, and potential artifacts and their causes, which are important for implementing the CS technique in clinical practice.

 Recently, compressed sensing, which allows for rapid MRI scanning using signal sparsity and random sampling, has been introduced as a method for routine clinical examinations. This article presents an overview of the implementation of compressed sensing on clinical scanners. In the first section, the purpose of this article and the motivation behind it are provided. In the second section, the practical implementation, including trajectories, reconstruction schemes, and algorithms, is reviewed. Clinically available applications that use compressed sensing techniques in clinical scanners are introduced in the third section. Finally, challenges and future prospects of the technology are discussed.

 Compressed sensing (CS) MR has been introduced as an innovative sparse recovery framework that supports k-space undersampling for accelerated image acquisition. CS is expected to achieve higher k-space undersampling by exploiting the underlying sparsity in an appropriate transform domain. Clinical applications of CS in neuroradiology are presented and discussed in this review.