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.

Pulmonary fibrosis（PF） is a progressive and life-threatening disease with limited therapeutic options， highlighting the urgent need for innovative drug discovery strategies. To address this challenge， the authors propose the formula-originated rational intelligent screening&translation（FIRST）， a systematic framework for developing anti-fibrotic monomers derived from classical traditional Chinese medicine（TCM）. The strategy integrates three key dimensions， including tissue-oriented intelligent screening of active compounds， structural optimization based on drug-target spatial interactions and plant biosynthetic pathways， and cross-scale validation of drug. We further highlight its applications in discovering tissue-oriented novel drugs from clinically validated TCM， the development and mechanistic elucidation of anti-fibrotic therapeutics， as well as the clinical translation and secondary development of candidate drugs. This strategy paves the way for first-in-class， formula-derived monomeric drugs with defined structures， clarified mechanisms， and proven safety， offering a transformative avenue to meet the urgent therapeutic needs of PF and setting a new paradigm for TCM-based drug innovation.

Pulmonary fibrosis（PF） is a progressive and life-threatening disease with limited therapeutic options， highlighting the urgent need for innovative drug discovery strategies. To address this challenge， the authors propose the formula-originated rational intelligent screening&translation（FIRST）， a systematic framework for developing anti-fibrotic monomers derived from classical traditional Chinese medicine（TCM）. The strategy integrates three key dimensions， including tissue-oriented intelligent screening of active compounds， structural optimization based on drug-target spatial interactions and plant biosynthetic pathways， and cross-scale validation of drug. We further highlight its applications in discovering tissue-oriented novel drugs from clinically validated TCM， the development and mechanistic elucidation of anti-fibrotic therapeutics， as well as the clinical translation and secondary development of candidate drugs. This strategy paves the way for first-in-class， formula-derived monomeric drugs with defined structures， clarified mechanisms， and proven safety， offering a transformative avenue to meet the urgent therapeutic needs of PF and setting a new paradigm for TCM-based drug innovation.

ObjectiveThe widespread adoption of portable fundus cameras for primary care and community screening is hindered by limitations in current autofocus(AF) technologies. Image-based methods relying on sharpness evaluation require iterative searches, resulting in slow convergence, while projection-based techniques are susceptible to optical artifacts and calibration errors. To address these challenges, this study introduces a novel AF system based on direct wavefront sensing, designed to deliver simultaneous high speed, high precision, and operational robustness within the compact form factor essential for portable ophthalmic devices. MethodsOur approach fundamentally reimagines the AF process by directly measuring the ocular wavefront aberration. We developed a custom portable fundus camera integrating a miniaturized Shack-Hartmann wavefront sensor (SHWS) into the optical path. An 850 nm laser diode projects a point source onto the retina via oblique illumination to minimize corneal reflections. Light scattered from this spot carries the eye’s refractive error through the imaging optics and is directed to the SHWS, positioned at a plane optically conjugate to the primary color CMOS imaging sensor. A microlens array within the SHWS samples the incident wavefront, generating a pattern of focal spots on a CCD. Real-time centroid analysis of these spots provides a map of local wavefront slopes. These measurements are processed through a singular value decomposition (SVD) algorithm to fit a Zernike polynomial basis set, enabling real-time reconstruction of the wavefront phase. The defocus component (S) is extracted from the second-order Zernike coefficients, providing a direct, quantitative measure of the refractive error in diopters. This value serves as a precise error signal in a closed-loop control system, which commands a voice-coil actuated focusing lens to its null position in a single, deterministic step, eliminating the need for iterative search algorithms. ResultsComprehensive evaluation demonstrated the system’s high performance. Testing on a calibrated model eye (OEMI-7) established a highly linear relationship between the computed defocus S and the focusing lens position across a ±20 Diopter (D) compensation range, achievable within a 5 mm mechanical travel. The system achieved a focusing precision of 0.08 D, corresponding to an 18-fold improvement over a conventional projection spot-size method tested under identical conditions. The total focus acquisition time, encompassing wavefront measurement, computation, and lens actuation, averaged under 0.5 s. Clinical validation with 25 human volunteers (50 eyes, refractive range -15 D to +10 D) confirmed practical efficacy. The wavefront-sensing AF succeeded in 92% of attempts with a mean time of 0.5 s, substantially outperforming a projection-based benchmark which achieved only a 32% success rate with an average time of 4.25 s. The system provided instantaneous directional guidance and maintained stability during minor ocular movements. Objective assessment of image quality, via amplitude contrast of retinal vasculature, showed consistent and significant enhancement following AF correction across the entire tested diopter range. ConclusionThis work successfully implements and validates a direct wavefront-sensing autofocus paradigm for portable fundus cameras. By directly quantifying and compensating for the optical defocus aberration, this method bypasses the fundamental limitations of image-processing and projection-based techniques, enabling rapid, precise, and deterministic diopter compensation. The developed system delivers an exceptional combination of a wide operational range (±20 D), high accuracy (0.08 D), fast convergence (0.5 s), and a compact physical footprint. This technology provides a practical and high-performance focusing solution capable of enhancing the reliability, throughput, and diagnostic utility of portable retinal imaging in large-scale screening applications. Future efforts will be directed towards system cost optimization and performance adaptation for diverse ocular conditions.

Objective To investigate the expression characteristics of the transcription factor E2F2 in clear cell renal cell carcinoma (ccRCC), its impact on patient prognosis, and its potential role in the tumor immune microenvironment, with validation using clinical samples and functional assays. Methods RNA sequencing data and clinical information of ccRCC patients were obtained from the TCGA database; GSE53757 and GSE66272 datasets were downloaded from the GEO database as external validation cohorts. The expression difference of E2F2 between ccRCC tissue and normal tissue was compared, and the relationship between E2F2 expression and clinical pathological characteristics was analyzed. Kaplan-Meier (KM) survival analysis with log-rank test was performed to evaluate the effects of E2F2 on overall survival (OS), progression-free survival (PFS), and disease-specific survival (DSS). The prognostic efficacy of E2F2 in predicting 1-, 3- and 5-year survival was evaluated using receiver operating characteristic (ROC) curve. GSEA was performed to identify E2F2-related signaling pathways, and the ESTIMATE and CIBERSORT algorithms were used to assess the relationship between E2F2 expression level and tumor immune cell infiltration and immune microenvironment. Twenty pairs of surgically resected and pathologically confirmed ccRCC tissues and matched adjacent non-tumor tissues were collected from our hospital, and immunohistochemistry (IHC) was performed to detect the protein expression of E2F2. Human ccRCC cell line 786-O was used for functional assays;shRNA was used to knock down E2F2 expression (constructing stable shE2F2#1 and shE2F2#2 cell lines), and qRT-PCR and Western blot were performed to verify knockdown efficiency, followed by MTT, colony formation, and Transwell migration assays to evaluate the effects of E2F2 on the biological behaviors of ccRCC cells. Results E2F2 was significantly upregulated in ccRCC tissues (the same results in the verification set). Higher E2F2 expression was associated with advanced histological grade, clinical stage and higher TNM classification (P＜0.05). KM analysis showed that patients in the E2F2 high-expression group had worse OS, PFS, and DSS (P=0.019, 0.036, ＜0.001); the ROC curves showed area under the curve (AUC) of E2F2 of predicting 1-, 3- and 5- year survival of ccRCC patients were 0.844, 0.851 and 0.815, respectively. GSEA revealed that the E2F2 low-expression group was enriched in multiple metabolism-related pathways, whereas the E2F2 high-expression group was associated with immune-related pathways. Immune analysis demonstrated that high E2F2 expression was associated with increased immune scores, increased proportion of immune cells, higher tumor mutation burden, and potentially stronger immunotherapy response. IHC results showed that the E2F2 immunoreactivity score in ccRCC tissues was significantly higher than that in adjacent non-tumor tissues (P＜0.05). Functional assays indicated that E2F2 knockdown significantly inhibited the proliferation, colony formation, and migration of ccRCC cells. Conclusion E2F2 is highly expressed in ccRCC and may be involved in tumorigenesis and progression through modulation of the immune microenvironment. Its expression level is closely associated with patient prognosis, and E2F2 has the potential to serve as a prognostic biomarker and immunotherapeutic target in ccRCC.

Objective:To explore the independent risk factors for uremic encephalopathy(UE)in maintenance hemodialysis(MHD)patients and provide evidence for early clinical warning and intervention.Methods:A case-control study was conducted,enrolling 67 MHD patients diagnosed with UE(UE group)at Laibin People's Hospital from January 2010 to December 2024,and 67 non-UE patients during the same period(control group).Demographic characteristics,dialysis parameters,laboratory indicators,and infection events were collected.Univariate and multivariate logistic regression analyses were used to identify independent risk factors for UE.Results:The UE group had significantly higher rates of infection(58.2％vs.29.9％),serum creatinine(789 vs.702 μmol/L),and iPTH levels(568 vs.385 pg/mL)compared to the control group(P＜0.05).Multivariate analysis revealed that concurrent infection(OR=3.022,95％CI:1.312-6.958),elevated serum creatinine(OR=1.004,95％CI:1.000-1.008),and elevated iPTH(OR=1.002,95％CI:1.001-1.003)were independent risk factors for UE(P＜0.05).The combined prediction model achieved an AUC of 0.878(95％CI:0.822-0.934),with 82.1％sensitivity and 80.6％specificity.Conclusion:Infection,elevated serum creatinine,and elevated iPTH significantly increase the risk of UE in MHD patients.Clinical management should emphasize infection prevention,toxin clearance optimization,and parathyroid function regulation to reduce UE incidence.

BACKGROUND:Bone microenvironment is also rich in various immune cells and cytokines,which are closely related to bone cells and form an interactive network.Therefore,bone aging is not only caused by the senescence of osteocytes,but also accelerated by age-related changes in the immune system.OBJECTIVE:To review the age-related changes of bone marrow mesenchymal stem cells,osteoblasts,osteoclasts,and immune cells in the bone microenvironment,emphasize the key role of the immune microenvironment in bone aging,and the potential of immunotherapy in the treatment of bone aging.METHODS:We searched PubMed and China National Knowledge Infrastructure for articles on the interaction between bone cell senescence and immune cell senescence using"osteocytes,bone aging,immune microenvironment,immune cells,cytokines,immunosenescence,immunotherapy"as Chinese and English search terms.According to the inclusion and exclusion criteria,128 articles were finally included in the review.RESULTS AND CONCLUSION:Bone aging is a common pathological condition in the elderly,characterized by the interaction of multiple biological processes,among which immune factors play a key role.The cells,molecules,and signaling pathways in the immune microenvironment together constitute a complex network,and the imbalance of this network will accelerate the process of bone aging.The combination of anti-cellular aging and immunotherapy may bring new methods for the treatment of bone aging diseases,including the removal of senescent cells,targeted drugs for senescence-related secretory phenotypes,targeted therapy of inflammatory cytokines,immune cell regulation therapy,stem cell therapy,and molecular therapy.To more effectively and reasonably remove senescent cells,a deeper understanding of the mechanism of senescent cells is needed,which will help to identify senescent cells more accurately.Immunotherapy shows great potential and prospects in the treatment of bone aging,but there are some potential risks.It is believed that with the advancement of science and technology,people can more accurately understand the genetic information and immune status of the human body and develop more personalized immunotherapy plans.

BACKGROUND:Bone microenvironment is also rich in various immune cells and cytokines,which are closely related to bone cells and form an interactive network.Therefore,bone aging is not only caused by the senescence of osteocytes,but also accelerated by age-related changes in the immune system.OBJECTIVE:To review the age-related changes of bone marrow mesenchymal stem cells,osteoblasts,osteoclasts,and immune cells in the bone microenvironment,emphasize the key role of the immune microenvironment in bone aging,and the potential of immunotherapy in the treatment of bone aging.METHODS:We searched PubMed and China National Knowledge Infrastructure for articles on the interaction between bone cell senescence and immune cell senescence using"osteocytes,bone aging,immune microenvironment,immune cells,cytokines,immunosenescence,immunotherapy"as Chinese and English search terms.According to the inclusion and exclusion criteria,128 articles were finally included in the review.RESULTS AND CONCLUSION:Bone aging is a common pathological condition in the elderly,characterized by the interaction of multiple biological processes,among which immune factors play a key role.The cells,molecules,and signaling pathways in the immune microenvironment together constitute a complex network,and the imbalance of this network will accelerate the process of bone aging.The combination of anti-cellular aging and immunotherapy may bring new methods for the treatment of bone aging diseases,including the removal of senescent cells,targeted drugs for senescence-related secretory phenotypes,targeted therapy of inflammatory cytokines,immune cell regulation therapy,stem cell therapy,and molecular therapy.To more effectively and reasonably remove senescent cells,a deeper understanding of the mechanism of senescent cells is needed,which will help to identify senescent cells more accurately.Immunotherapy shows great potential and prospects in the treatment of bone aging,but there are some potential risks.It is believed that with the advancement of science and technology,people can more accurately understand the genetic information and immune status of the human body and develop more personalized immunotherapy plans.

Background and Aims:Mucinous adenocarcinoma of the colorectum(MAC)is a distinct histologic subtype of colorectal cancer characterized by high malignancy and low diagnostic accuracy of preoperative biopsy,posing challenges for clinical decision-making.Given the critical role of the inflammatory microenvironment in tumor progression,this study aimed to develop and validate a nomogram model integrating preoperative systemic inflammatory indicators and clinical features to improve the preoperative diagnosis of MAC.Methods:Clinical data of 293 patients with colorectal cancer who underwent radical resection between June 2017 and June 2022 at the First Affiliated Hospital of the University of South China were retrospectively analyzed.Based on postoperative pathology,patients were classified into the mucinous adenocarcinoma(MAC)group and the non-specific adenocarcinoma(AC)group.Propensity score matching(PSM,1∶1)was used to balance age,T stage,and N stage.Differences in preoperative inflammatory indices were compared between groups.Univariate and multivariate logistic regression analyses were performed to identify independent predictors of MAC,which were incorporated into a diagnostic nomogram.The model's discrimination,calibration,and clinical utility were evaluated using the area under the receiver operating characteristic curve(AUC),calibration plots,and decision curve analysis(DCA).Results:Among the 293 patients,46 had MAC and 247 had AC,with a preoperative colonoscopic diagnostic rate of 54%for MAC.After PSM(43 pairs),platelet count,platelet lymphocyte ratio(PLR),systemic immune inflammation index(SII),inflammation related prognostic index(IPI),and systemic inflammation score(SIS)were significantly higher in the MAC group,while lymphocyte monocyte ratio(LMR)was lower(all P<0.05).Multivariate analysis identified tumor location,maximum tumor diameter,and preoperative IPI as independent predictors.The AUCs of the nomogram in the training(n=206)and validation(n=87)cohorts were 0.759(95%CI=0.662-0.856)and 0.776(95%CI=0.649-0.903),respectively.Calibration plots showed good agreement between predicted and observed probabilities,and DCA demonstrated satisfactory clinical applicability.Conclusion:A nomogram model integrating tumor location,tumor size,and preoperative IPI was successfully developed and validated for preoperative diagnosis of colorectal MAC.This model provides a practical,quantitative tool with good predictive performance to assist clinicians in individualized treatment planning,particularly for patients ineligible for surgical biopsy.