arXiv subjects

Jianwei Zuo

Publications and source records attributed to Jianwei Zuo.

8 recordsLinked to original sources

arXiv2026

High-Fidelity 3D Geometric Reconstruction of Pelvic Organs from MRI: A Hybrid Deep Learning and Iterative Optimization Approach

Patient-specific 3D reconstruction of pelvic organ geometry from MRI is important for pelvic floor modeling and downstream patient-specific analysis. However, while previous studies have focused primarily on either image segmentation or downstream use of 3D models, the reconstruction of high-fidelity, high-quality geometries remains labor-intensive and poorly standardized. The study introduced a hybrid deformable shape modeling framework that integrates deep learning prediction with iterative optimization for the reconstruction of the bladder, uterus, and rectum. The framework consists of three core components: a geometry-aware multi-level deep learning architecture that preserves topological consistency of pelvic organs; a two-stage amortized optimization training strategy that balances global shape capture and local surface refinement; and a holistic synergy mechanism--where iterative optimization provides supervision for deep learning during the training phase, and during inference, deep learning rapidly predicts the global organ morphology, followed by iterative optimization to refine local surfaces and mesh quality. This framework demonstrated marked superiority in geometric fidelity than current mainstream deep learning-based organ reconstruction models. For individual anatomical structures, the reconstructed 3D geometries for the bladder, rectum, and uterus achieved significantly lower Chamfer Distance values and higher Dice Similarity Coefficient scores. In addition, while maintaining high computational efficiency, the proposed architecture yielded superior overall volumetric mesh quality. At the patient level, the framework achieved higher mean values for the 10 worst elements for both minSICN and minSIGE compared to traditional geometric post-processing algorithms.

cs.CV↗

arXiv2026

Evaluating Deep Surrogate Models for Knee Joint Contact Mechanics Under Input-Limited Conditions

Background and Objective: Accurate surrogate modeling of knee joint contact mechanics is important for reconstructing stress distributions and identifying risk-relevant regions, yet the relative suitability of different modeling paradigms under practically relevant input-limited conditions remains unclear. Methods: Nine male soccer players performed 90{\deg} change-of-direction trials. Finite element simulations driven by subject-specific joint posture and reaction forces were converted into graph-structured samples. Five surrogate architectures representing local diffusion, history-context enhancement, hierarchical multi-scale modeling, explicit global interaction, and local-global hybridization were compared using three-fold cross-subject validation under full, pose-corrupted, load-corrupted, and minimal-input conditions. Performance was evaluated using full-field error, high-stress error, high-risk region overlap, and hotspot localization metrics. Results: The hybrid model achieved the best overall performance under full inputs and remained the most robust under pose- and load-corrupted conditions. Under minimal inputs, no single model dominated all metrics: the history-context model yielded lower overall and high-stress errors, the hybrid model better preserved high-risk region reconstruction, and the hierarchical model showed an advantage in hotspot localization. Conclusion: Evaluation of surrogate models for knee joint contact mechanics should shift from accuracy comparisons under ideal inputs to a comprehensive assessment of the preservation of risk-relevant information under realistic input constraints. Although the local-global hybrid model showed the best overall robustness, the optimal model under minimal-input conditions remained task-dependent.

q-bio.QM↗

arXiv2026

Characterizing Long-Range Dependencies in Knee Joint Contact Mechanics: A Comparison of Topology Diffusion, Global Routing, and Hybrid Graph Neural Networks

Finite element analysis of knee joint contact mechanics is computationally expensive, which has motivated the development of graph neural network surrogate models. However, effectively representing long-range dependencies in joint mechanical responses remains challenging. This study systematically compared topology diffusion, global routing, and their hybridization for surrogate modeling of knee joint contact mechanics. Using kinematic and force data from nine soccer players performing change-of-direction maneuvers, finite element simulations were used to generate graph-structured samples for training and evaluation under a grouped three-fold cross-subject evaluation framework. Five architectures were compared: standard MeshGraphNet, hierarchical MeshGraphNet, a routing-only transformer, a topology-biased routing transformer, and a hybrid model. The hybrid model achieved the best overall performance, yielding the lowest full-field error and peak stress error, together with the highest spatial agreement for high-risk regions. Among the non-hybrid models, the standard topology-diffusion model performed best overall, whereas routing-only strategies were less effective. These findings indicate that topology diffusion provides a robust basis for surrogate modeling of knee joint contact mechanics within the present benchmark, while the addition of global routing can further improve reconstruction of clinically relevant high-stress patterns.

q-bio.QM↗

arXiv2026

Towards Structure-Aware Surrogate Modeling: Explicit Region Interaction Improves Knee Contact Stress Prediction

Knee contact-stress hotspots are closely linked to meniscal/cartilage injury risk. Still, high-fidelity subject-specific FEA is too computationally expensive for large-cohort, multi-condition, near-real-time use. Existing MeshGraphNet-style surrogates mainly rely on stacked local message passing, which is often insufficient for modeling long-range dependencies and limits interpretability. This study benchmarked a deep-stacked baseline model against three explicit region-interaction architectures. Using a 90{\deg} change-of-direction task and a strict cross-subject evaluation framework, we assessed whole-field error, peak stress fidelity, and hotspot spatial consistency under matched computational budgets. Region-interaction models significantly reduced whole-field nodal stress errors compared to the purely stacked baseline. Crucially, they achieved markedly higher accuracy in reconstructing the high-stress tail and demonstrated superior spatial consistency and temporal robustness in localizing high-risk stress hotspots. Explicit region-level interaction provides a more structure-aligned surrogate modeling paradigm for knee contact mechanics and yields stronger risk-relevant stress phenotype recovery under comparable computational budgets, while supporting more interpretable injury-risk assessment.

q-bio.TO↗

arXiv2026

Disentangling History and Propagation Dependencies in Cross-Subject Knee Contact Stress Prediction Using a Shared MeshGraphNet Backbone

Background:Subject-specific finite element analysis accurately characterizes knee joint mechanics but is computationally expensive. Deep surrogate models provide a rapid alternative, yet their generalization across subjects under limited pose and load inputs remains unclear. It remains unclear whether the dominant source of prediction uncertainty arises from temporal history dependence or spatial propagation dependence. Methods:To disentangle these factors, we employed a shared MGN backbone with a fixed mesh topology. A dataset of running trials from nine subjects was constructed using an OpenSim-FEBio workflow. We developed four model variants to isolate specific dependencies: (1) a baseline MGN; (2) CT-MGN, incorporating a Control Transformer to encode short-horizon history; (3) MsgModMGN, applying state-conditioned modulation to message passing for adaptive propagation; (4) CT-MsgModMGN, combining both mechanisms. Models were evaluated using a rigorous grouped 3-fold cross-validation on unseen subjects.Results:The models incorporating history encoding significantly outperformed the baseline MGN and MsgModMGN in global accuracy and spatial consistency. Crucially, the CT module effectively mitigated the peak-shaving defect common in deep surrogates, significantly reducing peak stress prediction errors. In contrast, the spatial propagation modulation alone yielded no significant improvement over the baseline, and combining it with CT provided no additional benefit.Conclusion:Temporal history dependence, rather than spatial propagation modulation, is the primary driver of prediction uncertainty in cross-subject knee contact mechanics. Explicitly encoding short-horizon driver sequences enables the surrogate model to recover implicit phase information, thereby achieving superior fidelity in peak-stress capture and high-risk localization compared to purely state-based approaches.

q-bio.QM↗

arXiv2025

GNN-Based Deep Surrogate Modeling of Knee Contact Mechanics: Generalizing Neuromuscular Control Patterns Across Subjects

Background: Accumulation of abnormal contact stress is a primary biomechanical driver of acute meniscal tears and chronic osteoarthritis. While Finite Element Analysis (FEA) provides the necessary fidelity to quantify these injury-inducing loads, its high computational cost precludes clinical utility. Emerging deep surrogate models promise real-time assessment but suffer a critical blind spot: they predominantly focus on learning anatomical variations, largely overlooking the neuromuscular control patterns. These dynamic, subject-specific motor strategies fundamentally dictate potentially injurious stress distributions inside the knee. Methods: This study investigates the generalization capability of the topology-aware MeshGraphNet regarding cross-subject neuromuscular control patterns under fixed anatomical conditions. We constructed a dataset using gait data from nine subjects via an OpenSim-FEBio co-simulation platform. The MGN was compared against a structure-agnostic Node-wise MLP using a rigorous grouped 3-fold cross-validation on unseen subjects. Results: The MGN demonstrated superior fidelity, achieving a correlation of 0.94 with ground truth (vs. 0.88 for MLP). In contrast to the MLP, which exhibited the "peak shaving" defect common in deep learning, MGN significantly reduced peak-stress prediction errors and achieved higher spatial overlap in high-risk regions. This indicates that MGN effectively captured the non-local force-transmission pathways unique to each subject's movement strategy. Conclusion: By mimicking the propagation of physical stress through message passing, MGN successfully decodes the heterogeneity of human neuromuscular control, even under fixed anatomy. This establishes GNNs as robust clinical tools capable of identifying functional injury risks that are invisible to purely geometry-based surrogate models.

q-bio.QM↗

arXiv2023

Pelvic floor MRI segmentation based on semi-supervised deep learning

The semantic segmentation of pelvic organs via MRI has important clinical significance. Recently, deep learning-enabled semantic segmentation has facilitated the three-dimensional geometric reconstruction of pelvic floor organs, providing clinicians with accurate and intuitive diagnostic results. However, the task of labeling pelvic floor MRI segmentation, typically performed by clinicians, is labor-intensive and costly, leading to a scarcity of labels. Insufficient segmentation labels limit the precise segmentation and reconstruction of pelvic floor organs. To address these issues, we propose a semi-supervised framework for pelvic organ segmentation. The implementation of this framework comprises two stages. In the first stage, it performs self-supervised pre-training using image restoration tasks. Subsequently, fine-tuning of the self-supervised model is performed, using labeled data to train the segmentation model. In the second stage, the self-supervised segmentation model is used to generate pseudo labels for unlabeled data. Ultimately, both labeled and unlabeled data are utilized in semi-supervised training. Upon evaluation, our method significantly enhances the performance in the semantic segmentation and geometric reconstruction of pelvic organs, Dice coefficient can increase by 2.65% averagely. Especially for organs that are difficult to segment, such as the uterus, the accuracy of semantic segmentation can be improved by up to 3.70%.

cs.CV↗

arXiv2023

Frequency Domain Decomposition Translation for Enhanced Medical Image Translation Using GANs

Medical Image-to-image translation is a key task in computer vision and generative artificial intelligence, and it is highly applicable to medical image analysis. GAN-based methods are the mainstream image translation methods, but they often ignore the variation and distribution of images in the frequency domain, or only take simple measures to align high-frequency information, which can lead to distortion and low quality of the generated images. To solve these problems, we propose a novel method called frequency domain decomposition translation (FDDT). This method decomposes the original image into a high-frequency component and a low-frequency component, with the high-frequency component containing the details and identity information, and the low-frequency component containing the style information. Next, the high-frequency and low-frequency components of the transformed image are aligned with the transformed results of the high-frequency and low-frequency components of the original image in the same frequency band in the spatial domain, thus preserving the identity information of the image while destroying as little stylistic information of the image as possible. We conduct extensive experiments on MRI images and natural images with FDDT and several mainstream baseline models, and we use four evaluation metrics to assess the quality of the generated images. Compared with the baseline models, optimally, FDDT can reduce Fréchet inception distance by up to 24.4%, structural similarity by up to 4.4%, peak signal-to-noise ratio by up to 5.8%, and mean squared error by up to 31%. Compared with the previous method, optimally, FDDT can reduce Fréchet inception distance by up to 23.7%, structural similarity by up to 1.8%, peak signal-to-noise ratio by up to 6.8%, and mean squared error by up to 31.6%.

eess.IV↗