arXiv subjects

Bora Yimenicioglu

Publications and source records attributed to Bora Yimenicioglu.

5 recordsLinked to original sources

arXiv2026

FlowMorph: Physics-Consistent Self-Supervision for Label-Free Single-Cell Mechanics in Microfluidic Videos

Mechanical properties of red blood cells (RBCs) are promising biomarkers for hematologic and systemic disease, motivating microfluidic assays that probe deformability at throughputs of $10^3$--$10^6$ cells per experiment. However, existing pipelines rely on supervised segmentation or hand-crafted kymographs and rarely encode the laminar Stokes-flow physics that governs RBC shape evolution. We introduce FlowMorph, a physics-consistent self-supervised framework that learns a label-free scalar mechanics proxy $k$ for each tracked RBC from short brightfield microfluidic videos. FlowMorph models each cell by a low-dimensional parametric contour, advances boundary points through a differentiable ''capsule-in-flow'' combining laminar advection and curvature-regularized elastic relaxation, and optimizes a loss coupling silhouette overlap, intra-cellular flow agreement, area conservation, wall constraints, and temporal smoothness, using only automatically derived silhouettes and optical flow. Across four public RBC microfluidic datasets, FlowMorph achieves a mean silhouette IoU of $0.905$ on physics-rich videos with provided velocity fields and markedly improves area conservation and wall violations over purely data-driven baselines. On $\sim 1.5\times 10^5$ centered sequences, the scalar $k$ alone separates tank-treading from flipping dynamics with an AUC of $0.863$. Using only $200$ real-time deformability cytometry (RT-DC) events for calibration, a monotone map $E=g(k)$ predicts apparent Young's modulus with a mean absolute error of $0.118$\,MPa on $600$ held-out cells and degrades gracefully under shifts in channel geometry, optics, and frame rate.

cs.CV↗

arXiv2025

Adaptive EEG-based stroke diagnosis with a GRU-TCN classifier and deep Q-learning thresholding

Rapid triage of suspected stroke needs accurate, bedside-deployable tools; EEG is promising but underused at first contact. We present an adaptive multitask EEG classifier that converts 32-channel signals to power spectral density features (Welch), uses a recurrent-convolutional network (GRU-TCN) to predict stroke type (healthy, ischemic, hemorrhagic), hemispheric lateralization, and severity, and applies a deep Q-network (DQN) to tune decision thresholds in real time. Using a patient-wise split of the UCLH Stroke EIT/EEG data set (44 recordings; about 26 acute stroke, 10 controls), the primary outcome was stroke-type performance; secondary outcomes were severity and lateralization. The baseline GRU-TCN reached 89.3% accuracy (F1 92.8%) for stroke type, about 96.9% (F1 95.9%) for severity, and about 96.7% (F1 97.4%) for lateralization. With DQN threshold adaptation, stroke-type accuracy increased to about 98.0% (F1 97.7%). We also tested robustness on an independent, low-density EEG cohort (ZJU4H) and report paired patient-level statistics. Analyses follow STARD 2015 guidance for diagnostic accuracy studies (index test: GRU-TCN+DQN; reference standard: radiology/clinical diagnosis; patient-wise evaluation). Adaptive thresholding shifts the operating point to clinically preferred sensitivity-specificity trade-offs, while integrated scalp-map and spectral visualizations support interpretability.

cs.LG↗

arXiv2025

RareGraph-Synth: Knowledge-Guided Diffusion Models for Generating Privacy-Preserving Synthetic Patient Trajectories in Ultra-Rare Diseases

We propose RareGraph-Synth, a knowledge-guided, continuous-time diffusion framework that generates realistic yet privacy-preserving synthetic electronic-health-record (EHR) trajectories for ultra-rare diseases. RareGraph-Synth unifies five public resources: Orphanet/Orphadata, the Human Phenotype Ontology (HPO), the GARD rare-disease KG, PrimeKG, and the FDA Adverse Event Reporting System (FAERS) into a heterogeneous knowledge graph comprising approximately 8 M typed edges. Meta-path scores extracted from this 8-million-edge KG modulate the per-token noise schedule in the forward stochastic differential equation, steering generation toward biologically plausible lab-medication-adverse-event co-occurrences while retaining score-based diffusion model stability. The reverse denoiser then produces timestamped sequences of lab-code, medication-code, and adverse-event-flag triples that contain no protected health information. On simulated ultra-rare-disease cohorts, RareGraph-Synth lowers categorical Maximum Mean Discrepancy by 40 percent relative to an unguided diffusion baseline and by greater than 60 percent versus GAN counterparts, without sacrificing downstream predictive utility. A black-box membership-inference evaluation using the DOMIAS attacker yields AUROC approximately 0.53, well below the 0.55 safe-release threshold and substantially better than the approximately 0.61 plus or minus 0.03 observed for non-KG baselines, demonstrating strong resistance to re-identification. These results suggest that integrating biomedical knowledge graphs directly into diffusion noise schedules can simultaneously enhance fidelity and privacy, enabling safer data sharing for rare-disease research.

cs.LG↗

arXiv2025

TinyViT-Batten: Few-Shot Vision Transformer with Explainable Attention for Early Batten-Disease Detection on Pediatric MRI

Batten disease (neuronal ceroid lipofuscinosis) is a rare pediatric neurodegenerative disorder whose early MRI signs are subtle and often missed. We propose TinyViT-Batten, a few-shot Vision Transformer (ViT) framework to detect early Batten disease from pediatric brain MRI with limited training cases. We distill a large teacher ViT into a 5 M-parameter TinyViT and fine-tune it using metric-based few-shot learning (prototypical loss with 5-shot episodes). Our model achieves high accuracy (approximately 91%) and area under ROC of at least 0.95 on a multi-site dataset of 79 genetically confirmed Batten-disease MRIs (27 CLN3 from the Hochstein natural-history study, 32 CLN2 from an international longitudinal cohort, 12 early-manifestation CLN2 cases reported by Cokal et al., and 8 public Radiopaedia scans) together with 90 age-matched controls, outperforming a 3D-ResNet and Swin-Tiny baseline. We further integrate Gradient-weighted Class Activation Mapping (Grad-CAM) to highlight disease-relevant brain regions, enabling explainable predictions. The model's small size and strong performance (sensitivity greater than 90%, specificity approximately 90%) demonstrates a practical AI solution for early Batten disease detection.

cs.CV↗

arXiv2025

A Two-Feature Quantitative EEG Index of Pediatric Epilepsy Severity: External Pre-Validation on CHB-MIT and Roadmap to Dravet Cohorts

Objective biomarkers for staging pediatric epileptic encephalopathies are scarce. We revisited a large open repository -- the CHB-MIT Scalp EEG Database, 22 subjects aged 1.5-19 y recorded at 256 Hz under the 10-20 montage -- to derive and validate a compact quantitative index, DS-Qi = (theta/alpha)_posterior + (1 - wPLI_beta). The first term captures excess posterior slow-wave power, a recognized marker of impaired cortical maturation; the second employs the debiased weighted Phase-Lag Index to measure loss of beta-band synchrony, robust to volume conduction and small-sample bias. In 30-min awake, eyes-open segments, DS-Qi was 1.69 +/- 0.21 in epilepsy versus 1.23 +/- 0.17 in age-matched normative EEG (Cohen's d = 1.1, p < 0.001). A logistic model trained with 10 x 10-fold cross-validation yielded an AUC of 0.90 (95% CI 0.81-0.97) and optimal sensitivity/specificity of 86%/83% at DS-Qi = 1.46. Across multi-day recordings, test-retest reliability was ICC = 0.74, and higher DS-Qi correlated with greater seizure burden (rho = 0.58, p = 0.004). These results establish DS-Qi as a reproducible, single-number summary of electrophysiological severity that can be computed from short scalp EEG segments using only posterior and standard 10-20 electrodes.

q-bio.NC↗