Hepatocellular carcinoma (HCC) is a kind of complicated disease with an increasing incidence all over the world. A classic Chinese medicine formula, Zuojin pill (ZJP), was shown to exert therapeutic effects on HCC. However, its chemical and pharmacological profiles remain to be elucidated. In the current study, network pharmacology approach was applied to characterize the action mechanism of ZJP on HCC. All compounds were obtained from the corresponding databases, and active compounds were selected according to their oral bioavailability and drug-likeness index. The potential proteins of ZJP were obtained from the traditional Chinese medicine systems pharmacology (TCMSP) database and the traditional Chinese medicine integrated database (TCMID), whereas the potential genes of HCC were obtained from OncoDB.HCC and Liverome databases. The potential pathways related to genes were determined by gene ontology (GO) and pathway enrichment analyses. The compound-target and target-pathway networks were constructed. Subsequently, the potential underlying action mechanisms of ZJP on HCC predicted by the network pharmacology analyses were experimentally validated in HCC cellular and orthotopic HCC implantation murine models. A total of 224 components in ZJP were obtained, among which, 42 were chosen as bioactive components. The compound-target network included 32 compounds and 86 targets, whereas the target-pathway network included 70 proteins and 75 pathways. The in vitro and in vivo experiments validated that ZJP exhibited its prominent therapeutic effects on HCC mainly via the regulation of cell proliferation and survival though the EGFR/MAPK, PI3K/NF-κB, and CCND1 signaling pathways. In conclusion, our study suggested combination of network pharmacology prediction with experimental validation may offer a useful tool to characterize the molecular mechanism of traditional Chinese medicine (TCM) ZJP on HCC.

Compressed sensing (CS) reconstruction methods leverage sparse structure in underlying signals to recover high-resolution images from highly undersampled measurements. When applied to magnetic resonance imaging (MRI), CS has the potential to dramatically shorten MRI scan times, increase diagnostic value, and improve overall patient experience. However, CS has several shortcomings which limit its clinical translation such as: 1) artifacts arising from inaccurate sparse modelling assumptions, 2) extensive parameter tuning required for each clinical application, and 3) clinically infeasible reconstruction times. Recently, CS has been extended to incorporate deep neural networks as a way of learning complex image priors from historical exam data. Commonly referred to as unrolled neural networks, these techniques have proven to be a compelling and practical approach to address the challenges of sparse CS. In this tutorial, we will review the classical compressed sensing formulation and outline steps needed to transform this formulation into a deep learning-based reconstruction framework. Supplementary open source code in Python will be used to demonstrate this approach with open databases. Further, we will discuss considerations in applying unrolled neural networks in the clinical setting.

Purpose To develop a deep learning reconstruction approach to improve the reconstruction speed and quality of highly undersampled variable-density single-shot fast spin-echo imaging by using a variational network (VN), and to clinically evaluate the feasibility of this approach. Materials and Methods Imaging was performed with a 3.0-T imager with a coronal variable-density single-shot fast spin-echo sequence at 3.25 times acceleration in 157 patients referred for abdominal imaging (mean age, 11 years; range, 1-34 years; 72 males [mean age, 10 years; range, 1-26 years] and 85 females [mean age, 12 years; range, 1-34 years]) between March 2016 and April 2017. A VN was trained based on the parallel imaging and compressed sensing (PICS) reconstruction of 130 patients. The remaining 27 patients were used for evaluation. Image quality was evaluated in an independent blinded fashion by three radiologists in terms of overall image quality, perceived signal-to-noise ratio, image contrast, sharpness, and residual artifacts with scores ranging from 1 (nondiagnostic) to 5 (excellent). Wilcoxon tests were performed to test the hypothesis that there was no significant difference between VN and PICS. Results VN achieved improved perceived signal-to-noise ratio (P = .01) and improved sharpness (P < .001), with no difference in image contrast (P = .24) and residual artifacts (P = .07). In terms of overall image quality, VN performed better than did PICS (P = .02). Average reconstruction time ± standard deviation was 5.60 seconds ± 1.30 per section for PICS and 0.19 second ± 0.04 per section for VN. Conclusion Compared with the conventional parallel imaging and compressed sensing reconstruction (PICS), the variational network (VN) approach accelerates the reconstruction of variable-density single-shot fast spin-echo sequences and achieves improved overall image quality with higher perceived signal-to-noise ratio and sharpness. © RSNA, 2018 Online supplemental material is available for this article.

Hepatocellular carcinoma (HCC) is the sixth most common cancer worldwide with high mortality. Circulating miRNA has been demonstrated as a novel noninvasive biomarker for many tumors. This study aimed to investigate the potential of circulating miR-125b as a prognostic marker of HCC. Exosomes were extracted from serum samples collected from two independent cohorts: cohort 1: HCC (n=30), chronic hepatitis B (CHB, n=30), liver cirrhosis (LC, n=30); cohort 2: HCC (n=128). We found that miR-125b levels were remarkably increased in exosomes compared to those in serum from patients with CHB, LC, and HCC (P<0.01, respectively). However, miR-125b levels in exosomes and the serum from HCC patients were inferior to that of CHB (P<0.01 and P=0.06) and LC patients (P<0.01 for all). Additionally, miR-125b levels in exosomes were associated with tumor number (P=0.02), encapsulation (P<0.01), and TNM stage (P<0.01). Kaplan–Meier analysis indicated that HCC patients with lower exosomal miR-125b levels showed reduced time to recurrence (TTR) (P<0.01) and overall survival (OS) (P<0.01). Furthermore, multivariate analysis revealed that miR-125b level in exosomes, but not in serum, was an independent predictive factor for TTR (P<0.001) and OS (P=0.011). Exosomal miR-125b levels predicted the recurrence and survival of HCC patients with an area under the ROC curve of 0.739 (83.0% sensitivity and 67.9% specificity) and 0.702 (82.5% sensitivity and 53.4% specificity). In conclusion, exosomal miR-125b could serve as a promising prognostic marker for HCC.