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.

Objective: To identify early clinical predictors associated with dysphagia and delayed swallowing recovery in patients with traumatic brain injury (TBI). Methods: In this retrospective study, we enrolled adult TBI patients admitted to the rehabilitation unit of a tertiary medical center between June 2019 and June 2023. Data on baseline characteristics, neurological status, imaging findings, and rehabilitation-related variables were collected. Swallowing function was assessed using two indicators: (1) nasogastric (NG) tube retention and (2) the Functional Oral Intake Scale (FOIS) scores at 1, 4, and 12 weeks post-injury. Regression analyses were conducted to identify predictors associated with dysphagia and swallowing recovery. Results: A total of 160 patients were included. At 1 week post-injury, longer intensive care unit (ICU) stay, poor initial sitting balance and use of sedative medication in ICU were associated with NG tube retention. At 4 weeks, lower initial Rancho Los Amigos Scale (RLAS) scores, immobility-related complications, longer hospitalization, and temporal lobe hematomas were associated with persistent NG tube dependence. By 12 weeks, older age, delayed ability to follow commands, and poor initial sitting balance remained associated with NG tube retention. FOIS outcomes were also associated with older age, delayed time to follow commands, impaired initial sitting balance, prolonged ICU stay, temporal lobe hematomas, lower initial RLAS scores, immobility-related complications, prolonged endotracheal tube placement and extended hospital stays. Conclusion Impaired cognitive status, poor physical function, immobility-related complications, and temporal lobe hematomas were key factors associated with dysphagia and delayed oral intake in individuals with TBI.

Owing to its inherent advantages—such as being non-destructive, rapid, highly molecule-specific, and minimally interfered with by moisture—Raman spectroscopy has been widely adopted in the fields of skin barrier function assessment, monitoring the transdermal penetration of active cosmetic ingredients, and the identification and quality control of cosmetic products. Despite these strengths, the practical application of this technique faces a significant bottleneck: the strong fluorescence background generated by endogenous skin components and exogenous cosmetic additives. Endogenous skin substances, such as structural proteins (e.g., collagen and elastin), metabolic coenzymes (e.g., nicotinamide adenine dinucleotide), and pigments (e.g., melanin), together with exogenous cosmetic constituents like organic colorants, chemical sunscreens, and fragrances, often possess strong absorption and emission characteristics. When excited by lasers, these components produce a fluorescence background that can be 10⁶ to 10⁸ times stronger than the Raman scattering signals, effectively masking the inherently weak vibrational fingerprint information. In recent years, driven by the rapid development of optoelectronic hardware and artificial intelligence algorithms, fluorescence suppression strategies have evolved from isolated, single-method approaches into comprehensive, multi-level synergistic systems. These systems are categorized into three distinct tiers: sample preparation, signal acquisition, and data processing. At the sample preparation level, techniques such as photobleaching and surface-enhanced Raman spectroscopy (SERS) are employed to eliminate or bypass the generation of fluorescence at the source. At the signal acquisition level, instrumental improvements—including the use of long-wavelength near-infrared excitation (typically 785 nm or 1 064 nm), confocal spatial filtering, and shifted excitation Raman difference spectroscopy (SERDS)— are utilized to physically isolate Raman signals from the fluorescence background. Furthermore, at the data processing level, numerical baseline correction methods such as polynomial fitting, penalized least squares (e.g., airPLS, arPLS), wavelet transform, and derivative algorithms are increasingly integrated into the analytical pipeline to extract Raman spectral features from mixed signals without increasing hardware costs or acquisition time. This review provides a systematic categorization and critical evaluation of these fluorescence suppression methods, detailing their underlying principles, technical advantages, and inherent limitations in diverse experimental setups. By focusing on critical application scenarios—including skin barrier assessment, percutaneous absorption monitoring, the routine quality control of cosmetics, and the emerging field of portable on-site detection—this paper explores the current state of technique selection and optimization. Finally, the article discusses future development trends, emphasizing the necessity of constructing adaptive, tiered suppression strategies, developing intelligent and automated data processing algorithms, and promoting the integration of portable, multi-modal diagnostic devices. The objective of this review is to provide a comprehensive technical reference to facilitate the transition of Raman spectroscopy from a specialized laboratory tool into a routine, robust analytical platform for advancements in skin science and cosmetic research.

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.

Rheumatoid arthritis (RA) is a chronic autoimmune disease characterized by synovial inflammation, joint destruction, and functional impairment. Angiogenesis plays a key role in the pathological progression of RA with dysfunction of endothelial cells to promote synovial inflammation, sustain pannus formation, subsequently leading to joint damage. Colquhounia Root Tablets (CRT), a Chinese patent drug, has shown a satisfying clinical efficacy in treating RA, while the underlying mechanism by which CRT inhibits RA-associated angiogenesis remains unclear. In this study, we applied a research approach combining transcriptomic data analysis, bio-network mapping, and in vivo and in vitro experiments to explore the molecular mechanisms of CRT in suppressing angiogenesis in RA. Animal welfare and experimental procedures follow the regulations of the Animal Ethics Committee of Institute of Basic Theory for Chinese Medicine, China Academy of Chinese Medical Sciences (ratification number: IBTCMCACMS21-2307-06). Network analysis identified that key genes such as nucleotide-binding oligomerization domain-containing protein 2 (NOD2), SMAD family member 3 (SMAD3), and vascular endothelial growth factor A (VEGFA) significantly enriched in pathways related to NOD-like receptor signaling and VEGF signaling, indicating that CRT may inhibit angiogenesis by regulating vascular endothelial cell function with modulating angiogenesis-related pathways. In vivo data showed that CRT significantly reduced the positive expression of CD31 and VEGF in the ankle joint of adjuvant-induced arthritis (AIA) rats. In vitro data further confirmed that CRT effectively inhibited VEGF-induced migration, invasion, and tube formation in HUVECs, while significantly reduced the expression of angiogenesis-related factors VEGF/CD31/Ang-1, as well as the positive expression of VEGF and CD31 in HUVECs. Furthermore, CRT markedly decreased the protein expression of NOD2, VEGFA, and SMAD3. In conclusion, these findings indicate that CRT may inhibit the RA-related angiogenesis by targeting the NOD2/SMAD3/VEGF signaling axis to improve endothelial cell function, enriching the scientific connotation of CRT in inhibiting pathological angiogenesis in RA and also offer new insights for clinical prevention and treatment of RA.

ObjectiveBola-like short peptides exhibit novel self-assembly properties due to the formation of peptide dimers via hydrogen bonding interactions between their C-terminals. In this configuration, hydrophilic amino acids are distributed at both terminals, making these peptides behave similarly to Bola peptides. The electrostatic repulsive interactions arising from the hydrophilic amino acids at each terminal can be neutralized, thereby greatly promoting the lateral association of β-sheets. Consequently, assemblies with significantly larger widths are typically the dominant nanostructures for Bola-like peptides. To investigate the effect of hydrophilic amino acids on the self-assembly behavior of Bola-like peptides, the peptides Ac-RI₃-CONH₂ and Ac-HI₃-CONH₂ were designed and synthesized using the Bola-like peptide Ac-KI₃-CONH₂ as a template. Their self-assembly behavior was systematically examined. MethodsAtomic force microscopy (AFM) and transmission electron microscopy (TEM) were employed to characterize the morphology and size of the assemblies. The secondary structures of the assemblies were analyzed using circular dichroism (CD) and Fourier transform infrared (FTIR) spectroscopy. Small-angle neutron scattering (SANS) was used to obtain detailed structural information at a short-length scale. Based on these experimental results, the effects of hydrophilic amino acids on the self-assembly behavior of Bola-like short peptides were systematically analyzed, and the underlying formation mechanism was explored. ResultsThe aggregation process primarily involved three steps. First, peptide dimers were formed through hydrogen bonding interactions between their C-terminals. Within these dimers, the hydrophilic amino acids K, R, and H were positioned at both terminals, enabling the peptides to self-assemble in a manner similar to Bola peptides. Next, β-sheets were formed via hydrogen bonding interactions along the peptide backbone. Finally, self-assemblies were generated through the lateral association of β-sheets. The results demonstrated that both Ac-KI₃-CONH₂ and Ac-RI₃-CONH₂ could self-assemble into double-layer nanotubes with diameters of approximately 200 nm. These nanotubes were formed by the edge fusion of helical ribbons, which initially emerged from twisted ribbons. Notably, the primary assemblies of these peptides exhibited opposite chirality: nanofibers formed by Ac-KI₃-CONH₂ displayed left-handed chirality, whereas those formed by Ac-RI₃-CONH₂ exhibited right-handed chirality. This reversal in torsional direction was primarily attributed to the different abilities of K and R to form hydrogen bonds with water. In contrast, Ac-HI₃-CONH₂ formed narrower twisted ribbons with a significantly reduced width of approximately 30 nm, which was attributed to the strong steric hindrance caused by the imidazole rings. The multilayer height of these ribbons was mainly due to the unique structure of the imidazole rings, which can function as both hydrogen bond donors and acceptors, thereby promoting aggregate growth in the vertical direction. ConclusionThe final morphology of the self-assemblies resulted from a delicate balance of various non-covalent interactions. By altering the types of hydrophilic amino acid residues in Bola-like short peptides, the relative strength of non-covalent interactions that drive assembly formation can be effectively regulated, allowing precise control over the morphology and chirality of the assemblies. This study provides a simple and effective approach for constructing diverse self-assemblies and lays a theoretical foundation for the development of functional biomaterials.