Searcharxiv⌕ Search

arXiv subjects

Xinghao Yan

Publications and source records attributed to Xinghao Yan.

5 recordsLinked to original sources

Reference Coordinates, Output Perturbations, and Information Loss in EEG Decoding

Electroencephalography (EEG) decoders can respond to reference changes that preserve all relative-potential information. We use established measurement-operator theory to distinguish coordinate sensitivity, additional output-channel perturbations, and electrode loss. Exact pseudoinverse alignment supplies a consistency control; measurement-operator canonicalization (MOC) denotes a graph-Tikhonov estimator. The broader evaluation covers three public motor-imagery datasets and four decoders. The primary EEGNet comparison on Cho2017 and PhysioNet uses three paired training seeds, three shared noise realizations, and six front ends, with identical CAR training inputs sharing checkpoints. At 10 dB output perturbation, MOC-minus-raw disagreement was -0.144 and -0.107, while balanced-accuracy differences were 0.044 and 0.050, respectively; these four contrasts passed the retained Holm correction. MOC also reduced disagreement relative to pseudoinversion across all three seeds in both cohorts. However, comparison with fixed graph smoothing after pseudoinversion did not establish an additional MOC benefit. Preserving zero reference rows changed raw disagreement by less than 0.001 in magnitude; inverse-method predictions were unchanged. For canonical front ends, cross-reference disagreement was close to the reference obtained from independent noise within the same operator. Controlled weak-mode reconstruction and equal-rank electrode masks exposed separate stability and information-loss effects. The results locate the complete-reference gains within spatial processing under the specified stress model, while requiring decoding accuracy alongside consistency to assess practical utility.

eess.SP↗

Raysemble: Metric 3D Bone Reconstruction from a Single X-ray

Raysemble reconstructs eight lumbar and pelvic bones from a single X-ray by separating shape and placement. Each 3D query samples regional and global features at its image projection. A shared decoder predicts normalized bone shapes. Predicted depth and camera geometry determine 3D centers and scales for resampling these shapes onto a common grid in millimeters. Evaluation uses 23 held-out patients with 43 CT scans, each generating one simulated anteroposterior radiograph. Without rigid alignment to CT,Raysemble leads 15 evaluated methods, averaging 65.24% Dice, 9.09 mm HD95, and 3.32 mm ASSD over three random seeds. With identical inputs, it improves Dice over VolumeNeRF by 5.86 percentage points.

cs.CV↗

Branch Geometry and Finite-Radius Sensitivity of Hard-ReLU Training

Outer-learning algorithms use infinitesimal sensitivities to propose finite changes to initialization or training parameters. For hard-ReLU training, the derivative of the finite program and the derivative of its flow limit do not by themselves specify the response at a chosen radius. We characterize the intervening regime in which the perturbation radius is proportional to the GD step. Integer event rounding then survives at leading order: smooth Euler bias shifts each discrete phase, and upstream rounding moves downstream branch boundaries. We derive the crossing indices and a uniform endpoint expansion for finitely many separated transverse events in piecewise-$C^2$ dynamics, away from recursive phase boundaries. In contractive affine regions, an explicit remainder and complete branch verification certify finite candidate comparisons. Scalar phase frequencies and a coupled feedback ablation test the mechanism; frozen nonlinear-network experiments show radius-dependent prediction accuracy, including incomplete branch matches and failed-word tails. Together with local AD and uniform flow consistency, the result identifies sufficient response regimes: differentiating training is a choice of perturbation resolution as well as a choice of derivative.

cs.LG↗

Opportunistic Bone-Loss Screening from Routine Knee Radiographs Using a Multi-Task Deep Learning Framework with Sensitivity-Constrained Threshold Optimization

Background: Osteoporosis and osteopenia are often undiagnosed until fragility fractures occur. Dual-energy X-ray absorptiometry (DXA) is the reference standard for bone mineral density (BMD) assessment, but access remains limited. Knee radiographs are obtained at high volume for osteoarthritis evaluation and may offer an opportunity for opportunistic bone-loss screening. Objective: To develop and evaluate a multi-task deep learning system for opportunistic bone-loss screening from routine knee radiographs without additional imaging or patient visits. Methods: We developed STR-Net, a multi-task framework for single-channel grayscale knee radiographs. The model includes a shared backbone, global average pooling feature aggregation, a shared neck, and a task-aware representation routing module connected to three task-specific heads: binary screening (Normal vs. Bone Loss), severity sub-classification (Osteopenia vs. Osteoporosis), and weakly coupled T-score regression with optional clinical variables. A sensitivity-constrained threshold optimization strategy (minimum sensitivity >= 0.86) was applied. The dataset included 1,570 knee radiographs, split at the patient level into training (n=1,120), validation (n=226), and test (n=224) sets. Results: On the held-out test set, STR-Net achieved an AUROC of 0.933, sensitivity of 0.904, specificity of 0.773, and AUPRC of 0.956 for binary screening. Severity sub-classification achieved an AUROC of 0.898. The T-score regression branch showed a Pearson correlation of 0.801 with DXA-measured T-scores in a pilot subset (n=31), with MAE of 0.279 and RMSE of 0.347. Conclusions: STR-Net enables single-pass bone-loss screening, severity stratification, and quantitative T-score estimation from routine knee radiographs. Prospective clinical validation is needed before deployment.

cs.CV↗

AGE-Net: Spectral--Spatial Fusion and Anatomical Graph Reasoning with Evidential Ordinal Regression for Knee Osteoarthritis Grading

Automated Kellgren--Lawrence (KL) grading from knee radiographs is challenging due to subtle structural changes, long-range anatomical dependencies, and ambiguity near grade boundaries. We propose AGE-Net, a ConvNeXt-based framework that integrates Spectral--Spatial Fusion (SSF), Anatomical Graph Reasoning (AGR), and Differential Refinement (DFR). To capture predictive uncertainty and preserve label ordinality, AGE-Net employs a Normal-Inverse-Gamma (NIG) evidential regression head and a pairwise ordinal ranking constraint. On a knee KL dataset, AGE-Net achieves a quadratic weighted kappa (QWK) of 0.9017 +/- 0.0045 and a mean squared error (MSE) of 0.2349 +/- 0.0028 over three random seeds, outperforming strong CNN baselines and showing consistent gains in ablation studies. We further outline evaluations of uncertainty quality, robustness, and explainability, with additional experimental figures to be included in the full manuscript.

cs.CV↗