Angle recession is a common clinical sign typically associated with ocular trauma, potentially leading to severe visual impairment such as glaucoma. Ultrasound biomicroscopy (UBM) offers significant advantages in the diagnosis of angle recession. This study aims to develop an intelligent identification method for angle recession based on UBM images. Initially, a dataset containing 1060 human ocular UBM images was constructed, encompassing normal angles and angle recession cases at various stages; subsequently, identification models were developed using five You Only Look Once version 8 (YOLOv8) architectures of different scales: YOLOv8‑nano (YOLOv8n), YOLOv8‑small (YOLOv8s), YOLOv8‑medium (YOLOv8m), YOLOv8‑large (YOLOv8l), and YOLOv8‑extra‑large (YOLOv8x). Experimental results showed that the YOLOv8x model exhibited the most balanced performance among the five variants, achieving precision values of 0.975 for angle recession and 0.893 for normal angles on the validation set. To further enhance the diagnostic capability, a Cross-Scale Feature Fusion Module (CCFM) and Squeeze-and-Excitation Networks V2 (SENetV2) were integrated into the YOLOv8x baseline to construct the YOLOv8x-CCFM and YOLOv8x-CCFM-SENetV2 models, respectively. Experimental results demonstrated that the improved YOLOv8x-CCFM-SENetV2 model outperformed the baseline YOLOv8x on the validation set, specifically increasing the precision for normal angle identification by 5.6 percentage points and demonstrating more stable and balanced overall performance.

Molecular hydrogen (H₂) has emerged as a potential therapeutic agent with antioxidant, anti-inflammatory, cytoprotective, metabolic, and immunomodulatory effects. Its rapid diffusion across biological membranes facilitates tissue penetration, whereas low aqueous solubility, rapid elimination, and limited retention restrict conventional delivery. This review integrates the mechanisms, delivery technologies, therapeutic applications, safety, and translational barriers of hydrogen therapy, with particular emphasis on the therapeutic advantages and added risks of materials-enabled local and sustained H₂ generation across disease settings. Mechanistically, H₂ attenuates highly reactive oxygen and nitrogen species and regulates nuclear factor erythroid 2-related factor 2 (Nrf2)-dependent antioxidant defenses, mitochondrial homeostasis, nuclear factor kappa B/NLR family pyrin domain-containing 3 (NF-κB/NLRP3)-mediated inflammation, programmed cell death, and host–microbial interactions. To overcome the limitations of inhalation and hydrogen-rich fluids, hydrogen-carrying nanosystems, in situ hydrogen-generating biomaterials, stimulus-responsive nanoplatforms, and biological production systems have been developed to improve localization and prolong H₂ availability. Experimental studies demonstrate therapeutic potential of H₂ in acute organ injury, cardiometabolic, neurological, respiratory, oncological, gastrointestinal, renal, and tissue-repair applications, but clinical evidence remains exploratory and most biomaterial-based systems remain limited to cellular and small-animal studies. The future development of hydrogen therapy should prioritize disease-specific indications and confirm H₂-dependent efficacy, while material-based nanosystems should demonstrate controllable H₂ generation, biodegradability, manufacturing reproducibility, and long-term safety in large-animal studies and well-controlled clinical trials.

Accurate vessel segmentation is crucial for diagnosing cerebrovascular and retinal diseases, but the complexity of vessel structures makes manual annotation challenging, resulting in a lack of annotated data. Additionally, generated data often struggle to balance realism and diversity in vessel morphology. To address this, we provide a theoretical description of vessel structure and propose a vascular morphology-driven augmentation pipeline (VMDAP) for both feature reconstruction and vessel generation based on real vascular morphological characteristics. The pipeline consists of three components: the background restoration block (BRB), the vessel structure feature enhancement block (VSFEB), and the augmented data generation network (ADGN). VMDAP strategically separates vessel data into foreground and background, restores the background, reconstructs vessel masks features, and reintegrates them to generate new data. The ADGN incorporates vessel texture priors and employs a vessel detail enhancement loss to improve the realism of details. To address the performance characteristics of the VMDAP algorithm, this paper also introduces a novel loss function, DAclDice, which focuses on vessel branch structures to reduce false positives. Extensive experiments on six datasets across three representative network architectures validate the effectiveness of VMDAP and structure-driven loss function (DAclDice). Compared to nnU-Net with clDice loss, our method achieves an average Dice coefficient improvement of 2.15, a clDice improvement of 1.16, and a significant 36.17% reduction in 95th percentile Hausdorff distance (HD95). Excitingly, additional experiments demonstrate that VMDAP outperforms full real-data training when only half the real data are used.

Pulmonary delivery offers a noninvasive route for localized and systemic therapy while reducing gastrointestinal degradation and first-pass metabolism. However, its clinical efficacy is limited by heterogeneous pulmonary deposition, mucus and mucociliary clearance, macrophage-mediated elimination, disease-associated microenvironmental remodeling, and instability of biological cargoes during formulation and aerosolization. These challenges have driven growing interest in living biotherapeutics and bio-derived systems. These systems provide intrinsic capabilities for environmental sensing, tissue interaction, cellular targeting, cargo protection, and, in selected cases, active migration within diseased tissues. This narrative review presents an overview of inhaled living biotherapeutics and bio-derived carriers for precision theranostics of lung diseases, encompassing bacteria, bacteriophages, microalgae, mammalian cells, extracellular vesicles (EVs), outer membrane vesicles (OMVs), cell membrane-derived vesicles, and related biological systems. We classify these platforms by biological identity, mechanism of action, and product configuration, highlighting how intrinsic properties govern pulmonary distribution, target recognition, therapeutic activity, and safety. We further examine four engineering strategies: biological reprogramming, cargo loading and biointerface engineering, formulation and preservation, and aerosol delivery engineering. Finally, we discuss challenges in immunogenicity, phenotypic stability, dose consistency, scalability, aerosolization damage, and regulatory translation, outlining considerations for reproducible potency, safety, and quality. Collectively, these advances may transform passive pulmonary deposition into adaptive, mechanism-guided precision theranostics.

Magnetic particle imaging (MPI) is an emerging tracer-based imaging modality characterized by high sensitivity, quantitative linearity, and radiation-free operation. Despite these advantages, its performance is strongly influenced by many factors, including the system matrix (SM) calibration efficiency, reconstruction stability, noise suppression, and spatial resolution limitations. These technical challenges affect the reliability and robustness of MPI in biomedical imaging tasks such as tumor detection, vascular imaging, intracranial hemorrhage monitoring, and cell tracking. This review provides a structured overview of recent advances in MPI, with a particular focus on how deep learning techniques can be integrated into different stages of the reconstruction pipeline to address practical imaging challenges. Unlike existing reviews that mainly emphasize MPI principles, tracer development, or biomedical applications, this review organizes recent progress from the perspective of reconstruction pipeline optimization, covering signal acquisition and reconstruction foundations, X-space and SM-based methods, signal processing, SM calibration, inverse problem solving, and image post-processing. In addition, representative datasets and simulation platforms that support algorithm development and system evaluation are summarized. By connecting reconstruction theory and deep learning methodologies within a unified framework, this review highlights current methodological progress, key technical bottlenecks, and future opportunities for improving the stability, efficiency, and imaging performance of MPI.