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.

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.

Objective: This study aimed to explore the correlation between balance function and core muscle activation in patients with adolescent idiopathic scoliosis (AIS), compared to healthy individuals. Methods: A total of 24 AIS patients and 25 healthy controls were recruited. The limits of stability (LOS) test were conducted to assess balance function, while surface electromyography was used to measure the activity of core muscles, including the internal oblique, external oblique, and multifidus. Diaphragm thickness was measured using ultrasound during different postural tasks. Center of pressure (COP) displacement and trunk inclination distance were also recorded during the LOS test. Results: AIS patients showed significantly greater activation of superficial core muscles, such as the internal and external oblique muscles, compared to the control group (p < 0.05). Diaphragm activation was lower in AIS patients during balance tasks (p < 0.01). Although no significant difference was observed in COP displacement between the groups, trunk inclination was significantly greater in the AIS group during certain tasks (p < 0.05). Conclusion These findings suggest distinct postural control patterns in AIS patients, highlighting the importance of targeted interventions to improve balance and core muscle function in this population.

Objective: This study aimed to explore the correlation between balance function and core muscle activation in patients with adolescent idiopathic scoliosis (AIS), compared to healthy individuals. Methods: A total of 24 AIS patients and 25 healthy controls were recruited. The limits of stability (LOS) test were conducted to assess balance function, while surface electromyography was used to measure the activity of core muscles, including the internal oblique, external oblique, and multifidus. Diaphragm thickness was measured using ultrasound during different postural tasks. Center of pressure (COP) displacement and trunk inclination distance were also recorded during the LOS test. Results: AIS patients showed significantly greater activation of superficial core muscles, such as the internal and external oblique muscles, compared to the control group (p < 0.05). Diaphragm activation was lower in AIS patients during balance tasks (p < 0.01). Although no significant difference was observed in COP displacement between the groups, trunk inclination was significantly greater in the AIS group during certain tasks (p < 0.05). Conclusion These findings suggest distinct postural control patterns in AIS patients, highlighting the importance of targeted interventions to improve balance and core muscle function in this population.

Metabolites produced as intermediaries or end-products of microbial metabolism provide crucial signals for health and diseases, such as metabolic dysfunction-associated steatotic liver disease (MASLD). These metabolites include products of the bacterial metabolism of dietary substrates, modification of host molecules (such as bile acids [BAs], trimethylamine-N-oxide, and short-chain fatty acids), or products directly derived from bacteria. Recent studies have provided new insights into the association between MASLD and the risk of developing chronic kidney disease (CKD). Furthermore, alterations in microbiota composition and metabolite profiles, notably altered BAs, have been described in studies investigating the association between MASLD and the risk of CKD. This narrative review discusses alterations of specific classes of metabolites, BAs, fructose, vitamin D, and microbiota composition that may be implicated in the link between MASLD and CKD.

Twelve compounds were isolated from the rice fermentation extracts of Penicillium expansum GY618 by silica column chromatography, Sephadex gel column chromatography, ODS column chromatography and semi preparative HPLC methods. They were determined as 11-hydroxyl-penicitrinone F (1), penicitrinone F (2), betulin (3), erythrodiol (4), ergosterol (5), ergost-5α,8α-epidioxy-6,22-dien-3β-ol (6), (5α,8α-epidioxy-(22E,24R)-ergosta-6,9(11),22-trien-3β-ol) (7), 5α,8α-epidioxy-(22E,24R)-23-methylergosta-6,22-dien-3β-ol (8), 5α,8α-epidioxy- 23,24(R)-dimethylcholesta-6,9(11),22-trien-3β-ol (9), dankasterone A (10), (17R)-4-hydroxy-17-methylincisterol (11) and ergosta-4,6,8(14),22-tetraen-3-one (12), through mass spectrometer, nuclear magnetic resonance (NMR) and comparison with the literature. Compound 1 was a new compound and compounds 2-4, 6-12 were isolated from Penicillium expansum fungus for the first time. The tyrosinase inhibitory activity experiment showed that compounds 1, 3 and 12 showed certain inhibitory activity against tyrosinase with IC₅₀ values of (75 ± 9), (69 ± 8) and (64 ± 2) μmol·L^-1, respectively. The IC₅₀ of other compounds were all greater than 100 μmol·L^-1, while IC₅₀ of the positive control kojic acid was (46 ± 4) μmol·L^-1.

Objective: This study aimed to explore the correlation between balance function and core muscle activation in patients with adolescent idiopathic scoliosis (AIS), compared to healthy individuals. Methods: A total of 24 AIS patients and 25 healthy controls were recruited. The limits of stability (LOS) test were conducted to assess balance function, while surface electromyography was used to measure the activity of core muscles, including the internal oblique, external oblique, and multifidus. Diaphragm thickness was measured using ultrasound during different postural tasks. Center of pressure (COP) displacement and trunk inclination distance were also recorded during the LOS test. Results: AIS patients showed significantly greater activation of superficial core muscles, such as the internal and external oblique muscles, compared to the control group (p < 0.05). Diaphragm activation was lower in AIS patients during balance tasks (p < 0.01). Although no significant difference was observed in COP displacement between the groups, trunk inclination was significantly greater in the AIS group during certain tasks (p < 0.05). Conclusion These findings suggest distinct postural control patterns in AIS patients, highlighting the importance of targeted interventions to improve balance and core muscle function in this population.

Metabolites produced as intermediaries or end-products of microbial metabolism provide crucial signals for health and diseases, such as metabolic dysfunction-associated steatotic liver disease (MASLD). These metabolites include products of the bacterial metabolism of dietary substrates, modification of host molecules (such as bile acids [BAs], trimethylamine-N-oxide, and short-chain fatty acids), or products directly derived from bacteria. Recent studies have provided new insights into the association between MASLD and the risk of developing chronic kidney disease (CKD). Furthermore, alterations in microbiota composition and metabolite profiles, notably altered BAs, have been described in studies investigating the association between MASLD and the risk of CKD. This narrative review discusses alterations of specific classes of metabolites, BAs, fructose, vitamin D, and microbiota composition that may be implicated in the link between MASLD and CKD.