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.

Objectives: . Idiopathic sudden sensorineural hearing loss (ISSNHL) is a significant cause of hearing loss. Intratympanic steroid injection (ITSI) is commonly used as an initial or salvage treatment; however, the lack of a standardized treatment protocol has resulted in variability in clinical practice. In addition, no efficient prediction model currently exists to support personalized management. Therefore, this study aimed to develop tailored management strategies for ISSNHL using a machine-learning model. Methods: . This retrospective multicenter cohort study was conducted between January 2015 and December 2020, with data analysis performed between January 2021 and March 2024. Patients were selected based on the International Classification of Diseases, 10th Revision criteria for ISSNHL, along with relevant medication and procedure codes. Patients with pure-tone audiogram results not meeting ISSNHL criteria, better initial hearing in the affected ear, an identifiable etiology, no post-treatment audiogram, or delayed treatment (>6 weeks) were excluded. We included 770 patients diagnosed with ISSNHL who received ITSI. The primary outcome was the area under the receiver operating characteristic curve for prediction performance. Recovery status was determined using the last pure-tone audiogram. Modeling was conducted on the Quanta for Medical Care AI platform using five machine-learning algorithms and a nested cross-validation framework, in which feature selection and hyperparameter tuning were performed in the inner folds and model performance was evaluated in the outer folds. Results: . A random forest classifier outperformed the other models in predicting hearing outcomes, achieving an area under the receiver operating characteristic curve of 0.788. Time to ITSI was the most influential treatment-related factor, with ITSI administered within 10 days of hearing loss being associated with better outcomes. This model can be used to provide personalized prognostic estimates under different treatment protocols. Conclusion . The machine-learning-based prediction model facilitates personalized treatment strategies and timely treatment adjustments for ISSNHL, thereby optimizing the likelihood of complete recovery.

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.

Objective:To evaluate the prognostic value of droplet digital PCR(ddPCR)in conjunction with multiparametric flow cytometry(MFC)for measurable residual disease(MRD)detection in predicting relapse risk in patients with acute myeloid leukemia(AML).Methods:In this retrospective cohort study,we have analyzed 78 newly diagnosed patients with AML who underwent combined MRD monitoring using MFC and ddPCR at The Affiliated Hospital of Hebei University(January 2018-January 2025).Clinical outcomes-including MRD negativity rates,cumulative incidence of relapse(CIR),relapse-free survival(RFS),and overall survival(OS)-were systematically evaluated.Prognostic discrim-ination between the MRD-negative and MRD-positive subgroups was compared across standalone and combined detection approaches.Results:With a median follow-up of 17 months(range:2.4-86.7)and a median of one mutation tracked per patient(range:1-3),both MFC-MRD and ddPCR-MRD negative subgroups demonstrated superior 2-year RFS compared with MRD-positive counterparts.Notably,com-bined MFC/ddPCR monitoring enhanced prognostic discrimination,with MRD-negative patients achieving significantly prolonged 2-year RFS compared with MRD-positive patients.MFC-MRD negativity independently predicted improved 2-year OS.Conclusion:ddPCR-based multi-gene MRD profiling provides significant independent prognostic value in patients with AML.The synergistic application of MFC and ddPCR enables superior predictive accuracy for relapse risk and survival outcomes,supporting its integration into standardized MRD monitoring protocols.

Objective:To assess the effect of transversus abdominis plane block (TAPB) with liposomal bupivacaine and general anesthesia on postoperative delirium (POD) in elderly patients with prior novel coronavirus pneumonia (COVID-19).Methods:In this randomized double-blind controlled study, 416 patients of either sex, aged 65-90 yr, weighing 50-90 kg, of American Society of Anesthesiologists Physical Status classification Ⅰ-Ⅲ, diagnosed as having COVID-19 within 6 months prior to surgery, who underwent laparoscopic colorectal cancer surgery under combination of elective TAPB and combined intravenous-inhalational general anaesthesia at Qingdao Municipal Hospital from June 2023 to December 2024, were selected. The patients were divided into liposomal bupivacaine group ( n=208) and bupivacaine hydrochloride group ( n=208) using the random number table method. After induction of anaesthesia, bilateral TAPB was performed with liposomal bupivacaine injectio 266 mg (40 ml) in liposomal bupivacaine group and with 0.5% bupivacaine hydrochloride 40 ml in bupivacaine hydrochloride group. The primary outcome measure was the occurrence of POD within 7 days after surgery. Secondary outcome measures included severity of POD, pain scores at 24, 48 and 72 h after operation, the rate of postoperative rescue analgesia and consumption of morphine, duration of post-anesthesia care unit stay, and length of hospital stay. The occurrence of complications such as death, reoperation, atelectasis and pneumonia was recorded at 30 days after surgery. Results:Compared with bupivacaine hydrochloride group, the incidence of POD was significantly decreased (21.5% [43/200]versus 12.0% [24/200]), pain scores at 24, 48 and 72 h after operation were decreased, the rate of postoperative rescue analgesia and consumption of morphine were decreased, and the duration of post-anesthesia care unit stay and length of hospital stay were shortened in liposomal bupivacaine group ( P<0.05). There was no significant difference in the severity of POD and the case fatality rate and related complications within 30 days after surgery between the two groups ( P>0.05). Conclusions:Liposomal bupivacaine TAPB combined with general anesthesia can reduce the development of POD in elderly patients with prior COVID-19.

Objective:To evaluate the relationship between preoperative concentrations of soluble triggering receptor expressed on myeloid cells 2 (sTREM2) in cerebrospinal fluid (CSF) and postoperative delirium (POD) in patients undergoing total knee/hip arthroplasty.Methods:Six hundred and twenty-five patients of either sex, aged 50-90 yr, weighing 50-80 kg, with American Society of Anesthesiologists Physical Status classification Ⅰor Ⅱ, with the preoperative Mini-Mental State Examination score > 23, who underwent elective knee/hip arthroplasty under combined spinal-epidural anesthesia at Qingdao Municipal Hospital from January 2022 to December 2023, were selected. The CSF specimens 2 ml were withdrawn from the subarachnoid space after successful subarachnoid puncture for determination of the concentrations of sTREM2, Amyloid beta protein (Aβ 42), total tau protein (T-tau), and phosphorylated tau protein (p-tau) by enzyme-linked immunosorbent assay. POD was assessed using the Confusion Assessment Method. Patients were divided into POD group and non-POD group based on whether POD occurred. Logistic regression was used to identify the risk and protective factors for POD. The performance of CSF sTREM2 concentration combined with CSF biomarker levels in predicting POD was evaluated using the receiver operating characteristic (ROC) curve and clinical decision curve. The mediating effect of CSF biomarker concentrations in the relationship between CSF sTREM2 concentration and POD was analyzed. Results:Five hundred and nineteen patients were finally included, with 112 patients in POD group and 407 patients in non-POD group. The results of logistic regression analysis showed that the elevated preoperative sTREM2 concentration in CSF was the risk factor for POD after adjusting for multiple confounding factors such as age, sex, body mass index, years of education, Mini-Mental State Examination score, history of smoking, history of drinking, hypertension, diabetes mellitus and coronary heart disease. The area under the ROC curve of the preoperative sTREM2 concentration in CSF in predicting POD was 0.716, and the area under the ROC curve of the preoperative sTREM2 concentration in CSF combined with CSF biomarkers in predicting POD was 0.796. This model had high clinical application value and predictive efficacy. The relationship between the preoperative sTREM2 concentration in CSF and POD was partially mediated by the CSF p-tau concentration (proportion of mediated effect 24.67%) and t-tau protein concentration (proportion of mediated effect 17.33%).Conclusions:The elevated preoperative concentration of sTREM2 in CSF is a risk factor for POD in patients undergoing total knee/hip arthroplasty, and concentrations of t-tau and p-tau in CSF play a mediating role in the relationship between the preoperative CSF sTREM2 concentration and POD.

Objective:To evaluate the association between postoperative delirium (POD) and preoperative frailty in elderly patients undergoing knee or hip arthroplasty.Methods:This nested case-control study utilized medical records from elderly patients who underwent knee or hip arthroplasty under combined spinal-epidural anesthesia at Qingdao Municipal Hospital between September 2021 and May 2023. Participants were divided into 2 groups based on clinically diagnosed POD: POD group ( n=53) and non-POD group ( n=256). Univariate analysis was conducted on suspected influencing factors, and logistic regression analysis was utilized to identify the risk factors for POD. Receiver operating characteristic and clinical decision curves were plotted to evaluate the predictive performance of these risk factors for POD. Mediation analysis was performed, and a clinically applicable nomogram was constructed to achieve visual prediction of outcomes. Results:There were statistically significant differences in age, preoperative frailty, body mass index, American Society of Anesthesiologists Physical Status classification, Memorial Delirium Assessment Scale scores, and concentrations of Aβ 42, Aβ 40, phosphorylated tau protein (p-tau protein) and tau protein, Aβ 42/tau ratio and Aβ 42/p-tau ratio in cerebrospinal fluid (CSF) between non-POD group and POD group ( P<0.05). Preoperative frailty was a risk factor for POD ( P<0.05). Mediation analysis revealed that the association between preoperative frailty and POD was mediated by CSF tau protein concentrations. The area under the receiver operating characteristic curve of preoperative frailty and CSF biomarker concentrations in predicting POD was 0.974 ( P<0.05). The clinical decision curve demonstrated that the model combining the preoperative frailty and CSF biomarker concentrations predicted a higher net benefit ( P<0.05). The clinical decision curve showed that the model combining preoperative frailty and CSF biomarker concentrations predicted a higher net benefit. Conclusions:Preoperative frailty is a risk factor for POD in elderly patients undergoing knee or hip arthroplasty, and its combination with CSF biomarker concentrations can effectively predict the occurrence of POD. CSF tau concentration mediates the association between preoperative frailty and development of POD.

Objective:To evaluate the association between the preoperative aspartate aminotransferase/alanine aminotransferase (AST/ALT) ratio and postoperative delirium (POD) in patients undergoing total knee/hip arthroplasty.Methods:In this nested case-control study, medical records from patients, aged ≥55 yr, of American Society of Anesthesiologists Physical Status classification Ⅰ or Ⅱ, with Mini-Mental State Examination (MMSE) scale score >24 on preoperative day 1, scheduled for elective total knee/hip arthroplasty under combined spinal-epidural anesthesia at Qingdao Municipal Hospital between November 2021 and December 2023, were collected. POD was assessed using the Confusion Assessment Method. Patients were categorized into POD and non-POD groups based on the occurrence of POD. Logistic regression was employed to identify protective and risk factors for POD. The predictive performance of preoperative AST/ALT ratio alone and its combination with cerebrospinal fluid (CSF) biomarker concentrations for POD was evaluated using receiver operating characteristic curves, and the clinical utility of the prediction models was assessed using decision curve analysis. Mediation analysis was conducted to examine the mediation role of CSF biomarkers in the relationship between the preoperative AST/ALT ratio and POD. Restricted cubic splines were used to assess the nonlinear relationship between the preoperative AST/ALT ratio and POD.Results:A total of 460 patients were finally included, with 49 in POD group and 411 in non-POD group. After adjustment for multiple confounding factors including age, sex, educational level, MMSE score, history of hypertension, history of diabetes, history of smoking and history of alcohol use, multivariable logistic regression identified that the higher preoperative AST/ALT ratio, CSF total tau protein (t-tau) and phosphorylated tau protein (p-tau) concentrations were independent risk factors for POD, whereas lower CSF β-amyloid 42 (Aβ 42) concentration, Aβ 42/t-tau ratio and Aβ 42/p-tau ratio served as protective factors ( P<0.05). The area under the receiver operating characteristic curve of the preoperative AST/ALT ratio combined with CSF biomarkers in predicting POD was 0.939 ( P<0.001), demonstrating high clinical efficacy. After adjusting for age, educational level, sex, MMSE score, history of hypertension, history of diabetes, history of smoking, history of alcohol use and body mass index, restricted cubic splines revealed a nonlinear relationship between preoperative AST/ALT levels and the probability of POD, and the probability of POD increased with rising ratios when the preoperative AST/ALT ratio ranged from 1.09 to 1.40 ( Poverall < 0.05, Pnonlinear <0.05). After stratification by sex, the preoperative AST/ALT ratio demonstrated a linear relationship with the probability of POD ( Poverall <0.05, Pnonlinear>0.05). Mediation analysis indicated that the relationship between the preoperative AST/ALT ratio and POD was partially mediated by CSF p-tau concentration (proportion mediated 18.1%), CSF t-tau concentration (proportion mediated 12.0%), and the Aβ 42/t-tau ratio (proportion mediated 15.4%). Conclusions:A higher preoperative AST/ALT ratio is an independent risk factor for POD in total knee/hip arthroplasty patients. The concentrations of CSF t-tau and p-tau and Aβ 42/t-tau ratio have a mediating role in the relationship between the preoperative AST/ALT ratio and POD.

Objective:To explore the genotype and the clinical phenotype of SCN2A-related developmental delay in children. Methods:A case series study was adopted. Collect clinical data from 10 cases of children with SCN2A gene variants diagnosed with global developmental delay/intellectual disability who were admitted to the Children′s Hospital between July 2019 and March 2023. Summarize the clinical phenotype and genotype based on clinical data such as general information, clinical manifestations, imaging examinations, laboratory tests, genetic testing results, and comprehensive pediatric neuropsychological development assessment. Results:A total of 10 patients were recruited, including 7 males and 3 females, with an age range of 27 days to 5 years and 9 months. 9 patients underwent children′s neuropsychological and behavioral assessments, and the results were consistent with global developmental delay, including 2 mild cases, 4 moderate cases, and 3 severe cases. 3 cases had autism spectrum disorder, and 2 cases had epilepsy. 6 patients underwent complete head MRI examination, and 4 of them showed abnormalities, including delayed myelination, widening of the local extra brain space in the frontal lobe, and abnormal frontal lobe morphology. All 10 cases had point variants. Among them, 9 cases are de novo and 1 case is maternal inheritance. Out of 10 cases, there were 5 cases with copy number variations, but all of them were of unknown significance. Among the 10 variants, 8 have been reported and 2 have not been reported, namely c.4145A>T(p.N1382I) and c.4937T>A(p.I1646N). In this study, 4 out of 10 patients with SCN2A variants had variation sites located in the S4 segment of domain which constitute Nav1.2, the sodium ion channel encoded by SCN2A. The developmental quotient level was lower when the variation sites were located in the S4 segment of domain, and the difference was statistically significant ( t=-3.101, P=0.017), indicating that the severity of developmental delay may be related to the localization of amino acids corresponding to variant sites within the protein domain. Conclusion:SCN2A mutations are strongly associated with diverse neurodevelopmental disorders. In this study, the phenotypic spectrum of SCN2A variants encompassed epilepsy, global developmental delay, and autism spectrum disorder. Affected individuals exhibited early-onset developmental delays, predominantly moderate to severe in severity. Voltage-sensing domain dysfunction in sodium channels may constitute a critical pathomechanism underlying neurodevelopmental impairments. Further electrophysiological characterization and molecular mechanistic studies are warranted todelineate the genotype-phenotype correlations between specific variant loci and clinical severity.