arXiv subjects

Shixin Xu

Publications and source records attributed to Shixin Xu.

At least 19 recordsLinked to original sources

arXiv2026

Multiscale retinal flow on a spherical cap of varying aperture

Modelling retinal haemodynamics is crucial for understanding retinal microcirculation but is computationally demanding because it involves coupling between the vasculature and surrounding tissue across multiple scales. This computational burden has been substantially alleviated by a recent analytic solution on the planar disc that enables lumping the capillary bed and surrounding tissue into an effective resistor. However, that formulation treats the retina as a flat surface, whereas the retina is a curved surface with a finite anterior aperture. In this work, we develop a nontrivial and physiologically necessary extension to spherical-cap tissue domains with varying apertures, where surface curvature and finite-aperture boundaries complicate solving coupled Darcy equations on a curved manifold. Using a stereographic projection and a decoupling transformation, we derive an analytic solution for the capillary-tissue system on the spherical cap that represents flow in both the capillary bed and interstitial tissue more realistically while retaining the efficient resistor formulation, a key advantage of the planar-disc formulation. This solution is coupled to one-dimensional (1D) arteriolar and venular flows to obtain a multiscale description of retinal haemodynamics. Using a vasculature model designed to capture retinal vascular features, we show that the multiscale model's predictions are consistent with experimental data. We further explore aperture effects using both a fixed hemispherical vasculature and aperture-dependent vasculature. The aperture affects retinal haemodynamics mainly through changes in the constructed vasculature itself, whereas the surface-averaged pressures and relative terminal flow distributions remain nearly unchanged. This framework provides a foundation for studying retinal pathophysiology on more anatomically realistic domains.

physics.bio-ph↗

arXiv2026

Interpretable Fundus Image Classification via Ring-Based Retinal Vasculature Features

Retinal fundus photography is widely used for screening and monitoring ocular diseases, but many modern classification pipelines rely on deep latent representations and provide limited interpretability. This study develops an interpretable fundus image classification framework based on a ring-structured representation of the retinal vasculature centered on the optic disc. The method quantifies vessel geometry, color appearance, oxygenation-related vascular appearance, and vessel--background entropy within concentric retinal regions. These physiologically motivated descriptors are derived from vessel masks, image intensities, and optical-density measurements and aggregated across rings to capture spatial variation in vascular properties. Using only quantitative vascular descriptors, the proposed method achieved strong classification performance across three public fundus datasets. On HRF, it achieved 91.1\% accuracy using automatically generated vessel masks, matching RETFound, a vision transformer pretrained on large-scale retinal fundus image data, under the same evaluation setting. Additional analyses suggest that pretrained image models are sensitive to acquisition-related spatial cues, including fundus scale and retinal position within the field of view, as well as broader non-vessel image characteristics. This framework may support interpretable disease classification, quantitative retinal phenotyping, and retinal biomarker discovery without requiring large task-specific training datasets.

cs.CV↗

arXiv2026

StageGuard: Physiologically Constrained Sleep Staging

Automated sleep staging is increasingly used in large-scale studies to derive sleep-architecture endpoints: total sleep time, REM latency, sleep efficiency, and bout-duration statistics. Deep learning models achieve epoch-level accuracy approaching inter-rater agreement, yet often produce hypnograms that violate physiological invariants, such as rare transitions (e.g., direct Wake -> REM) or excessively fragmented sequences. Such violations can bias downstream sleep metrics, regardless of overall accuracy. We propose StageGuard, a plug-and-play, backbone-agnostic structured-inference framework that wraps any neural sleep-staging backbone with physiology-informed priors. StageGuard combines (1) a differentiable soft transition penalty that discourages physiologically rare transitions during training, and (2) a semi-Markov constrained decoder with a duration-augmented state space that jointly enforces transition penalties and minimum bout durations at inference. Unlike hard-prohibition methods, it admits rare transitions when emission evidence is overwhelming, leaving informative pathological events recoverable rather than blocked. StageGuard constrains staging outputs to satisfy known physiological priors rather than modeling sleep generatively. We quantify the validity gap using transition-violation rate (TVR) and fragmentation index (FI) and demonstrate that, across six backbones and four datasets, StageGuard reduces TVR to physiologically plausible levels and lowers FI by 56-62%, while maintaining or slightly improving classification accuracy. Crucially, improved constraint satisfaction translates into 59-79% lower error on derived sleep-architecture statistics not directly optimized by the method, and recovers the direction and effect size of expert-defined subgroup differences (OSA severity, age) more faithfully than the unconstrained baseline.

cs.LG↗

arXiv2026

AQP4 Regulates Gap-Dominated Glymphatic Clearance through Dynamic Gliovascular Coupling

Aquaporin-4 (AQP4) is enriched at perivascular astrocytic endfeet, and impaired AQP4 function or localization is associated with reduced glymphatic transport. However, mechanical models suggest that pressure-driven exchange across the gliovascular interface occurs predominantly through inter-endfoot gaps rather than directly through the AQP4-rich membrane. How AQP4 regulates clearance in such a gap-dominated system remains unclear. We develop a reduced arterial PVS-ECS-venous PVS model coupling vascular deformation, AQP4-mediated endfoot water exchange, dynamic inter-endfoot gap regulation, and tracer transport. Cardiac-like oscillations generate strong bidirectional exchange but weak net clearance, whereas asymmetric vasodilation enhances directional transport by suppressing recovery-phase backflow. Dynamic gap regulation provides additional hydraulic rectification. Although gap-mediated flux is much larger than direct AQP4-mediated flux, PVS-facing AQP4 substantially affects clearance by altering the pressure--volume balance and hence the driving force for the dominant gap pathway. Reducing PVS-facing AQP4 permeability, or redistributing AQP4 away from the PVS-facing membrane at fixed total conductance, reduces cumulative venous output by about 40\%. Aging-like changes in vascular motion, PVS mechanical coupling, and perivascular AQP4 enrichment further compound this impairment. These results suggest that AQP4 regulates gap-dominated glymphatic clearance through dynamic hydraulic coupling at the gliovascular interface.

physics.med-ph↗

arXiv2026

TabLoRA: Parameter-Efficient Low-Rank Ensemble Learning for Large-Scale Tabular Data

Tabular learning is still dominated by gradient-boosted decision trees (GBDTs), while recent deep learning approaches have become increasingly competitive. However, applying deep tabular models to large-scale datasets remains challenging, as large sample sizes, high feature dimensionality, or many target classes can introduce substantial computational cost. We propose TabLoRA, a parameter-efficient trainable neural ensemble for large-scale tabular learning. Instead of using fully independent ensemble backbones, TabLoRA shares a common backbone across predictors and introduces predictor-specific low-rank adaptations, enabling ensemble-style prediction without full parameter duplication. Across benchmarks, TabLoRA achieves a favorable balance between predictive performance and practical efficiency compared with GBDT methods and recent deep learning baselines under the same resource constraints. Memory analysis and ablation studies further show that the proposed design improves the feasibility of neural ensemble learning while preserving much of the benefit of full ensembles.

cs.LG↗

arXiv2025

TWLR: Text-Guided Weakly-Supervised Lesion Localization and Severity Regression for Explainable Diabetic Retinopathy Grading

Accurate medical image analysis can greatly assist clinical diagnosis, but its effectiveness relies on high-quality expert annotations Obtaining pixel-level labels for medical images, particularly fundus images, remains costly and time-consuming. Meanwhile, despite the success of deep learning in medical imaging, the lack of interpretability limits its clinical adoption. To address these challenges, we propose TWLR, a two-stage framework for interpretable diabetic retinopathy (DR) assessment. In the first stage, a vision-language model integrates domain-specific ophthalmological knowledge into text embeddings to jointly perform DR grading and lesion classification, effectively linking semantic medical concepts with visual features. The second stage introduces an iterative severity regression framework based on weakly-supervised semantic segmentation. Lesion saliency maps generated through iterative refinement direct a progressive inpainting mechanism that systematically eliminates pathological features, effectively downgrading disease severity toward healthier fundus appearances. Critically, this severity regression approach achieves dual benefits: accurate lesion localization without pixel-level supervision and providing an interpretable visualization of disease-to-healthy transformations. Experimental results on the FGADR, DDR, and a private dataset demonstrate that TWLR achieves competitive performance in both DR classification and lesion segmentation, offering a more explainable and annotation-efficient solution for automated retinal image analysis.

cs.CV↗

arXiv2025

A novel multiscale modelling for the hemodynamics in retinal microcirculation with an analytic solution for the capillary-tissue coupled system

Mathematical modelling of the microcirculatory hemodynamics in the retina is an essential tool for understanding various diseases of the retina, yet remains challenging due to the multiscale nature of the retinal vasculature and its coupling to surrounding tissue. To address this, we develop a multiscale model that couples retinal vasculature across scales with interstitial tissue. Our model combines the one-dimensional (1D) model for arterioles and venules with the coupled Darcy equations for capillaries and tissue. The model uses an analytic solution for capillary-tissue coupled system that provides a simple interpretation of the results along with much faster computation. The analytic solution implies a dynamic coupling condition that links the capillary bed with upstream arteriolar and downstream venular flows. The model is mathematically robust, demonstrated through analysis of the solution's truncation error and convergence. Its predictive accuracy is validated against experimental data and other models, making it useful in interpreting experimental results. Finally, the role of various parameters in controlling retinal hemodynamics is explored.

physics.bio-ph↗

arXiv2025

Efficient Global-Local Fusion Sampling for Physics-Informed Neural Networks

The accuracy of Physics-Informed Neural Networks (PINNs) critically depends on the placement of collocation points, as the PDE loss is approximated through sampling over the solution domain. Global sampling ensures stability by covering the entire domain but requires many samples and is computationally expensive, whereas local sampling improves efficiency by focusing on high-residual regions but may neglect well-learned areas, reducing robustness. We propose a Global-Local Fusion (GLF) Sampling Strategy that combines the strengths of both approaches. Specifically, new collocation points are generated by perturbing training points with Gaussian noise scaled inversely to the residual, thereby concentrating samples in difficult regions while preserving exploration. To further reduce computational overhead, a lightweight linear surrogate is introduced to approximate the global residual-based distribution, achieving similar effectiveness at a fraction of the cost. Together, these components, residual-adaptive sampling and residual-based approximation, preserve the stability of global methods while retaining the efficiency of local refinement. Extensive experiments on benchmark PDEs demonstrate that GLF consistently improves both accuracy and efficiency compared with global and local sampling strategies. This study provides a practical and scalable framework for enhancing the reliability and efficiency of PINNs in solving complex and high-dimensional PDEs.

cs.LG↗

arXiv2025

Glymphatic Clearance in the Optic Nerve: A Multidomain Electro-osmostic Model

Effective metabolic waste clearance and maintaining ionic homeostasis are essential for the health and normal function of the central nervous system. To understand its mechanism and the role of fluid flow, we develop a multidomain electro-osmotic model of optic-nerve microcirculation that couples hydrostatic and osmotic fluid transport with electro-diffusive solute movement across axons, glia, the extracellular space, and arterial/venous/capillary perivascular spaces. Cerebrospinal fluid enters the optic nerve via the arterial parivascular space, passes both the glial and ECS before exiting through the venous parivascular space. Exchanges across astrocytic endfeet are essential and they occur in two distinct and coupled paths: through AQP4 on glial membranes and gaps between glial endfeet, thus establishing a mechanistic substrate for two modes of glymphatic transport, at rest and during stimulus-evoked perturbations. Parameter sweeps show that lowering AQP4-mediated fluid permeability or PVS permeability elevates pressure, suppresses radial exchange and slows clearance, effects most pronounced for solutes reliant on PVS V export. The model reproduces baseline and stimulus-evoked flow and demonstrates that PVS-mediated export is the primary clearance route for both small and moderate solutes. Small molecules clear faster because rapid ECS diffusion broadens their distribution and enhances ECS PVS exchange, whereas moderate species have low ECS diffusivity, depend on transendfoot transfer, and clear more slowly via PVS V convection. Our framework can also be used to explain the sleep-wake effect mechanistically: enlarging ECS volume or permeability increases transinterface flux and accelerates waste removal.

q-bio.CB↗

arXiv2025

Brain-Inspired Perspective on Configurations: Unsupervised Similarity and Early Cognition

Infants discover categories, detect novelty, and adapt to new contexts without supervision-a challenge for current machine learning. We present a brain-inspired perspective on configurations, a finite-resolution clustering framework that uses a single resolution parameter and attraction-repulsion dynamics to yield hierarchical organization, novelty sensitivity, and flexible adaptation. To evaluate these properties, we introduce mheatmap, which provides proportional heatmaps and reassignment algorithm to fairly assess multi-resolution and dynamic behavior. Across datasets, configurations are competitive on standard clustering metrics, achieve 87% AUC in novelty detection, and show 35% better stability during dynamic category evolution. These results position configurations as a principled computational model of early cognitive categorization and a step toward brain-inspired AI.

cs.LG↗

arXiv2025

Mixing Configurations for Downstream Prediction

Clustering-based features are widely used in machine learning, but most methods must choose a resolution -- a choice that is global, fixed, and ad hoc. Recent work shows that varying the resolution parameter produces only a finite set of structurally stable partitions, known as configurations. Based on this, we introduce Configuration-Mixed Prediction (CMP), a setting where models learn to adaptively weight these configurations per sample for downstream prediction. We propose MixConfig, a plug-and-play feature augmentation module that extracts configurations from any frozen embedding and learns energy-aware mixing weights via a novel selector that jointly reasons about sample context, cluster assignments, and stability statistics. Experiments across tabular, molecular, vision, and text domains demonstrate consistent improvements over single-resolution and static baselines across diverse predictor architectures, with gains particularly pronounced in low-data regimes.

cs.LG↗

arXiv2025

Pump-driven droplet electrohydrodynamics: deformation, pinch-off and recoalescence

We investigate pump-driven droplet electrohydrodynamics with an emphasis on deformation, pinch-off, and recoalescence. A thermodynamically consistent phase-field framework is developed that couples Nernst--Planck--Poisson electrodiffusion with incompressible Navier--Stokes--Cahn--Hilliard flow, and incorporates interfacial ionic pumps as prescribed surface fluxes. In the pump-free baseline, applied fields merely polarise the droplet and deformation is negligible. By contrast, surface-localised pumping drives the accumulation of positive ions within the droplet, elevates the interior potential, and generates non-uniform electric fields. The resulting Lorentz stresses stretch and displace the droplet, thin interfacial necks, and trigger pinch-off; the daughter droplets subsequently recoalesce, often after wall contact, yielding flattened remnants. In multiple-droplet settings, pump-induced charging produces lateral electrostatic repulsion and asymmetric deformation; under geometric confinement, crescent bending and star-like morphologies emerge. Shear-flow tests further show that a pumped droplet can be immobilised and ruptured while an unpumped neighbour is advected downstream, suggesting a route to sorting. Taken together, the results establish interfacial pumping as an internal actuation mechanism that robustly controls droplet morphology and dynamics across configurations.

physics.flu-dyn↗

arXiv2025

Thermodynamically Consistent Modeling and Stable ALE Approximations of Reactive Semi-Permeable Interfaces

Reactive, semi-permeable interfaces play important roles in key biological processes such as targeted drug delivery, lipid metabolism, and signal transduction. These systems involve coupled surface reactions, transmembrane transport, and interfacial deformation, often triggered by local biochemical signals. The strong mechanochemical couplings complicate the modeling of such interfacial dynamics. We propose a thermodynamically consistent continuum framework that integrates bulk fluid motion, interfacial dynamics, surface chemistry, and selective solute exchange, derived via an energy variation approach to ensure mass conservation and energy dissipation. To efficiently solve the resulting coupled system, we develop a finite element scheme within an Arbitrary Lagrangian-Eulerian (ALE) framework, incorporating the Barrett-Garcke-Nurnberg (BGN) strategy to maintain mesh regularity and preserve conservation laws. Numerical experiments verify the convergence and conservation properties of the scheme and demonstrate its ability in capturing complex interfacial dynamics. Two biologically inspired examples showcase the model's versatility: cholesterol efflux via the ABCG1 pathway, involving multistage interfacial reactions and HDL uptake; and a self-propelled droplet system with reaction-activated permeability, mimicking drug release in pathological environments. This work provides a unified computational platform for studying strongly coupled biochemical and mechanical interactions at interfaces, offering new insights into reactive transport processes in both biological and industrial contexts.

math.NA↗

arXiv2025

Phase-Field Modeling and Energy-Stable Schemes for Osmotic Flow through Semi-Permeable

We present a thermodynamically consistent phase-field model for simulating fluid transport across semi-permeable membranes, with a particular focus on osmotic pressure effects. The model extends the classical Navier-Stokes-Cahn-Hilliard (NSCH) system by introducing an Allen-Cahn-type transmembrane flux governed by chemical potential imbalances, resulting in a strongly coupled system involving fluid motion, solute transport, and interface dynamics. To solve this system efficiently and accurately, we develop high-order, energy-stable numerical schemes. The local discontinuous Galerkin (LDG) method is employed for spatial discretization, offering high-order accuracy and geometric flexibility. For temporal integration, we first construct a first-order decoupled scheme with rigorous energy stability, and then improve temporal accuracy via a semi-implicit spectral deferred correction (SDC) method. Numerical experiments confirm the theoretical properties of the proposed scheme and demonstrate the influence of osmotic pressure and membrane permeability on droplet morphology at equilibrium. The framework offers a robust and versatile tool for modeling transmembrane fluid transport in both biological and industrial applications.

physics.flu-dyn↗

arXiv2025

Micro-Macro Modeling of Polymeric Fluids with Multi-Bead Polymer Chain

This work extends the classical dumbbell (two-bead) model of polymer chains to a more detailed multi-bead representation, where each polymer chain consists of $N$ beads connected by $N-1$ springs. We develop a thermodynamically consistent micro-macro model based on the energy variational method to describe the coupled dynamics of polymer configurations and fluid flow. The resulting framework captures complex microscopic behaviors, such as bond stretching and alignment under flow, and links them to macroscopic stress responses.

cond-mat.soft↗

arXiv2025

TIME: TabPFN-Integrated Multimodal Engine for Robust Tabular-Image Learning

Tabular-image multimodal learning, which integrates structured tabular data with imaging data, holds great promise for a variety of tasks, especially in medical applications. Yet, two key challenges remain: (1) the lack of a standardized, pretrained representation for tabular data, as is commonly available in vision and language domains; and (2) the difficulty of handling missing values in the tabular modality, which are common in real-world medical datasets. To address these issues, we propose the TabPFN-Integrated Multimodal Engine (TIME), a novel multimodal framework that builds on the recently introduced tabular foundation model, TabPFN. TIME leverages TabPFN as a frozen tabular encoder to generate robust, strong embeddings that are naturally resilient to missing data, and combines them with image features from pretrained vision backbones. We explore a range of fusion strategies and tabular encoders, and evaluate our approach on both natural and medical datasets. Extensive experiments demonstrate that TIME consistently outperforms competitive baselines across both complete and incomplete tabular inputs, underscoring its practical value in real-world multimodal learning scenarios.

cs.CV↗

arXiv2025

Beyond Single-Channel: Multichannel Signal Imaging for PPG-to-ECG Reconstruction with Vision Transformers

Reconstructing ECG from PPG is a promising yet challenging task. While recent advancements in generative models have significantly improved ECG reconstruction, accurately capturing fine-grained waveform features remains a key challenge. To address this, we propose a novel PPG-to-ECG reconstruction method that leverages a Vision Transformer (ViT) as the core network. Unlike conventional approaches that rely on single-channel PPG, our method employs a four-channel signal image representation, incorporating the original PPG, its first-order difference, second-order difference, and area under the curve. This multi-channel design enriches feature extraction by preserving both temporal and physiological variations within the PPG. By leveraging the self-attention mechanism in ViT, our approach effectively captures both inter-beat and intra-beat dependencies, leading to more robust and accurate ECG reconstruction. Experimental results demonstrate that our method consistently outperforms existing 1D convolution-based approaches, achieving up to 29% reduction in PRD and 15% reduction in RMSE. The proposed approach also produces improvements in other evaluation metrics, highlighting its robustness and effectiveness in reconstructing ECG signals. Furthermore, to ensure a clinically relevant evaluation, we introduce new performance metrics, including QRS area error, PR interval error, RT interval error, and RT amplitude difference error. Our findings suggest that integrating a four-channel signal image representation with the self-attention mechanism of ViT enables more effective extraction of informative PPG features and improved modeling of beat-to-beat variations for PPG-to-ECG mapping. Beyond demonstrating the potential of PPG as a viable alternative for heart activity monitoring, our approach opens new avenues for cyclic signal analysis and prediction.

eess.IV↗

arXiv2025

Characterization of phospholipid-cholesterol bilayers as self-assembled amphiphile block polymers that contain headgroups

Cholesterol is known to modulate the structure and function of biological membranes. In this study, we use self-consistent field theory (SCFT) to investigate phospholipid/cholesterol bilayer membranes modeled with two types of diblock copolymers. These copolymer-based bilayers serve as biomimetic platforms with applications in areas such as drug delivery. Our simulations identify a minimum free energy configuration characterized by phospholipid tails tilted relative to the membrane normal. The model quantitatively captures the well-known area condensation effect as cholesterol concentration increases, along with membrane thickening and reduced tilt angle. Thermodynamically, we observe a linear dependence between cholesterol's chemical potential and its concentration within the 37-50% range, consistent with experimental results. Additionally, we analyze the effects of block copolymer length and headgroup interactions on bilayer structure. Interactions between phospholipid headgroups and the solvent emerge as the most influential. This work provides a theoretical framework for understanding cholesterol's regulatory role in membrane structure and mechanics.

cond-mat.soft↗