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.

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.

BACKGROUND:There have been many studies on biofeedback therapy and three-dimensional gait function analysis for chronic non-specific low back pain at home and abroad,but few studies on the combination of the two have been reported. OBJECTIVE:To study the effect of biofeedback assisted electrical stimulation on the change of walking ability in chronic non-specific low back pain by collecting gait parameter data through three-dimensional gait analysis. METHODS:Sixty patients with chronic non-specific low back pain,34 males and 26 females,aged 32-58 years,were selected and admitted to First Affiliated Hospital of Guangdong Pharmaceutical University from June 2021 to September 2022.They were divided into control group(n=30)and trial group(n=30)according to the principle of random allocation.Both groups of patients received conventional treatment of dynamic interference with the waist,20 minutes/time,once/day,5 times a week,for 20 times.The control group received supine bypass and prone bypass suspension core muscle training on the basis of conventional treatment,5 times a week,for 20 times.The trial group received biofeedback assisted electrical stimulation therapy on the basis of the control group,20 minutes/time,once/day,5 times a week,for 20 times.The low back pain score,the mean value of electromyography and the gait parameters were compared and analyzed before and after treatment between the two groups. RESULTS AND CONCLUSION:(1)After treatment,the numerical rating scale score,Japanese Orthopaedic Association score,and Oswestry disability index of the two groups were significantly improved compared with those before treatment(P<0.05).Numerical rating scale score,Japanese Orthopaedic Association score,and Oswestry disability index of the trial group were better than those of the control group(P<0.05).(2)After treatment,the mean values of surface electromyography of rectus abdominis,gluteus maximus,and erector spinae muscle in the two groups were higher than those before treatment(P<0.05),and the mean values of surface electromyography of rectus abdominis,gluteus maximus,and erector spinae muscle in the trial group were higher than those in the control group(P<0.05).(3)After treatment,the step width,step speed,step frequency,step length ratio between healthy and diseased sides,the relative value of support between healthy and diseased sides,the relative value of swing between diseased and healthy sides,the sagittal motion range of hip joint and knee joint between healthy and diseased sides and the foot angle between healthy and diseased sides were all better than those before treatment in both groups(P<0.05).The above indexes of the trial group were better than those of the control group after treatment(P<0.05).(4)These results suggest that biofeedback assisted electrical stimulation can significantly alleviate chronic non-specific low back pain,and improve the lower limb walking function.

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 delineate the current research landscape,emerging hotspots,and frontiers re-garding the relationship between the oral microbiome and digestive system diseases.Methods We retrieved publications from the Web of Science Core Collection database using topic-specific queries on"oral microbi-ome"and"digestive diseases."Bibliometric analysis was performed using VOSviewer,CiteSpace,and the"bibliometrix"package in R for data mining and visualization.Results A total of 1228 eligible articles were included.Analysis revealed that research on the correlation between oral microbiota and digestive system diseases will remain a global hotspot.Academic institutions dominated the publications,with centralized institutional distribution and team-based collaboration,though overall collaboration networks remained fragmented.Geo-graphically,the United States emerged as the leading contributor,followed by China and the United Kingdom.While China-U.S.collaborations were prominent,China's engagement with other regions remained limited.Current research hotspots focus on the interplay between oral microbiota and gut microbiota,inflam-matory bowel disease(IBD),and digestive system tumors.Conclusions Research in this field demonstrates high activity and diversity.Studies on the associations of oral microbiota with gut microbiota,IBD,and diges-tive system tumors(particularly esophageal,gastric,pancreatic,and colorectal cancers)remain prominent.Future studies should prioritize elucidating underlying mechanisms and innovating in biomarker discovery and application.However,insufficient collaboration and resource-sharing among institutions currently hinder pro-gress in this field.

AIM To investigate the protective effect of Sanfeng Tongqiao Dropping Pills against house dust mite(HDM)-induced allergic asthma in mice.METHODS Compared to the intact BALB/c mice in the blank control group,the BALB/c mice randomly assigned into the model group,the dexamethasone group(0.67 mg/kg),and the low-dose,medium-dose,and high-dose Sanfeng Tongqiao Dropping Pills groups(15,30 and 60 mg/kg),were induced into acute allergic asthma models via weekly intraperitoneal sensitization with 0.1 mL HDM solution(0.5 mg/mL)for three weeks followed by three consecutive daily intranasal challenges with 10 μL HDM solution(2.5 mg/mL)starting in the third week.The drug administered continuously 7 days after the last excitation.The mice had their airway reactive Penh value detected,their pulmonary pathological changes observed by HE staining,their blood eosinophils(EOS)counted,their Th2 cytokines in lung tissue and serum IgE levels detected by ELISA,and their number of peripheral blood mononuclear cells(PBMC)and pulmonary Th2 cells detected by flow cytometry.Chronic allergic asthma was induced in grouped BALB/c mice through repeated intranasal challenges with 10 μL HDM solution(2.5 mg/mL)administered five times weekly for five consecutive weeks.Drug treatment continued for 14 days following the final challenge.After the final treatment,the mice had their pulmonary pathological changes observed by HE staining,and their levels of Th2 cytokines in B ALF and lung tissue and serum IgE detected by ELISA.RESULTS Compared to the blank control group,the acute allergic asthma model group exhibited increases in Penh value,EOS count and IgE level in serum,IL-4 and IL-5 levels in lung tissue(P＜0.01);obvious pulmonary inflammatory cells infiltration,and thickened airway wall;and increase in pulmonary number of Th2 cells(P＜0.01).Compared to the model group,the groups intervened with Sanfeng Tongqiao Dropping Pills demonstrated decreased Penh value,serum EOS count,IgE level and IL-5 level in lung tissue(P＜0.05,P＜0.01);reduced pulmonary inflammatory infiltration and alleviated airway wall thickening;and decreased number of pulmonary Th2 cells.Compared to the blank group,the chronic allergic asthma model group showed obvious pulmonary inflammatory infiltration and airway wall thickening;and increased EOS count and IgE level in serum,IL-4 and IL-13 in lung tissue and IL-14 in BALF(P＜0.05,P＜0.01).Compared to the model group,the groups intervened with either medium-dose or high-dose Sanfeng Tongqiao Dropping Pills demonstrated reduced pulmonary inflammatory infiltration;and decreased serum EOS count,IgE level,IL-13 in lung tissue and IL-14 in BALF(P＜0.05,P＜0.01).CONCLUSION Sanfeng Tongqiao Dropping Pills reduce Th2 cells in peripheral blood and lung tissue,suppress type 2 inflammation,and thereby alleviate allergic asthma.

Objective To delineate the current research landscape,emerging hotspots,and frontiers re-garding the relationship between the oral microbiome and digestive system diseases.Methods We retrieved publications from the Web of Science Core Collection database using topic-specific queries on"oral microbi-ome"and"digestive diseases."Bibliometric analysis was performed using VOSviewer,CiteSpace,and the"bibliometrix"package in R for data mining and visualization.Results A total of 1228 eligible articles were included.Analysis revealed that research on the correlation between oral microbiota and digestive system diseases will remain a global hotspot.Academic institutions dominated the publications,with centralized institutional distribution and team-based collaboration,though overall collaboration networks remained fragmented.Geo-graphically,the United States emerged as the leading contributor,followed by China and the United Kingdom.While China-U.S.collaborations were prominent,China's engagement with other regions remained limited.Current research hotspots focus on the interplay between oral microbiota and gut microbiota,inflam-matory bowel disease(IBD),and digestive system tumors.Conclusions Research in this field demonstrates high activity and diversity.Studies on the associations of oral microbiota with gut microbiota,IBD,and diges-tive system tumors(particularly esophageal,gastric,pancreatic,and colorectal cancers)remain prominent.Future studies should prioritize elucidating underlying mechanisms and innovating in biomarker discovery and application.However,insufficient collaboration and resource-sharing among institutions currently hinder pro-gress in this field.

AIM To investigate the effects of Changpu Yujin Decoction(CPYJD)on striatal mitophagy and PINK1/Parkin signaling pathway in a rat model of Tourette syndrome(TS).METHODS Thirty-six SPF male SD rats were randomly assigned to the control group(n=9)and the TS modeling group(n=27).Rats in the modeling group received daily intraperitoneal injections of 3,3'-iminodipropionitrile(IDPN)(300 mg/kg)for 7 consecutive days to establish the TS model.Post-modeling,successfully induced TS rats were re-randomized into model group(no treatment),tiapride group(47.91 mg/kg)and CPYJD group(77.28 g/kg).All groups received their respective interventions via intragastric administration daily for 28 days.Following drug administration,behavioral scores were assessed in each group.Pathological alterations in the striatum were examined using HE staining,while ultrastructural changes were evaluated by transmission electron microscopy(TEM).Neuronal apoptosis was quantified via TUNEL staining,and ROS levels in striatum were measured by ELISA.Co-localization of PINK1 and LC3B was assessed using immunofluorescence(IF).Finally,mRNA and protein expressions of PINK1,Parkin,Beclin-1,P62 and LC3B(LC3B-Ⅱ/Ⅰ ratio)were analyzed by RT-qPCR and Western blot.RESULTS Compared to the control group,the model group demonstrated significantly increased behavioral scores(P＜0.01),elevated neuronal apoptosis rate and higher ROS levels in the striatum(P＜0.01);severe neuronal and mitochondrial damage in the striatum;significantly reduced mRNA and protein expressions of PINK1,Parkin,Beclin-1 and LC3B(LC3B-Ⅱ/Ⅰ ratio)in the striatum(P＜0.01);markedly upregulated P62 mRNA and protein expressions(P＜0.01).Compared to the model group,both the tiapride and CPYJD intervention groups exhibited significantly reduced behavioral scores(P＜0.01);decreased neuronal apoptosis rate and lower ROS levels(P＜0.01);improved pathological alterations in the striatal neurons and mitochondria;increased mRNA and protein expressions of PINK1,Parkin and Beclin-1 in the striatum(P＜0.05,P＜0.01);and decreased P62 mRNA and protein expressions(P＜0.01).Furthermore,the rats in the CPYJD group specifically showed elevated LC3B mRNA level and LC3B-Ⅱ/Ⅰ protein ratio in striatum(P＜0.05,P＜0.01).CONCLUSION The effect of CPYJD intervention in TS rats may involve activation of mitophagy through regulation of the PINK1/Parkin signaling pathway,improving mitochondrial function,reducing ROS levels,and thereby protecting neurons.

Objective:To develop an artificial intelligence (AI)-based platelet review strategy to identify abnormal platelet histograms with no significant difference between initial impedance platelet count (PLT-I) and PLT-F results.Methods:This study included 5 119 routine blood analysis in Nanfang Hospital of Southern Medical University and its Ganzhou branch from July 2023 and March 2024. Specimens exhibiting abnormal platelet histograms and an initial platelet count >40×10?/L underwent review using the fluorescent platelet count (PLT-F) channel. Consistency of the results was defined as a difference between impedance platelet count (PLT-I) and PLT-F less than ±20% of the PLT-F results. A deep learning model was developed using platelet and red blood cell histogram data from a training set of 3 807 specimens. The model′s diagnostic performance was evaluated on an independent external validation set ( n=805) using receiver operating characteristic (ROC) curve analysis. Changes in the number of reviewed samples and sample turnaround time were analyzed to assess its clinical utility. Results:The deep learning model based on platelet and red blood cell histograms achieved an area under the ROC curve (AUC) of 0.854 in the training set. At a cutoff value of 0.1, the sensitivity was 0.954 and specificity was 0.358. The model could reduce review by 16.80% (190/1 131). In the validation set, the AUC was 0.805, with a sensitivity of 0.955 and specificity of 0.307, corresponding to a reduction of 17.41% (47/270) in reviewed specimens.Conclusion:The platelet review prediction model developed based on deep learning technology can efficiently identify samples with consistent results before and after review, reducing unnecessary reviews and shortening specimen testing time, thereby improving the efficiency of platelet test.