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.

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 This study reports on the obligatory parasitism of water mites Arrenurus sp. on Anopheles messeae at the Manzhouli Port, Inner Mongolia, China. Methods Duing July 2024, a survey on the mosquito diversity was conducted at the Manzhouli Port. Captured mosquitoes and their ectoparasites were identified to species level. Results A total of 1840 adult mosquitoes were collected, representing species from three genera: Culex(Cx. modestus, Cx. pipiens pallens), Aedes(Ae. dorsalis, Ae. flavidorsalis, Ae. flavescens), and Anopheles (An. messeae). Among all the mosqutioes specimens,3 out of 150 captured An. messeae were found to carry ectoparasitic mites, with number of 2,4,27 mites separately. Morphological and molecular identification reached the same result as water mites(Hydrachnidiae, Hydracrina). COI gene sequence showed 94% similarity with the closest species Arrenurus truncatellus. Conlusions Literature review suggests water mites are host-specific parasitism of mosquito species and herein with the first record of Arrenurus sp. parasiting on An. Messeae in the most high-latitude region globally.

Alzheimer's disease(AD)is a progressive,irreversible neurodegenerative disorder characterized by gradual brain cell degeneration,leading to progressive decline in cognitive function and ultimately death.Early identification and intervention are critical to AD diagnosis.In recent years,deep learning has further advanced image-based AD classification methods and facilitated the application of deep models in the early AD diagnosis.To achieve accurate early diagnosis and subsequent classification of AD,researchers have integrated deep learning with magnetic resonance imaging to develop more precise models.By analyzing and synthesizing relevant domestic and international literature,this review introduces commonly used public datasets and evaluation criteria for AD,analyzes the application of magnetic resonance imaging in AD classification and its integration with deep learning methods,and highlights the roles of techniques such as convolutional neural networks,transfer learning,attention mechanisms,and multimodal approaches in AD classification.It also discusses the advantages,limitations,and developmental trends of deep learning in AD classification,aiming to provide new insights for the application of deep learning in AD research.

Objective:To analyze the preferences of medical staff in TCM hospitals in Beijing regarding the achievements transformation of hospital traditional Chinese medicine preparations,and to provide a reference for formulating incentive policies.Methods:233 medical staff from five TCM hospitals in Beijing were taken as the research objects,and surveyed with a questionnaire designed based on the discrete choice experiment(DCE).Mixed logit models and latent class models were then used to analyze their transformation preferences.Results:The mixed Logit model revealed that seven key attributes significantly influenced medical staff's preferences for the achievements transformation of traditional Chinese medicine preparations(P<0.05).Latent class analysis identified three distinct preference groups among respondents:an organization-dependent group(27.0%),a pro-transformation group(61.4%),and a conservative group(11.6%).Conclusions:Medical Staff preferred transformation conditions that increased monthly income;utilized"human use+re-experimentation";involved the hospital's achievements transformation department as the entity;were funded by the hospital;offered a 70%profit share;enabled promotion three years earlier,and assigned patents to the hospital.The study recommends implementing diverse incentive measures and developing differentiated strategies tailored to the distinct Medical Staff categories to facilitate the transformation of hospital traditional Chinese medicine preparations into new drugs.

Objective:To evaluate value of CT perfusion in evaluating the efficacy of different vascular reconstruction methods in the treatment of adult ischemic moyamoya disease.Methods:The clinical data of 80 adult patients with moyamoya disease with ischemic blood type who received revascularization in the Affiliated Hospital of Jining Medical University from February 2019 to February 2023 were retrospectively analyzed, including 43 patients who received superficial temporal arterio-middle cerebral artery anastomosis (direct group) and 37 patients who received brain-dural arterio-artery vascularization (indirect group). The improvement of clinical symptoms, Modified Rankin Scale (mRS) Score, collateral vessels and CTP parameters were compared between the two groups.Results:The improvement of clinical symptoms in the direct group was better than that in the indirect group ( P<0.05), and the significant remission rate was significantly higher than that in the indirect group [86.0%(37/43) vs 59.5%(22/37), χ 2=7.262, P=0.007]. The postoperative mRS score in the direct group was significantly lower than that before surgery [0(0, 1) vs 1(1, 2), Z=5.550, P<0.001]. The score of mRS After surgery in the indirect group was significantly lower than that before surgery [0(0, 1) vs 1(1, 2), Z=4.281, P<0.001], but there was no statistically significant difference between the two groups ( P>0.05). There was no significant difference in digital subtraction angiography (DSA) collateral vessel formation between the two groups ( P>0.05). The CTP parameters of the two groups before and after surgery were consistent between observers and within observers [intraclass correlation coefficient (ICC) range 0.88-0.94]. In the operation area, the relative cerebral blood flow (rCBF) after surgery was significantly increased, and the relative time to peak (rTTP) and relative mean transit time (rMTT) were significantly decreased in both groups, with statistical significance ( P<0.05). In the ipsilateral basal ganglia and frontal lobe, rCBF in the direct group was significantly increased, rTTP and rMTT were significantly decreased, and the differences were statistically significant (all P<0.05), while there were no statistically significant differences in parameters in the indirect group (all P>0.05). The changes of rCBF, rTTP and rMTT in the operative area in the direct group were better than those in the indirect group, and the changes of rCBF, rTTP and rCBF in the basal ganglia and frontal lobe were better than those in the indirect group, with statistical significance (all P<0.05), while there were no statistically significant differences in the remaining parameters (all P>0.05). Conclusions:CT perfusion is of great value in evaluating the difference of clinical symptom improvement in the treatment of adult ischemic moyamoya disease with different vascular reconstruction methods.

Aim To investigate the potential role and related mechanisms of protein phosphatase 2Cm(PP2Cm)overexpression in atorvastatin-induced insu-lin resistance.Methods Male C57BL/6J mice,fibro-blast growth factor 21 knockout(FGF21-KO)mice,and wildtype(WT)mice were raised for 12 weeks to construct models.Groups included atorvastatin,con-trol,atorvastatin+PP2Cm overexpression(OE),FGF21-KO+vehicle,FGF21-KO+PP2Cm OE,WT+vehicle,WT+PP2Cm OE.Body weight,fasting blood glucose levels,fasting insulin levels,and intraperitoneal glucose tolerance tests(IPGTT)were measured in 4,8 and 12 weeks.The concentrations of branched-chain a-mino acids(BCAA)in cells,tissues and serum,as well as the mRNA and protein expression of BCAA cat-abolic enzymes,were determined by qRT-PCR,Western blot and ELISA after atorvastatin treatment.Further-more,the effects of PP2Cm overexpression on these in-dicators were explored,and the FGF21 was verified in vivo and in vitro.Results Atorvastatin induced insu-lin resistance in mice,altered insulin,glucose tolerance and increased BCAA levels.PP2Cm overexpression mitigated these changes.In the Atorvastatin+PP2Cm OE group,FGF21 mRNA,protein and concentration were all significantly upregulated.Regardless of PP2Cm overexpression,the knockout of FGF21 signifi-cantly increased BCAA expression levels,both fasting insulin and blood glucose levels were significantly high-er than those in WT group.Conclusions FGF21 may be an important regulator of PP2Cm involved in atorv-astatin-induced insulin resistance.PP2Cm overexpres-sion alleviates the effects of atorvastatin-induced insulin resistance by regulating FGF21.

Objective:To investigate the current status and challenges of pediatric life support training in China and provide references for improving training quality.Methods:A cross-sectional study was conducted to collect data from pediatric life support training centers across the country，covering basic institutional information，training capacity and training faculty，training program funding，as well as existing challenges and issues.The domestic registry of training centers in 2023 was obtained through the American Heart Association's online platform.After contacting and verifying each center，an online questionnaire was distributed，and the aggregated data were statistically analyzed.Results:A total of 42 institutions participated in the survey，including 19 children's hospitals，14 general hospitals，6 maternal and child health hospitals，2 women and children’s hospitals，and 1 training institution.The distribution of training centers showed a concentration in coastal areas，with the top three provinces/municipalities being Guangdong（7/42，16.7%），Zhejiang（6/42，14.3%），and Shanghai（4/42，9.5%）.As of December 31 2023，the 42 institutions had an annual basic life support（BLS）training volume of 8 587 individuals，the median was 120 (100,200)，and an annual pediatric advanced life support（PALS）training volume of 2 448 individuals，the median was 30 (20,50).Among the 42 institutions，there were 598 BLS instructors and 306 PALS instructors.Among the surveyed institutions，24（24/42，57.1%）reported BLS instructor teams comprising fewer than 10 members，and 33（33/42，78.6%）reported PALS instructor teams comprising fewer than 10.Only 7 centers(7/42,16.7%）reported having dedicated funding support.The top three challenges were：training sessions occupying instructors’personal time（27/42，64.3%），low instructor compensation（16/42，38.1%），and issues with the data submission system（16/42，38.1%）.Conclusion:Pediatric life support training centers in China are primarily children’s hospitals，with a geographical concentration in coastal areas，which is also reflected in the distribution of training scale and instructor resources.Most centers have relatively small training scales and limited instructor capacity，with many instructors conducting training during their personal time.These issues may hinder the implementation and effectiveness of training programs.

Objective To explore the effects of different education and examination methods on the examination results during the screening/evaluation of patent foramen ovale by contrast-enhanced transcranial Doppler(cTCD).Methods Patients who underwent cTCD screening/evaluation for patent foramen ovale in our hospital from May 2023 to February 2024 were retrospectively selected as the research subjects.The patients were divided into the observation group and the control group according to different education and examination methods during the peri-examination period.Patients who received video education,modified Valsalva maneuver,and injection of contrast agent with 20 mL syringe were included into the observation group,and patients who received artificial education,Valsalva maneuver,and injection of contrast agent with 10 mL syringe were included into the control group.The positive detection rate of patent foramen ovale,right-to-left shunt microbubble grading during Valsalva/modified Valsalva maneuver,systolic blood flow velocity,pulsatility index(PI),resistive index(RI),examination duration,total physician-patient communication time,whether occlusion surgery was performed,and patient satisfaction were compared between the two groups.Results The positive detection rate of patent foramen ovale by cTCD(82.93%vs.95.92%),the detection rate of the maximum amout(grade Ⅲ)of microbubbles(39.02%vs.61.22%),the total physician-patient communication time during the peri-examination period[11.30(10.00,14.00)minutes vs.8.23(7.00,10.00)minutes],the rate of occlusion surgery(48.78%vs.73.47%),and the total patient satisfaction(80.49%vs.91.84%)showed statistically significant differences between the control group and the observation group(P<0.05).Additionally,the receiver operating characteristic(ROC)curve analysis showed that the area under the curve(AUC)for diagnosing patent foramen ovale were 0.718 in the control group and 0.855 in the observation group.Conclusion Peri-examination interventions such as video education,modified Valsalva maneuver,and injection of contrast agent with 20 mL syringe can improve the positive detection rate of patent foramen ovale,reduce ineffective physician-patient communication,and improve patient satisfaction.