Machado-Joseph disease, or spinocerebellar ataxia type 3 (SCA3), represents the most common autosomal dominant cerebellar ataxia worldwide. Despite its progressive and debilitating nature, disease-modifying therapies remain elusive. Repetitive transcranial magnetic stimulation (rTMS) has emerged as a promising non-invasive intervention; however, its clinical application has been hindered by inconsistent protocols and a lack of mechanistic understanding. A recent landmark study published in Brain Stimulation by Chen et al. addressed these challenges by combining a high-dose intermittent theta-burst stimulation (iTBS) protocol with concurrent transcranial magnetic stimulation-electroencephalography (TMS-EEG). This commentary provides an in-depth analysis of their findings, highlighting the restoration of cerebello-cortical inhibition (CBI) as a key therapeutic mechanism. Furthermore, we discuss the broader implications of this work, proposing that future translational research should integrate accelerated iTBS (aiTBS) paradigms, cortical response measurements (CRM), and individualized neuro-navigation to establish a new era of precision neuromodulation for ataxia.

Machado-Joseph disease, or spinocerebellar ataxia type 3 (SCA3), represents the most common autosomal dominant cerebellar ataxia worldwide. Despite its progressive and debilitating nature, disease-modifying therapies remain elusive. Repetitive transcranial magnetic stimulation (rTMS) has emerged as a promising non-invasive intervention; however, its clinical application has been hindered by inconsistent protocols and a lack of mechanistic understanding. A recent landmark study published in Brain Stimulation by Chen et al. addressed these challenges by combining a high-dose intermittent theta-burst stimulation (iTBS) protocol with concurrent transcranial magnetic stimulation-electroencephalography (TMS-EEG). This commentary provides an in-depth analysis of their findings, highlighting the restoration of cerebello-cortical inhibition (CBI) as a key therapeutic mechanism. Furthermore, we discuss the broader implications of this work, proposing that future translational research should integrate accelerated iTBS (aiTBS) paradigms, cortical response measurements (CRM), and individualized neuro-navigation to establish a new era of precision neuromodulation for ataxia.

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.

With the rapid development of generative artificial intelligence(GAI)technologies,their widespread application in academic research and writing is continuously expanding the boundaries of sci-entific inquiry.However,this trend has also raised a series of ethical and regulatory challenges,inclu-ding issues related to authorship,content authenticity,citation accuracy,and accountability.In light of the growing involvement of AI in generating academic content,establishing an open,controllable,and trustworthy ethical governance framework has become a key task for safeguarding research integrity and maintaining trust within the academic community.This expert consensus outlines ethical requirements across key stages of AI-assisted academic writing-including topic selection,data management,citation practices,and authorship attribution.It aims to clarify the boundaries and ethical obligations surrounding AI use in academic writing,ensuring that technological tools enhance efficiency without compromising in-tegrity.The goal is to provide guidance and institutional support for building a responsible and sustainable research ecosystem.

Bismuth iodide(BiOI)with different crystal plane ratios of(110)to(001)was synthesized,and typeⅡheterojunction formed between(001)and(110)crystal planes of BiOI was used to improve the separation efficiency of photogenerated electrons and holes.Then the BiOI(001)/(110)was composited with nitrogen-doped graphene quantum dots(N-GQDs)to prepare a ternary composites,which could enhance the range and intensity of light absorption,and prolonged the lifetime of photogenerated electrons due to the formation of Z-scheme heterojunctions between BiOI and N-GQDs,thereby leading to the excellent photoelectric performance of the BiOI/N-GQDs for generating sensitive photoelectric response signals.A photoelectrochemical sensor for sensitive detection of chlorpyrifos(CPF)was designed with BiOI/N-GQDs-modified FTO electrode as a photocathode.The S and N atoms contained in CPF were coordinated with Bi(Ⅲ)on the surface of BiOI,which reduced the photocurrent of BiOI/N-GQDs.The photocurrent change was linear with logarithm of concentration of CPF in the range of 1.5×10-12-5.0×10-9 mol/L,and the detection limit was 1.5×10-12 mol/L.The sensor was highly sensitive,selective and stable,and could be used for determination of trace CPF in environmental and food samples.

Objective:To evaluate whether the mechanism by which mesenchymal stem cell-derived exosomes (MSC-exo) mitigated endotoxin-induced lung injury was related to the heme oxygenase-1 (HO-1)/mitochondrial signaling pathway in alveolar macrophages of mice.Methods:In vivo experiment Eighteen C57BL/6 wild-type (WT) mice were divided into 3 groups ( n=6 each) using a random number table method: control group (C group), lipopolysaccharide (LPS) group (L group) and LPS + MSC-exo group (LM group). Six HO-1 conditional knockout mice (HO-1 -/-) were selected and served as HO-1 -/- + MSC-exo + LPS group (HML group). The model of endotoxin-induced lung injury was prepared by injection of LPS 15 mg/kg. MSC-exo (2×10 11 particles) was intravenously injected at 1 h before injection of LPS in LM group. MSC-exo (2×10 11 particles) was intravenously injected and 1 h later LPS was injected in HML group. The expression of HO-1 in macrophages was detected using immunofluorescence, lung injury was assessed following hematoxylin-eosin staining, the wet/dry weight ratio (W/D ratio) was determined, and the mitochondrial morphology was observed with a transmission electron microscope. Cell experiment Alveolar macrophages (MH-S) were divided into 4 groups ( n=20 each) using a random number table method: control group (C group), LPS+ phosphate buffer solution group (LP group), LPS+ MSC-exo group (LM group), and LPS+ MSC-exo+ HO-1 small-interfering RNA group (LMS group). Cells were incubated for 12 h with LPS 10 μg/ml in LP, LM and LMS groups. In addition, LM group was incubated with MSC-exo 100 μg/ml, LP group was incubated with the equal volume of phosphate buffer solution, and the alveolar macrophages were transfected with HO-1 small interfering RNA and incubated with MSC-exo 100 μg/ml in LMS group at the same time. The concentrations of interleukin-1beta (IL-1β) and tumor necrosis factor-alpha (TNF-α) in supernatant were measured by enzyme-linked immunosorbent assay, HO-1 expression was detected by Western blot, the mitochondrial membrane potential was measured using JC-1 staining, and the expression of reactive oxygen species (ROS) was detected by fluorescence. Results:In vivo experiment Compared to C group, the lung injury score and W/D ratio were significantly increased ( P<0.05), the fluorescence signal of HO-1 in macrophages was enhanced, and the damage to mitochondria was aggravated in L group. Compared to L group, the lung injury score and W/D ratio were significantly decreased ( P<0.05), the fluorescence signal of HO-1 in macrophages was enhanced, and the damage to mitochondria was reduced in LM group. Compared to LM group, the lung injury score and W/D ratio were significantly increased ( P<0.05), macrophages had no HO-1 fluorescence signal, and the damage to mitochondria was aggravated in HML group. Cell experiment Compared to C group, the concentrations of IL-1β and TNF-α in supernatant were significantly increased, the expression of HO-1 was up-regulated ( P<0.05), and the mitochondria predominantly exhibited green JC-1 fluorescence, accompanied by an enhanced ROS fluorescence signal in LP group. Compared to LP group, the concentrations of IL-1β and TNF-α in supernatant were significantly decreased, the expression of HO-1 was up-regulated ( P<0.05), and the mitochondria predominantly exhibited red JC-1 fluorescence, accompanied by a weakened ROS fluorescence signal in LM group. Compared to LM group, the concentrations of IL-1β and TNF-α in supernatant were significantly increased, the expression of HO-1 was down-regulated ( P<0.05), and the mitochondria predominantly exhibited green JC-1 fluorescence, accompanied by an enhanced ROS fluorescence signal in LMS group. Conclusions:The mechanism by which MSC-exo attenuates endotoxin-induced lung injury may be related to up-regulation of HO-1 expression in alveolar macrophages and reduction of mitochondrial damage in mice.

Objective To observe the value of preoperative magnetization transfer imaging(MTI)for predicting postoperative pancreatic fistula(POPF)after distal pancreatectomy(DP).Methods A total of 65 patients with pancreatic tumor who underwent DP and preoperative MR scanning were retrospectively enrolled and divided into clinically relevant POPF(CR-POPF)group(n=14,with grade B or C fistula),biochemical fistula group(n=31,postoperative drain fluid amylase level exceeding 3 times the upper limit of normal)and non-fistula group(n=20,postoperative drain fluid amylase level not exceeding 3 times the upper limit of normal)based on postoperative records.Clinical data and magnetization transfer ratio(MTR)of pancreatic tissue at the surgical margin were compared among 3 groups.The predictive value of MTR for CR-POPF was evaluated according to the area under the curve(AUC)of receiver operating characteristic(ROC)curve.Results Patients' age,intraoperative blood loss and the proportion of pancreatic ductal adenocarcinoma in both CR-POPF group and biochemical fistula group were lower than those in non-fistula group(all adjusted P＜0.05),while no significant difference was found between the former two groups(all adjusted P＞0.05).MTR of pancreatic tissue at the surgical margin in CR-POPF group was lower than that in both biochemical fistula group and non-fistula group(both P＜0.05),whereas no statistical difference was detected between the latter two groups(P＞0.05).The AUC of MTR for predicting CR-POPF after DP was 0.727.Conclusion Preoperative MTI could be used to predict POPF after DP.

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.