Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstruction, and focuses on various DL approaches and architectures designed to improve image quality, accelerate scans, and address data-related challenges. It explores end-to-end neural networks, pre-trained and generative models, and self-supervised methods, and highlights their contributions to overcoming traditional MRI limitations. It also discusses the role of DL in optimizing acquisition protocols, enhancing robustness against distribution shifts, and tackling biases. Drawing on the extensive literature and practical insights, it outlines current successes, limitations, and future directions for leveraging DL in MRI reconstruction, while emphasizing the potential of DL to significantly impact clinical imaging practices.

Purpose: As the field of CEST grows, various novel preparation periods using different parameters are being introduced. At the same time, large, multisite clinical studies require clearly defined protocols, especially across different vendors. Here, we propose a CEST definition standard using the open Pulseq format for a shareable, simple, and exact definition of CEST protocols.Methods: We present the benefits of such a standard in three ways: (1) an open database on GitHub, where fully defined, human‐readable CEST protocols can be shared; (2) an open‐source Bloch‐McConnell simulation to test and optimize CEST preparation periods in silico; and (3) a hybrid MR sequence that plays out the CEST preparation period and can be combined with any existing readout module.Results: The exact definition of the CEST preparation period, in combination with the flexible simulation, leads to a good match between simulations and measurements. The standard allowed finding consensus on three amide proton transfer–weighted protocols that could be compared in healthy subjects and a tumor patient. In addition, we could show coherent multisite results for a sophisticated CEST method, highlighting the benefits regarding protocol sharing and reproducibility.Conclusion: With Pulseq‐CEST, we provide a straightforward approach to standardize, share, simulate, and measure different CEST preparation schemes, which are inherently completely defined.

Purpose: To develop a clinical CEST MR fingerprinting (CEST‐MRF) method for brain tumor quantification using EPI acquisition and deep learning reconstruction.Methods: A CEST‐MRF pulse sequence originally designed for animal imaging was modified to conform to hardware limits on clinical scanners while keeping scan time under 2 min. Quantitative MRF reconstruction was performed using a deep reconstruction network (DRONE) to yield the water relaxation and chemical exchange parameters. The feasibility of the six parameter DRONE reconstruction was tested in simulations using a digital brain phantom. A healthy subject was scanned with the CEST‐MRF sequence, conventional MRF and CEST sequences for comparison. Reproducibility was assessed via test–retest experiments and the concordance correlation coefficient calculated for white matter and gray matter. The clinical utility of CEST‐MRF was demonstrated on four patients with brain metastases in comparison to standard clinical imaging sequences. Tumors were segmented into edema, solid core, and necrotic core regions and the CEST‐MRF values compared to the contra‐lateral side.Results: DRONE reconstruction of the digital phantom yielded a normalized RMS error of ≤7% for all parameters. The CEST‐MRF parameters were in good agreement with those from conventional MRF and CEST sequences and previous studies. The mean concordance correlation coefficient for all six parameters was 0.98 ± 0.01 in white matter and 0.98 ± 0.02 in gray matter. The CEST‐MRF values in nearly all tumor regions were significantly different (P = 0.05) from each other and the contra‐lateral side.Conclusion: Combination of EPI readout and deep learning reconstruction enabled fast, accurate and reproducible CEST‐MRF in brain tumors.

Multimodal medical imaging is gaining increased popularity in the clinic. This stems from the fact that data acquired from different physical phenomena may provide complementary information resulting in a more comprehensive picture of the pathological state. In this context, nano-sized contrast agents may augment the potential sensitivity of each imaging modality and allow targeted visualization of physiological points of interest (e.g. tumours). In this study, 7 nm copper oxide nanoparticles (CuO NPs) were synthesized and characterized. Then, in vitro and phantom specimens containing CuO NPs ranging from 2.4 to 320 μ g · mL ⁻¹ were scanned, using both 9.4 T MRI and through-transmission ultrasonic imaging. The results show that the CuO NPs induce shortening of the magnetic T1 relaxation time on the one hand, and increase the speed of sound and ultrasonic attenuation coefficient on the other. Moreover, these visible changes are NP concentration-dependent. The change in the physical properties resulted in a substantial increase in the contrast-to-noise ratio (3.4–6.8 in ultrasound and 1.2–19.3 in MRI). In conclusion, CuO NPs are excellent candidates for MRI-ultrasound dual imaging contrast agents. They offer radiation-free high spatial resolution scans by MRI, and cost-effective high temporal resolution scans by ultrasound.