Predictive value of ultrasonic artificial intelligence in placental characteristics of early pregnancy for gestational diabetes mellitus.

Background: To explore the predictive value of placental features in early pregnancy for gestational diabetes mellitus (GDM) using deep and radiomics-based machine learning (ML) applied to ultrasound imaging (USI), and to develop a nomogram in conjunction with clinical features. Methods: This retrospective multicenter study included 415 pregnant women at 11-13 weeks of gestation from two institutions: the discovery group from center 1 (n=305, control group n=166, GDM group n=139), and the independent validation cohort (n=110, control group n=57, GDM group n=53) from center 2. The 2D USI underwent pre-processed involving normalization and resampling. Subsequently, the study performed screening of radiomics features with Person correlation and mutual information methods. An RBF-SVM model based on radiomics features was constructed using the five-fold cross-validation method. Resnet-50 as the backbone network was employed to learn the region of interest and constructed a deep convolutional neural network (DLCNN) from scratch learning. Clinical variables were screened using one-way logistic regression, with P<0.05 being the threshold for statistical significance, and included in the construction of the clinical model. Nomogram was built based on ML model, DLCNN and clinical models. The performance of nomogram was assessed by calibration curves, area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). Results: The AUCs for the ML model in the discovery cohort and independent validation cohort were 0.91 (0.88-0.94) and 0.86 (0.79-0.93), respectively. And 0.65 (0.59-0.71), 0.69 (0.59-0.79) for the DLCNN, 0.66 (0.59-0.72), 0.66 (0.55-0.76) for the clinical model, respectively. The nomogram exhibited the highest performance with AUCs of 0.93 (0.90-0.95) and 0.88 (0.81-0.94) The receiver operating characteristic curve (ROC) proved the superiority of the nomogram of clinical utility, and calibration curve showed the goodness of fit of the model. The DCA curve indicated that the nomogram outperformed other models in terms of net patient benefit. Conclusions: The study emphasized the intrinsic relationship between early pregnancy placental USI and the development of GDM. The use of nomogram holds potential for clinical applications in predicting the development of GDM.

Ultrasound-triggered release of miR-199a-3p from liposome nanobubbles for enhanced hepatocellular carcinoma treatment.

This study was aimed to develop an efficient tumour-targeted liposome nanobubbles (LNBs) system using ultrasound-targeted nanobubble destruction for enhanced release and transfection of miRNA-199a-3p in hepatocellular carcinoma (HCC) therapy. The prepared LNBs comprised a polyethylene glycol-modified liposome shell and a perfluoropentane (PFP) core. MiRNA-199a-3p was attached to the nanocomposite surface via electrostatic adsorption, while RGD peptide functionalized the LNBs surface for enhanced HCC cell targeting, namely PFP@miR-RGD-LNBs. The LNBs were spherical with a narrow size distribution. The gene-loaded LNBs effectively condensed miR-199a-3p and protected it from enzymatic degradation. Low-intensity focused ultrasound (LIFU) promoted a fast release of miR-199a-3p from the prepared LNBs, thereby enhancing therapeutic effects. The combined application of PFP@miR-RGD-LNBs and LIFU exhibited a more potent inhibitory effect on HepG2 cells than the other groups, potentially due to LIFU promoting rapid and efficient gene release at the target site and increasing cell membrane permeability. Quantitative reverse transcription-polymerase chain reaction analysis revealed significantly increased mRNA expression levels of key apoptosis markers (Bad, Bax, Caspase-9 and Caspase-3) in the PFP@miR-RGD-LNBs + LIFU group compared to other groups. These findings suggest that the prepared LNBs are highly likely to be promising candidates for further exploration of HCC gene delivery and therapy.

Synergistic delivery of resveratrol and ultrasmall copper-based nanoparticles by aptamer-functionalized ultrasound nanobubbles for the treatment of nonalcoholic fatty liver disease.

Nonalcoholic fatty liver disease (NAFLD) is related to the production of reactive oxygen species (ROS) and oxidative stress, so antioxidant treatment can prevent its further development. Ultrasmall copper-based nanoparticles (CuNPs) have shown multiple enzyme-like activities for scavenging oxygen species, providing a new strategy for the treatment of inflammatory diseases. Resveratrol (Res), a natural polyphenol compound, has attracted much attention due to its ability to inhibit oxidative stress. We therefore aimed to first combine these two agents for the treatment of NAFLD. However, due to the poor water solubility and stability of Res, which is easily metabolized in the intestine, the development of a stable and effective carrier became the key to achieving a synergistic effect. Liver-targeted nanocarriers loaded with bioactive compounds may provide a more effective approach for the treatment of NAFLD. Therefore, we developed a novel ultrasonic nanobubble carrying nucleic acid aptamers with liver targeting properties, which has the advantages of a small molecular weight, no immunogenicity, a low cost of synthesis, and high stability through chemical modification. Res and the ultrasmall CuNPs were specifically delivered to liver tissue to maximize therapeutic efficiency. This study found that the combination of these two components can effectively treat inflammation in NAFLD and suggested that liver-targeted NAFLD-specific aptamer-mediated targeted ultrasound nanobubbles that can simultaneously deliver Res and CuNPs may be a safe and effective new platform for NAFLD and other liver diseases.