ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

Objective To investigate the status of population dynamics and distribution changes of Aedes aegypti in Guangdong Province.Methods Continuous monitoring was conducted from May 2018 to July 2024 in Wushi Town and Qishui Town,Leizhou City,Zhanjiang City,Guangdong Province.Additionally,a survey of the distribution of Ae.aegypti along the Leizhou Peninsula coast was carried out.Results The density of Ae.aegypti in Zhanjiang showed a gradual decline from 2018 to 2024.The last detection of adult Ae.aegypti in Wushi Town was in September 2021,and the last larva was found in October 2023.No Ae.aegypti was detected in Qishui Town during surveys from 2021 to 2024.A survey of 18 coastal villages in the Leizhou Peninsula revealed no detections of Ae.aegypti.Conclusions This study provides a basis for understanding the distribution and population density fluctuations of Ae.aegypti,assessing its invasion risk,and scientifically conducting relevant prevention and control efforts.

Objective:To investigate the regulatory effects of transcutaneous auricular vagus nerve stimulation (taVNS) on functional connectivity (FC) of thalamic subregions in patients with premenstrual syndrome (PMS).Methods:This study was a cross-sectional investigation. Clinical, laboratory, and imaging data were retrospectively collected from 56 PMS patients (PMS group) and 66 healthy controls (control group) recruited from various universities and hospitals in Nanning between November 2021 and June 2024. Resting-state functional MRI (fMRI) data and fMRI data during taVNS immediate stimulation (2 Hz, 25 Hz) were acquired from subjects during their late luteal phase. Using thalamic subregions (anterior thalamic nucleus, lateral nucleus, ventral nucleus, medial nucleus, central nucleus, posterior nucleus) as seeds, two-sample t-tests or paired t-tests were employed to analyze alterations in thalamic subregion FC in PMS patients and the regulatory effects of taVNS on these changes. Independent samples t-test were used to compare the differences in clinical and laboratory indicators between the PMS group and the control group. The relationship between taVNS regulation of thalamic subregion FC in PMS patients and thalamic internal functional connectivity were analyzed using mediation effect analysis. Results:Compared to the control group, patients in the PMS group showed increased scores on the Daily Record of Severity of Problems, Pittsburgh Sleep Quality Index, Self-Rating Anxiety Scale, Self-Rating Depression Scale, Hamilton Anxiety Rating Scale 17, and Hamilton Depression Rating Scale 14 during the late luteal phase ( P<0.05). At baseline, PMS patients exhibited higher FC between the left thalamic lateral nucleus and the left insula, and lower FC between the left medial nucleus, posterior nucleus, and ventral nucleus of the thalamus and the right middle frontal gyrus (MFG) compared to the control group (GRF corrected, voxel-level P<0.001, cluster-level P<0.05). During 2 Hz taVNS immediate stimulation in PMS group, FC between the left thalamic medial nucleus, posterior nucleus, ventral nucleus and the right MFG, as well as the FC between the left thalamic ventral nucleu and the left MFG increased compared to baseline levels; meanwhile, FC between the left thalamic posterior nucleus, ventral nucleus and the left insula decreased compared to baseline levels (GRF corrected, voxel-level P<0.001, cluster-level P<0.05). During 25 Hz taVNS immediate stimulation, the FC between the left thalamic ventral nucleus and the right MFG decreased compared to the baseline level (GRF corrected, voxel-level P<0.001, cluster-level P<0.05). Mediation effect analysis showed that the FC between the left thalamic posterior nucleus and the left lateral nucleus mediated part of the association between the FC of the left lateral thalamic nucleus-left insula and the FC of the left ventral thalamic nucleus-left putamen/insula; there were significant direct effects between the FC of the left lateral thalamic nucleus-the left posterior nucleus and FC of the left lateral thalamic nucleus-the left insula, as well as between the FC of the left ventral thalamic nucleus-the left MFG and FC of the left ventral thalamic nucleus-the right MFG. Conclusions:taVNS can modulate abnormal FC of the left thalamic subregions in PMS patients, restoring it toward normalization. The regulatory effects of 2 Hz stimulation are more pronounced than those of 25 Hz stimulation. This modulation primarily operates through two pathways: the left thalamic lateral nucleus-left insula-left thalamic ventral nucleus pathway and the left MFG-left thalamic ventral nucleus-right MFG.

Background: Despite the fact that an increasing number of studies have focused on developing therapies for acute lung injury, managing acute respiratory distress syndrome (ARDS) remains a challenge in intensive care medicine.Whether the pathology of animal models with acute lung injury in prior studies differed from clinical symptoms of ARDS, resulting in questionable management for human ARDS. To evaluate precisely the therapeutic effect of trans‑ planted stem cells or medications on acute lung injury, we developed an animal model of severe ARDS with lower lung function, capable of keeping the experimental animals survive with consistent reproducibility. Establishing this animal model could help develop the treatment of ARDS with higher efficiency. Results: In this approach, we intratracheally delivered bleomycin (BLM, 5 mg/rat) into rats’ left trachea via a needle connected with polyethylene tube, and simultaneously rotated the rats to the left side by 60 degrees. Within sevendays after the injury, we found that arterial blood oxygen saturation ­(SpO2 ) significantly decreased to 83.7%, partial pressure of arterial oxygen ­(PaO2 ) markedly reduced to 65.3 mmHg, partial pressure of arterial carbon dioxide ­(PaCO2 )amplified to 49.2 mmHg, and the respiratory rate increased over time. Morphologically, the surface of the left lung appeared uneven on Day 1, the alveoli of the left lung disappeared on Day 2, and the left lung shrank on Day 7. A his‑ tological examination revealed that considerable cell infiltration began on Day 1 and lasted until Day 7, with a larger area of cell infiltration. Serum levels of IL-5, IL-6, IFN-γ, MCP-1, MIP-2, G-CSF, and TNF-α substantially rose on Day 7. Conclusions This modified approach for BLM-induced lung injury provided a severe, stable, and one-sided (left-lobe) ARDS animal model with consistent reproducibility. The physiological symptoms observed in this severe ARDS animal model are entirely consistent with the characteristics of clinical ARDS. The establishment of this ARDS animal model could help develop treatment for ARDS.

ObjectivePrimary liver cancer, predominantly hepatocellular carcinoma (HCC), is a significant global health issue, ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality. Accurate and early diagnosis of HCC is crucial for effective treatment, as HCC and non-HCC malignancies like intrahepatic cholangiocarcinoma (ICC) exhibit different prognoses and treatment responses. Traditional diagnostic methods, including liver biopsy and contrast-enhanced ultrasound (CEUS), face limitations in applicability and objectivity. The primary objective of this study was to develop an advanced, light-weighted classification network capable of distinguishing HCC from other non-HCC malignancies by leveraging the automatic analysis of brightness changes in CEUS images. The ultimate goal was to create a user-friendly and cost-efficient computer-aided diagnostic tool that could assist radiologists in making more accurate and efficient clinical decisions. MethodsThis retrospective study encompassed a total of 161 patients, comprising 131 diagnosed with HCC and 30 with non-HCC malignancies. To achieve accurate tumor detection, the YOLOX network was employed to identify the region of interest (ROI) on both B-mode ultrasound and CEUS images. A custom-developed algorithm was then utilized to extract brightness change curves from the tumor and adjacent liver parenchyma regions within the CEUS images. These curves provided critical data for the subsequent analysis and classification process. To analyze the extracted brightness change curves and classify the malignancies, we developed and compared several models. These included one-dimensional convolutional neural networks (1D-ResNet, 1D-ConvNeXt, and 1D-CNN), as well as traditional machine-learning methods such as support vector machine (SVM), ensemble learning (EL), k-nearest neighbor (KNN), and decision tree (DT). The diagnostic performance of each method in distinguishing HCC from non-HCC malignancies was rigorously evaluated using four key metrics: area under the receiver operating characteristic (AUC), accuracy (ACC), sensitivity (SE), and specificity (SP). ResultsThe evaluation of the machine-learning methods revealed AUC values of 0.70 for SVM, 0.56 for ensemble learning, 0.63 for KNN, and 0.72 for the decision tree. These results indicated moderate to fair performance in classifying the malignancies based on the brightness change curves. In contrast, the deep learning models demonstrated significantly higher AUCs, with 1D-ResNet achieving an AUC of 0.72, 1D-ConvNeXt reaching 0.82, and 1D-CNN obtaining the highest AUC of 0.84. Moreover, under the five-fold cross-validation scheme, the 1D-CNN model outperformed other models in both accuracy and specificity. Specifically, it achieved accuracy improvements of 3.8% to 10.0% and specificity enhancements of 6.6% to 43.3% over competing approaches. The superior performance of the 1D-CNN model highlighted its potential as a powerful tool for accurate classification. ConclusionThe 1D-CNN model proved to be the most effective in differentiating HCC from non-HCC malignancies, surpassing both traditional machine-learning methods and other deep learning models. This study successfully developed a user-friendly and cost-efficient computer-aided diagnostic solution that would significantly enhances radiologists’ diagnostic capabilities. By improving the accuracy and efficiency of clinical decision-making, this tool has the potential to positively impact patient care and outcomes. Future work may focus on further refining the model and exploring its integration with multimodal ultrasound data to maximize its accuracy and applicability.

Background: Despite the fact that an increasing number of studies have focused on developing therapies for acute lung injury, managing acute respiratory distress syndrome (ARDS) remains a challenge in intensive care medicine.Whether the pathology of animal models with acute lung injury in prior studies differed from clinical symptoms of ARDS, resulting in questionable management for human ARDS. To evaluate precisely the therapeutic effect of trans‑ planted stem cells or medications on acute lung injury, we developed an animal model of severe ARDS with lower lung function, capable of keeping the experimental animals survive with consistent reproducibility. Establishing this animal model could help develop the treatment of ARDS with higher efficiency. Results: In this approach, we intratracheally delivered bleomycin (BLM, 5 mg/rat) into rats’ left trachea via a needle connected with polyethylene tube, and simultaneously rotated the rats to the left side by 60 degrees. Within sevendays after the injury, we found that arterial blood oxygen saturation ­(SpO2 ) significantly decreased to 83.7%, partial pressure of arterial oxygen ­(PaO2 ) markedly reduced to 65.3 mmHg, partial pressure of arterial carbon dioxide ­(PaCO2 )amplified to 49.2 mmHg, and the respiratory rate increased over time. Morphologically, the surface of the left lung appeared uneven on Day 1, the alveoli of the left lung disappeared on Day 2, and the left lung shrank on Day 7. A his‑ tological examination revealed that considerable cell infiltration began on Day 1 and lasted until Day 7, with a larger area of cell infiltration. Serum levels of IL-5, IL-6, IFN-γ, MCP-1, MIP-2, G-CSF, and TNF-α substantially rose on Day 7. Conclusions This modified approach for BLM-induced lung injury provided a severe, stable, and one-sided (left-lobe) ARDS animal model with consistent reproducibility. The physiological symptoms observed in this severe ARDS animal model are entirely consistent with the characteristics of clinical ARDS. The establishment of this ARDS animal model could help develop treatment for ARDS.

Background: Despite the fact that an increasing number of studies have focused on developing therapies for acute lung injury, managing acute respiratory distress syndrome (ARDS) remains a challenge in intensive care medicine.Whether the pathology of animal models with acute lung injury in prior studies differed from clinical symptoms of ARDS, resulting in questionable management for human ARDS. To evaluate precisely the therapeutic effect of trans‑ planted stem cells or medications on acute lung injury, we developed an animal model of severe ARDS with lower lung function, capable of keeping the experimental animals survive with consistent reproducibility. Establishing this animal model could help develop the treatment of ARDS with higher efficiency. Results: In this approach, we intratracheally delivered bleomycin (BLM, 5 mg/rat) into rats’ left trachea via a needle connected with polyethylene tube, and simultaneously rotated the rats to the left side by 60 degrees. Within sevendays after the injury, we found that arterial blood oxygen saturation ­(SpO2 ) significantly decreased to 83.7%, partial pressure of arterial oxygen ­(PaO2 ) markedly reduced to 65.3 mmHg, partial pressure of arterial carbon dioxide ­(PaCO2 )amplified to 49.2 mmHg, and the respiratory rate increased over time. Morphologically, the surface of the left lung appeared uneven on Day 1, the alveoli of the left lung disappeared on Day 2, and the left lung shrank on Day 7. A his‑ tological examination revealed that considerable cell infiltration began on Day 1 and lasted until Day 7, with a larger area of cell infiltration. Serum levels of IL-5, IL-6, IFN-γ, MCP-1, MIP-2, G-CSF, and TNF-α substantially rose on Day 7. Conclusions This modified approach for BLM-induced lung injury provided a severe, stable, and one-sided (left-lobe) ARDS animal model with consistent reproducibility. The physiological symptoms observed in this severe ARDS animal model are entirely consistent with the characteristics of clinical ARDS. The establishment of this ARDS animal model could help develop treatment for ARDS.

Background: Despite the fact that an increasing number of studies have focused on developing therapies for acute lung injury, managing acute respiratory distress syndrome (ARDS) remains a challenge in intensive care medicine.Whether the pathology of animal models with acute lung injury in prior studies differed from clinical symptoms of ARDS, resulting in questionable management for human ARDS. To evaluate precisely the therapeutic effect of trans‑ planted stem cells or medications on acute lung injury, we developed an animal model of severe ARDS with lower lung function, capable of keeping the experimental animals survive with consistent reproducibility. Establishing this animal model could help develop the treatment of ARDS with higher efficiency. Results: In this approach, we intratracheally delivered bleomycin (BLM, 5 mg/rat) into rats’ left trachea via a needle connected with polyethylene tube, and simultaneously rotated the rats to the left side by 60 degrees. Within sevendays after the injury, we found that arterial blood oxygen saturation ­(SpO2 ) significantly decreased to 83.7%, partial pressure of arterial oxygen ­(PaO2 ) markedly reduced to 65.3 mmHg, partial pressure of arterial carbon dioxide ­(PaCO2 )amplified to 49.2 mmHg, and the respiratory rate increased over time. Morphologically, the surface of the left lung appeared uneven on Day 1, the alveoli of the left lung disappeared on Day 2, and the left lung shrank on Day 7. A his‑ tological examination revealed that considerable cell infiltration began on Day 1 and lasted until Day 7, with a larger area of cell infiltration. Serum levels of IL-5, IL-6, IFN-γ, MCP-1, MIP-2, G-CSF, and TNF-α substantially rose on Day 7. Conclusions This modified approach for BLM-induced lung injury provided a severe, stable, and one-sided (left-lobe) ARDS animal model with consistent reproducibility. The physiological symptoms observed in this severe ARDS animal model are entirely consistent with the characteristics of clinical ARDS. The establishment of this ARDS animal model could help develop treatment for ARDS.

Background: Despite the fact that an increasing number of studies have focused on developing therapies for acute lung injury, managing acute respiratory distress syndrome (ARDS) remains a challenge in intensive care medicine.Whether the pathology of animal models with acute lung injury in prior studies differed from clinical symptoms of ARDS, resulting in questionable management for human ARDS. To evaluate precisely the therapeutic effect of trans‑ planted stem cells or medications on acute lung injury, we developed an animal model of severe ARDS with lower lung function, capable of keeping the experimental animals survive with consistent reproducibility. Establishing this animal model could help develop the treatment of ARDS with higher efficiency. Results: In this approach, we intratracheally delivered bleomycin (BLM, 5 mg/rat) into rats’ left trachea via a needle connected with polyethylene tube, and simultaneously rotated the rats to the left side by 60 degrees. Within sevendays after the injury, we found that arterial blood oxygen saturation ­(SpO2 ) significantly decreased to 83.7%, partial pressure of arterial oxygen ­(PaO2 ) markedly reduced to 65.3 mmHg, partial pressure of arterial carbon dioxide ­(PaCO2 )amplified to 49.2 mmHg, and the respiratory rate increased over time. Morphologically, the surface of the left lung appeared uneven on Day 1, the alveoli of the left lung disappeared on Day 2, and the left lung shrank on Day 7. A his‑ tological examination revealed that considerable cell infiltration began on Day 1 and lasted until Day 7, with a larger area of cell infiltration. Serum levels of IL-5, IL-6, IFN-γ, MCP-1, MIP-2, G-CSF, and TNF-α substantially rose on Day 7. Conclusions This modified approach for BLM-induced lung injury provided a severe, stable, and one-sided (left-lobe) ARDS animal model with consistent reproducibility. The physiological symptoms observed in this severe ARDS animal model are entirely consistent with the characteristics of clinical ARDS. The establishment of this ARDS animal model could help develop treatment for ARDS.