To investigate venous thromboembolism (VTE) in patients undergoing distal cholangiocarcinoma (dCCA) surgery, we performed a single-center study to assess its prevalence, risk factors, prognosis. We studied a total of 177 patients undergoing dCCA surgery from January 2017 to April 2022. Demographic, clinical data, laboratory data (including lower extremity ultrasound findings), and outcome variables were obtained, and compared between VTE and non-VTE groups. Of the 177 patients undergoing dCCA surgery (aged 65.2 ± 9.6 years; 108 (61.0%) male), 64 patients developed VTE after surgery. Logistic multivariate analysis showed that, age, operation procedure, TNM stage, ventilator duration and preoperative D-dimer were independent risk factors. Based on these factors, we constructed the nomogram to predict VTE after dCCA for the first time. The areas under the receiver operating curve (ROC) of the nomogram were 0.80 (95% CI: 0.72-0.88) and 0.79 (95% CI: 0.73-0.89) in the training and validation groups, respectively. Patients developed VTE had a worse prognosis by Kaplan-Meier curve analysis (p = 0.001). The prevalence of VTE is high and is associated with adverse outcomes in patients undergoing dCCA surgery. We developed a nomogram assessing VTE risk, which may help clinicians to screen out people at high risk for VTE and to undertake rational preventive measures.

Micro(mi)RNAs play an essential role in the epithelial-mesenchymal transition (EMT) process in human cancers. This study aimed to uncover the regulatory mechanism of miR-1301-3p on EMT in pancreatic cancer (PC). The miRNA profilings from Gene Expression Omnibus data sets (GSE31568, GSE41372, and GSE32688) demonstrated the downregulation of miR-1301-3p in PC tissues, which was validated with 72 paired PC tissue samples through qRT-PCR detection. The low level of miR-1301-3p was associated with a poor prognosis for PC patients from the PC cohort of The Cancer Genome Atlas and the validation cohort. Gene Ontology analyses indicated that the target genes of miR-1301-3p were involved in cell cycle and adherent junction regulation. In vitro assays revealed that miR-1301-3p suppressed the proliferation and migration abilities of PC cells. Western blotting and luciferase reporter assays suggested that miR-1301-3p inhibited RhoA expression by targeting its 3-untranslated region; RhoA upregulated N-cadherin and vimentin levels; however, it downregulated the E-cadherin level. In conclusion, our study showed that miR-1301-3p could serve as a prognostic biomarker for PC and suppress PC cell malignancy by targeting the RhoA-induced EMT process.

Machine learning has become an emerging paradigm for microrobotics, enabling autonomous micro-/nanorobot navigation in complex and highly disturbed environments without requirements of precise models. However, the state-of-the-art learning-based methods adopt “black-box” neural networks (NNs), which raises critical concerns about the trustworthiness of the generated navigation policies, especially for biomedical scenarios. Motivated to address this issue, we propose a physics-constrained learning framework that embeds deterministic physical laws into network architectures to achieve trustworthy microrobot navigation. Instead of learning from scratch, we explicitly encode the monotonic relationships of kinematics and safety rules into NNs. These constraints serve as structural inductive biases, theoretically guaranteeing that navigation policies operate strictly within the trustworthy action domains. Experiments demonstrate that microrobots can autonomously reach random targets without collision with obstacles during long-time and long-distance navigation, proving our framework’s reliability owing to its explainable nature. This work can bridge the gap between data-driven performance and rigorous safety requirements, constituting a meaningful step toward trustworthy artificial intelligence–empowered microrobotics.

Segmentation of the pancreatic computed tomography (CT) image in the Internet of Medical Things (IoMT) environment faces dual challenges of feature robustness and accurate recognition of small organs. As a clinically critical but anatomically challenging organ, the pancreas exhibits small volume, high interpatient variability, and low contrast with surrounding tissues, making automatic pancreas segmentation a representative and difficult task in abdominal CT analysis. Existing automatic, machine-centric segmentation methods often perform unsatisfactorily across different medical institutions due to variations in imaging devices, changes in scanning protocols, as well as the irregular shape and blurred boundaries of the pancreas. To address this problem, this article proposes a SimCLR-based Contrastive Swin-UNet (ContSwinU) model, which integrates contrastive learning with the Swin Transformer architecture to achieve feature robustness learning and high-precision pancreas segmentation. Specifically, ContSwinU leverages SimCLR to learn robust feature representations, thereby enhancing the model’s generalization capability across diverse scenarios. Additionally, by incorporating the hierarchical window attention mechanism of the Swin Transformer, the model effectively balances local texture and global structural information, improving segmentation accuracy for the pancreas as a small organ. Experimental results on a public pancreas CT dataset demonstrate that ContSwinU achieves an IoU of 0.8041, a Dice coefficient of 0.8872, and a recall of 0.9014, significantly outperforming mainstream baseline methods. These results indicate that the proposed framework is well suited for challenging small-organ segmentation tasks and has the potential to be extended to other organs and multicenter IoMT scenarios. This study provides an effective solution for pancreas segmentation in IoMT environments and has substantial clinical application value.