Zhengyu Shen

Accurate segmentation of oral mucosal lesions remains challenging because lesion regions often resemble surrounding mucosa, with subtle color differences, weak texture contrast, unclear boundaries, and distractors such as saliva, folds, reflections, and uneven illumination. This study proposes RIVER-NET to improve oral mucosal lesion delineation in complex intraoral images. RIVER-NET is a U-shaped multi-branch progressive aggregation network integrating three task-oriented modules. The Multi-Scale Residual Unit (MSRU) captures multi-scale mucosal texture changes and irregular lesion morphology before spatial downsampling. Dynamic Gated Context Fusion (DGCF) enables gated encoder–decoder context interaction to suppress lesion-like distractors while preserving lesion details. Multi-scale Alignment and Attentive Fusion (MAAF) aligns and attentively aggregates multi-level features to reduce semantic–spatial misalignment and enhance boundary recovery. On the Oral Pathological Mucosa (OPM) dataset, RIVER-NET achieved a Dice score of 75.59% and an IoU of 0.632, outperforming U-Net by 30.88 percentage points in Dice and nnU-Net by 5.23 percentage points. Component-wise and parameter-matched replacement results were consistent with complementary effects of MSRU, DGCF, and MAAF under the current experimental setting. On the independent public ISIC dataset, on which models were trained and evaluated under five-fold cross-validation, RIVER-NET achieved 94.62 ± 2.18% Dice and 0.900 ± 0.039 IoU. Without fine-tuning on the external Autooral dataset, it achieved the highest Dice (0.5547) and specificity (0.9324). RIVER-NET showed promising segmentation performance on the evaluated datasets. These findings demonstrate algorithm-level feasibility but do not establish readiness for clinical use.

Diabetic foot ulcer (DFU) is among the most severe complications of diabetes, where delayed healing is closely linked to impaired angiogenesis and ferroptosis-associated iron dysregulation. However, the underlying molecular mechanisms remain incompletely understood, and effective interventions specifically targeting DFU healing are still lacking. Here, we present a biomimetic iron homeostasis rebalancing nanoregulator, atRA/GOQDs nanoparticles (RG NPs), designed to rebalance pathological iron dynamics and restore the angiogenic microenvironment in chronic diabetic wounds. RG NPs integrate two complementary regulatory modes: labile iron sequestration mediated by GOQDs and intracellular iron buffering reinforcement through atRA-induced ferritin upregulation. This dual-mode strategy actively reconstructs iron equilibrium, suppresses lipid peroxidation at its source, and inhibits endothelial ferroptosis, thereby facilitating angiogenic function and tissue repair. In vitro, RG NPs exhibited robust labile iron sequestration capacity, enhanced ferritin expression, attenuated ferroptosis injury, and restored endothelial angiogenic activity. In db/db mice, local application of RG NPs significantly accelerated wound closure. Collectively, our work reveals an iron homeostasis-angiogenesis regulatory axis and offers a system-level therapeutic strategy that highlights a conceptual shift from conventional antioxidant and simple iron chelation strategies toward a coordinated iron homeostasis regulation in chronic diabetic wound repair.

Background: Oral mucosal diseases are similar to the surrounding normal tissues, i.e., their many non-salient features, which poses a challenge for accurate segmentation lesions. Additionally, high-precision large models generate too many parameters, which puts pressure on storage and makes it difficult to deploy on portable devices. Methods: To address these issues, we design a non-salient target segmentation model (NTSM) to improve segmentation performance while reducing the number of parameters. The NTSM includes a difference association (DA) module and multiple feature hierarchy pyramid attention (FHPA) modules. The DA module enhances feature differences at different levels to learn local context information and extend the segmentation mask to potentially similar areas. It also learns logical semantic relationship information through different receptive fields to determine the actual lesions and further elevates the segmentation performance of non-salient lesions. The FHPA module extracts pathological information from different views by performing the hadamard product attention (HPA) operation on input features, which reduces the number of parameters. Results: The experimental results on the oral mucosal diseases (OMD) dataset and international skin imaging collaboration (ISIC) dataset demonstrate that our model outperforms existing state-of-the-art methods. Compared with the nnU-Net backbone, our model has 43.20% fewer parameters while still achieving a 3.14% increase in the Dice score. Conclusions: Our model has high segmentation accuracy on non-salient areas of oral mucosal diseases and can effectively reduce resource consumption.