Super-resolution neural networks improve the spatiotemporal resolution of adaptive MRI-guided radiation therapy.

BACKGROUND: Magnetic resonance imaging (MRI) offers superb non-invasive, soft tissue imaging of the human body. However, extensive data sampling requirements severely restrict the spatiotemporal resolution achievable with MRI. This limits the modality's utility in real-time guidance applications, particularly for the rapidly growing MRI-guided radiation therapy approach to cancer treatment. Recent advances in artificial intelligence (AI) could reduce the trade-off between the spatial and the temporal resolution of MRI, thus increasing the clinical utility of the imaging modality. METHODS: We trained deep learning-based super-resolution neural networks to increase the spatial resolution of real-time MRI. We developed a framework to integrate neural networks directly onto a 1.0 T MRI-linac enabling real-time super-resolution imaging. We integrated this framework with the targeting system of the MRI-linac to demonstrate real-time beam adaptation with super-resolution-based imaging. We tested the integrated system using large publicly available datasets, healthy volunteer imaging, phantom imaging, and beam tracking experiments using bicubic interpolation as a baseline comparison. RESULTS: Deep learning-based super-resolution increases the spatial resolution of real-time MRI across a variety of experiments, offering measured performance benefits compared to bicubic interpolation. The temporal resolution is not compromised as measured by a real-time adaptation latency experiment. These two effects, an increase in the spatial resolution with a negligible decrease in the temporal resolution, leads to a net increase in the spatiotemporal resolution. CONCLUSIONS: Deployed super-resolution neural networks can increase the spatiotemporal resolution of real-time MRI. This has applications to domains such as MRI-guided radiation therapy and interventional procedures.

Magnetic resonance imaging (MRI) is a medical imaging modality that is used to image organs such as the brain, lungs, and liver as well as diseases such as cancer. MRI scans taken at high resolution are of overly long duration. This time constraint limits the accuracy of MRI-guided cancer radiation therapy, where imaging must be fast to adapt treatment to tumour motion. Here, we deployed artificial intelligence (AI) models to achieve fast and high detail MRI. We additionally validated our AI models across various scenarios. These AI-based models could potentially enable people with cancer to be treated with higher accuracy and precision.

Plug-and-Play latent feature editing for orientation-adaptive quantitative susceptibility mapping neural networks.

Quantitative susceptibility mapping (QSM) is a post-processing technique for deriving tissue magnetic susceptibility distribution from MRI phase measurements. Deep learning (DL) algorithms hold great potential for solving the ill-posed QSM reconstruction problem. However, a significant challenge facing current DL-QSM approaches is their limited adaptability to magnetic dipole field orientation variations during training and testing. In this work, we propose a novel Orientation-Adaptive Latent Feature Editing (OA-LFE) module to learn the encoding of acquisition orientation vectors and seamlessly integrate them into the latent features of deep networks. Importantly, it can be directly Plug-and-Play (PnP) into various existing DL-QSM architectures, enabling reconstructions of QSM from arbitrary magnetic dipole orientations. Its effectiveness is demonstrated by combining the OA-LFE module into our previously proposed phase-to-susceptibility single-step instant QSM (iQSM) network, which was initially tailored for pure-axial acquisitions. The proposed OA-LFE-empowered iQSM, which we refer to as iQSM+, is trained in a simulated-supervised manner on a specially-designed simulation brain dataset. Comprehensive experiments are conducted on simulated and in vivo human brain datasets, encompassing subjects ranging from healthy individuals to those with pathological conditions. These experiments involve various MRI platforms (3T and 7T) and aim to compare our proposed iQSM+ against several established QSM reconstruction frameworks, including the original iQSM. The iQSM+ yields QSM images with significantly improved accuracies and mitigates artifacts, surpassing other state-of-the-art DL-QSM algorithms. The PnP OA-LFE module's versatility was further demonstrated by its successful application to xQSM, a distinct DL-QSM network for dipole inversion. In conclusion, this work introduces a new DL paradigm, allowing researchers to develop innovative QSM methods without requiring a complete overhaul of their existing architectures.

Roles and challenges encountered by midwives in the management of postpartum haemorrhage following normal vaginal delivery: A scoping review.

AIMS: To establish a comprehensive understanding of the roles of midwives and the challenges they encounter in the prevention, diagnosis and management of postpartum haemorrhage (PPH) following normal vaginal delivery. DESIGN: We conducted a scoping review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis for Scoping Reviews (PRISMA-ScR) recommendations. METHODS: We considered studies related to the roles of midwives and the challenges they encounter in the prevention, diagnosis and management of PPH during vaginal delivery. We excluded guidelines, consensuses, abstracts of meetings and non-English language studies. Databases, including the Cochrane Library, PubMed, Web of Science, Ovid, Medline, Embase, JBI EBP and BIOSIS Previews, were searched on January 1, 2023, with no time limitations. RESULTS: We included 28 publications. Midwives play important roles in the prevention, diagnosis and management of postpartum haemorrhage during vaginal delivery. In the prevention of PPH, midwives' roles include identifying and managing high-risk factors, managing labour and implementing skin-to-skin contact. In the diagnosis of PPH, midwives' roles include early recognition and blood loss estimation. In the management of PPH, midwives are involved in mobilizing other professional team members, emergency management, investigating causes, enhancing uterine contractions, the repair of perineal tears, arranging transfers and preparation for surgical intervention. However, midwives face substantial challenges, including insufficient knowledge and skills, poor teamwork skills, insufficient resources and the need to deal with their negative emotions. Midwives must improve their knowledge, skills and teamwork abilities. Health care system managers and the government should give full support to midwives. Future research should focus on developing clinical practice guidelines for midwives for preventing, diagnosing and managing postpartum haemorrhage.

Imaging and Downstaging Bladder Cancer with the 177Lu-Labeled Bioorthogonal Nanoprobe.

Efforts on bladder cancer treatment have been shifting from extensive surgery to organ preservation in the past decade. To this end, we herein develop a multifunctional nanoagent for bladder cancer downstaging and bladder-preserving therapy by integrating mucosa penetration, reduced off-target effects, and internal irradiation therapy into a nanodrug. Specifically, an iron oxide nanoparticle was used as a carrier that was coated with hyaluronic acid (HA) for facilitating mucosa penetration. Dibenzocyclooctyne (DBCO) was introduced into the HA coating layer to react through bioorthogonal reaction with azide as an artificial receptor of bladder cancer cells, to improve the cellular internalization of the nanoprobe labeled with 177Lu. Through magnetic resonance imaging, the targeted imaging of both nonmuscle-invasive bladder cancer (NMIBC) and muscle-invasive bladder cancer (MIBC) was realized after intravesical instillation of the multifunctional probe, both NMIBC and MIBC were found downstaged, and the metastasis was inhibited, which demonstrates the potential of the multifunctional nanoprobe for bladder preservation in bladder cancer treatment.

Trapped in Endosome PEGylated Ultra-Small Iron Oxide Nanoparticles Enable Extraordinarily High MR Imaging Contrast for Hepatocellular Carcinomas.

The early diagnosis of hepatocellular carcinomas (HCCs) remains challenging in the clinic. Primovist-enhanced magnetic resonance imaging (MRI) aids HCC diagnosis but loses sensitivity for tumors <2 cm. Therefore, developing advanced MRI contrast agents is imperative for improving the diagnostic accuracy of HCCs in very-early-stage. To address this challenge, PEGylated ultra-small iron oxide nanoparticles (PUSIONPs) are synthesized and employed as liver-specific T1 MRI contrast agents. Intravenous delivery produces simultaneous hyperintense HCC and hypointense hepatic parenchyma signals on T1 imaging, creating an extraordinarily high tumor-to-liver contrast. Systematic studies uncover PUSIONP distribution in hepatic parenchyma, HCC lesions at the organ, tissue, cellular, and subcellular levels, revealing endosomal confinement of PUSIONP without aggregation. By mimicking such situations, the dependency of relaxometric properties on local PUSIONP concentration is investigated, emphasizing the key role of different endosomal concentrations in liver and tumor cells for high tumor-to-liver contrast and clear tumor boundaries. These findings offer exceptional imaging capabilities for early HCC diagnosis, potentially benefiting real HCC patients.

Open-source hardware and software for the measurement, characterization, reporting, and correction of geometric distortion in MRI.

BACKGROUND: Geometric distortion is a serious problem in MRI, particularly in MRI guided therapy. A lack of affordable and adaptable tools in this area limits research progress and harmonized quality assurance. PURPOSE: To develop and test a suite of open-source hardware and software tools for the measurement, characterization, reporting, and correction of geometric distortion in MRI. METHODS: An open-source python library was developed, comprising modules for parametric phantom design, data processing, spherical harmonics, distortion correction, and interactive reporting. The code was used to design and manufacture a distortion phantom consisting of 618 oil filled markers covering a sphere of radius 150 mm. This phantom was imaged on a CT scanner and a novel split-bore 1.0 T MRI magnet. The CT images provide distortion-free dataset. These data were used to test all modules of the open-source software. RESULTS: All markers were successfully extracted from all images. The distorted MRI markers were mapped to undistorted CT data using an iterative search approach. Spherical harmonics reconstructed the fitted gradient data to 1.0 ± 0.6% of the input data. High resolution data were reconstructed via spherical harmonics and used to generate an interactive report. Finally, distortion correction on an independent data set reduced distortion inside the DSV from 5.5 ± 3.1 to 1.6 ± 0.8 mm. CONCLUSION: Open-source hardware and software for the measurement, characterization, reporting, and correction of geometric distortion in MRI have been developed. The utility of these tools has been demonstrated via their application on a novel 1.0 T split bore magnet.

Using Adaptive Imaging Parameters to Improve PEGylated Ultrasmall Iron Oxide Nanoparticles-Enhanced Magnetic Resonance Angiography.

The PEGylated ultrasmall iron oxide nanoparticles (PUSIONPs) exhibit longer blood residence time and better biodegradability than conventional gadolinium-based contrast agents (GBCAs), enabling prolonged acquisitions in contrast-enhanced magnetic resonance angiography (CE-MRA) applications. The image quality of CE-MRA is dependent on the contrast agent concentration and the parameters of the pulse sequences. Here, a closed-form mathematical model is demonstrated and validated to automatically optimize the concentration, echo time (TE), repetition time (TR) and flip angle (FA). The pharmacokinetic studies are performed to estimate the dynamic intravascular concentrations within 12 h postinjection, and the adaptive concentration-dependent sequence parameters are determined to achieve optimal signal enhancement during a prolonged measurement window. The presented model is tested on phantom and in vivo rat images acquired from a 3T scanner. Imaging results demonstrate excellent agreement between experimental measurements and theoretical predictions, and the adaptive sequence parameters obtain better signal enhancement than the fixed ones. The low-dose PUSIONPs (0.03 mmol kg-1 and 0.05 mmol kg-1) give a comparable signal intensity to the high-dose one (0.10 mmol kg-1) within 2 h postinjection. The presented mathematical model provides guidance for the optimization of the concentration and sequence parameters in PUSIONPs-enhanced MRA, and has great potential for further clinical translation.