Oral squamous cell carcinoma (OSCC) is a common head and neck malignancy. Approximately 50% to 60% of patients with OSCC are diagnosed at a locally advanced stage (clinical staging III-IVa). Even with comprehensive and sequential treatment primarily based on surgery, the 5-year overall survival rate remains below 50%, and patients often suffer from postoperative functional impairments such as difficulties with speaking and swallowing. Programmed death receptor-1 (PD-1) inhibitors are increasingly used in the neoadjuvant treatment of locally advanced OSCC and have shown encouraging efficacy. However, clinical practice still faces key challenges, including the definition of indications, optimization of combination regimens, and standards for efficacy evaluation. Based on the latest research advances worldwide and the clinical experience of the expert group, this expert consensus systematically evaluates the application of PD-1 inhibitors in the neoadjuvant treatment of locally advanced OSCC, covering combination strategies, treatment cycles and surgical timing, efficacy assessment, use of biomarkers, management of special populations and immune related adverse events, principles for immunotherapy rechallenge, and function preservation strategies. After multiple rounds of panel discussion and through anonymous voting using the Delphi method, the following consensus statements have been formulated: 1) Neoadjuvant therapy with PD-1 inhibitors can be used preoperatively in patients with locally advanced OSCC. The preferred regimen is a PD-1 inhibitor combined with platinum based chemotherapy, administered for 2-3 cycles. 2) During the efficacy evaluation of neoadjuvant therapy, radiographic assessment should follow the dual criteria of Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 and immune RECIST (iRECIST). After surgery, systematic pathological evaluation of both the primary lesion and regional lymph nodes is required. For combination chemotherapy regimens, PD-L1 expression and combined positive score need not be used as mandatory inclusion or exclusion criteria. 3) For special populations such as the elderly (≥ 70 years), individuals with stable HIV viral load, and carriers of chronic HBV/HCV, PD-1 inhibitors may be used cautiously under the guidance of a multidisciplinary team (MDT), with close monitoring for adverse events. 4) For patients with a poor response to neoadjuvant therapy, continuation of the original treatment regimen is not recommended; the subsequent treatment plan should be adjusted promptly after MDT assessment. Organ transplant recipients and patients with active autoimmune diseases are not recommended to receive neoadjuvant PD-1 inhibitor therapy due to the high risk of immune related activation. Rechallenge is generally not advised for patients who have experienced high risk immune related adverse events such as immune mediated myocarditis, neurotoxicity, or pneumonitis. 5) For patients with a good pathological response, individualized de escalation surgery and function preservation strategies can be explored. This consensus aims to promote the standardized, safe, and precise application of neoadjuvant PD-1 inhibitor strategies in the management of locally advanced OSCC patients.

IgA nephropathy (IgAN) is the most common primary glomerulonephritis worldwide and a major cause of chronic kidney disease and kidney failure. IgAN exhibits marked heterogeneity in clinical presentation, histopathology, and pathogenic mechanisms, contributing to variable treatment responses and prognosisamong patients. Precise risk assessment and individualized intervention are therefore of critical importance. This review systematically traces the evolution of IgAN management from traditional risk stratification toward biomarker-driven precision medicine. We first review the clinical utility and limitations of established risk stratification tools, including the KDIGO guidelines, the Oxford MEST-C classification, and the International IgAN Prediction Tool. We then discuss emerging biomarkers closely linked to disease pathogenesis, including galactose-deficient IgA1 (Gd-IgA1), anti-Gd-IgA1 autoantibodies, B cell activating factor (BAFF), a proliferation-inducing ligand (APRIL), and complement components, as well as the targeted therapies they have informed. In addition, urinary biomarkers and multi-omics approaches show promise for dynamic disease monitoring and individualized risk stratification.

Elderly patients with primary membranous nephropathy (PMN) exhibit significant prognostic heterogeneity and poor tolerance to immunotherapy. However, there is a lack of early prognostic prediction tools specifically for this population. This study aimed to develop a prognostic prediction model applicable to elderly PMN patients.

Infection-related glomerulonephritis (IRGN) is an immune-mediated glomerular injury triggered by infectious agents. This article reports a case of immune complex-mediated glomerulonephritis following acute hepatitis B virus infection, which continued to progress despite standard antiviral and immunosuppressive therapy. Given the significant elevation of soluble complement membrane attack complex (sC5b-9), an indicator of terminal complement pathway activation, the patient was treated with eculizumab. Following treatment, the patient's urine protein-to-creatinine ratio significantly decreased, hypoalbuminemia and hematuria markedly improved, and sC5b-9 levels declined. This case suggests that abnormal complement system activation may be a key mechanism driving disease persistence in some patients with IRGN. For those unresponsive to conventional therapy, complement function screening and targeted terminal complement pathway inhibition may represent an effective salvage strategy.

Immune checkpoint inhibitors (ICIs) are widely used in the treatment of malignant tumors, and their related immune-related adverse events (irAEs) have attracted increasing attention. This study reports the diagnosis and treatment process of a case of immune cystitis in a patient with hepatobiliary tract malignant tumor after treatment with pembrolizumab. The patient was admitted to the hospital due to frequent urination, urgency of urination and dysuria for 1 month. Previous repeated anti-infection treatments were ineffective. Combined with medical history, laboratory tests, imaging findings, cystoscopy and pathological results, the patient was clinically diagnosed with ICIs-associated immune cystitis (Pembrolizumab) ultimately. The patient's symptoms significantly improved after treatment with glucocorticoids. This case reindicates that clinicians need to improve awareness of ICI-related urinary system irAEs. Early identification and timely intervention can significantly improve patient prognosis.

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 To establish a rat model of acute antibody-mediated rejection (AMR) in kidney transplantation and investigate the preventive effect of dihydroartemisinin (DHA) on acute AMR. Methods BN rats were used as donors and Lewis rats as recipients. Kidney transplantation was performed 2 weeks after skin transplantation for sensitization. After establishing the acute AMR model in rat kidney transplantation, the recipients of experimental groups included the syngeneic kidney transplantation group (6 rats), the allogeneic kidney transplantation group (6 rats), the syngeneic skin transplantation followed by kidney transplantation group (12 rats), and the allogeneic skin transplantation followed by kidney transplantation group (24 rats). The groups for investigating the preventive effect of DHA on acute AMR included the control group (allogeneic skin transplantation followed by kidney transplantation) and the DHA group (allogeneic skin transplantation followed by kidney transplantation + DHA), with 12 rats in each group. The survival time of recipient rats, serum donor-specific antibody (DSA) levels and graft pathological changes were used to identify the acute AMR model. On this basis, DSA levels, pathological changes in the transplant kidneys and peripheral blood B-cell levels were detected to assess the preventive effect of DHA on acute AMR. Results Compared with the allogeneic kidney transplantation group, skin transplantation sensitization significantly shortened the survival time of recipient rats (P<0.01). Compared with the syngeneic skin transplantation followed by kidney transplantation group, the allogeneic skin transplantation followed by kidney transplantation group showed significantly elevated serum DSA-IgG levels from 7 days after skin transplantation to 5 days after kidney transplantation (P<0.01), and significantly elevated DSA-IgM levels at 7 and 14 days after skin transplantation(all P<0.01). The transplant kidneys in the allogeneic skin transplantation followed by kidney transplantation group showed a small number of inflammatory cell infiltrations, tubular necrosis, capillaritis, and C4d deposition starting from 1 day after kidney transplantation, with these pathological changes worsening as the post-transplantation days increased. The kidney damage became significant starting from 3 days after transplantation. The above pathology manifestations were consistent with the characteristics of acute AMR. On the basis of establishing the acute AMR model, DHA treatment significantly prolonged the survival time of recipient rats (P<0.01) , and reduced serum DSA-IgG and DSA-IgM levels. DHA treatment significantly alleviated the pathological manifestations of acute AMR, including kidney damage, inflammatory cell infiltration, capillaritis and tubular necrosis, and also reduced C4d deposition in the transplant kidneys, inflammatory cell infiltration and peripheral blood CD19⁺ B-cell levels. Conclusions An acute AMR model is established by performing kidney transplantation 2 weeks after allogeneic skin transplantation in rats. It is discovered that DHA has immunosuppressive effects and may effectively prevent acute AMR, which provides a new strategy for the management of clinical AMR.

Objective To investigate the effects and mechanisms of Huatan Quyu Decoction on learning and memory abilities in rats with vascular dementia(VD).Methods Totally 112 male SD rats were randomly selected with 16 rats as the sham-operation group,the remaining rats were used to prepare VD models by segmental ligation of the common carotid artery.The successfully modeled rats were randomly divided into model group,Huatan Quyu Decoction low-,medium-and high-dosage groups(6.1,12.1,24.2 g/kg),donepezil hydrochloride group(0.5 mg/kg)and combination group(Huatan Quyu Decoction 12.1 g/kg+donepezil hydrochloride 0.5 mg/kg),with 16 rats in each group.Each group was given the corresponding treatment measures for 4 weeks.The Morris water maze test was used to assess learning and memory abilities,neurological function was evaluated using Garcia score,HE staining was used to observe the morphology of the hippocampal tissue,ELISA was employed to detect the serum content of Aβ,immunohistochemistry was utilized to observe the β-catenin,LRP6 and GSK-3β protein expression in brain tissue.Results Compared with the sham-operation group,the escape latency of the model group rats was prolonged(P<0.01),the number of crossing platforms was reduced(P<0.01),and the neurological deficit score was decreased(P<0.01),the arrangement of hippocampal tissue cells was disorderly,and the tissue was severely damaged,the serum Aβ content increased(P<0.01),the expressions of β-catenin and LRP6 protein in brain tissue decreased,and the expression of GSK-3β protein increased(P<0.01).Compared with the model group,the escape latency of rats in each administration group was shortened,the number of crossing platforms increased,the neurological deficit score increased,the number of hippocampal cells was relatively more,the arrangement was more orderly,and the structure was relatively complete,the serum Aβ content decreased,the expressions of β-catenin and LRP6 proteins increased,and the expression of GSK-3β protein decreased.Among them,Huatan Quyu Decoction high-dosage group had a significantly better effect than Huatan Quyu Decoction low-and medium-dosage groups(P<0.01),and there was no statistical significance in various indicators compared with the donepezil hydrochloride group(P>0.05).Compared with the donepezil hydrochloride group,the combination group showed significant improvements in learning and memory abilities(P<0.01),the neurological deficit score significantly increased(P<0.01),the number of hippocampal cells significantly increased,arranged neatly,and structurally intact,the serum Aβ content significantly decreased(P<0.01),the expression of β-catenin and LRP6 proteins significantly increased,and the expression of GSK-3β protein significantly decreased(P<0.01).Conclusion Huatan Quyu Decoction can repair cognitive function in VD rats,improve learning and memory abilities,and alleviate VD symptoms by activating the Wnt/β-catenin signaling pathway to reduce serum Aβ content,decrease the apoptosis of nerve cells and alleviate the degree of pathological damage in hippocampal tissue.