Skip to main content
Search

Capital Medical University

9 related articles

Subscribe to updates
  1. arXiv

    Retinal cross-modal registration skips segmentation: MICRO benchmark and one-step OFS2Reg reach 0.784 success rate

    Cross-modal retinal image rigid registration has largely relied on a two-step pipeline that segments vessels first and detects keypoints second, so registration quality is capped by segmentation accuracy. The MICRO benchmark gathers 1,365 cross-modal retinal image pairs spanning preoperative, intraoperative and postoperative surgery phases, each with expert-annotated control points. Built on that benchmark, the one-step OFS2Reg constructs keypoint topology constraints directly through a frequency-guided structure preservation descriptor and cross-modal vessel structure similarity learning, reaching a 0.784 success rate and 5.08-pixel RMSE on the MICRO-pre subset.

  2. medRxiv

    Fetal ultrasound screening learns from scarce labels: RadarMAE's radar-style masking holds cross-hospital metric drops to 0.04

    First-trimester ultrasound images for Down syndrome screening are low-resolution and structurally variable, and confirmed rare cases are scarce, so standard self-supervised pretraining struggles. RadarMAE instead masks alternating concentric rings and angular sectors, a radar-like pattern that forces the network to learn the continuous curvature and elongated shapes of craniofacial structures, reaching AUC 0.99 and 97% accuracy on an internal cohort. With domain-adversarial adaptation, the model calibrates on unlabeled images from four external hospitals and limits the drop in key metrics to 0.04 or less.

  3. medRxiv

    Undiagnosed hypertension screening drops missed cases from 1,237 to 729 with positive-unlabeled learning

    Treating undiagnosed hypertension screening as a positive-unlabeled problem in 43,105 Chinese community adults reached a sensitivity of 0.817 and 729 false negatives in an independent test set, 41.1% fewer than standard XGBoost.

  4. medRxiv

    A protective effect in observational data may be all bias: new metric attributes a 16.9% mortality drop to systematic error

    Observational causal estimates gain a continuous reporting channel: the Bias Attribution Fraction (BAF) writes the share of an observed log relative risk attributable to systematic bias as a number between 0 and 1, with a 95% credible interval. Across 1,920,000 simulated repetitions, the calibrated P-value alone declared 36.02% of truly bias-dominated repetitions usable, adding the BAF point estimate cut that to 16.48%, and requiring the whole credible interval below 0.5 cut it to 10.16%. In a MIMIC IV beta-blocker target trial emulation, the 16.9% one-year mortality reduction associated with reaching target dose disappeared after calibration, with BAF 0.875 and a verdict of not usable as effect evidence.

  5. The FASEB Journal

    Integrating Metabolomics, Mendelian Randomization, and Machine Learning, a Study Flags Phenylalanine and Its Transporter SLC6A14 as Candidate Diagnostic and Therapeutic Targets in Pancreatic Cancer

    Integrating plasma metabolomics, Mendelian randomization, and machine learning, this study identified phenylalanine as causally associated with pancreatic cancer among 55 plasma metabolites (IVW OR = 1.641, 95% CI 1.052–2.562, p = 0.029), derived eight related differentially expressed genes, built a random forest diagnostic model from 113 combinations of 12 algorithms (training AUC 0.994; validation AUCs 0.918, 0.983, 0.923), used SHAP to rank SLC6A14 as the top feature, and combined single-cell sequencing, simulated gene knockout, molecular docking, and molecular dynamics to suggest genistein binds SLC6A14 stably, with RT-qPCR confirming high expression of the five model genes in a BxPC-3 versus HPDE6-C7 cell pair.

  6. arXiv

    NeuroSymb-MRG generates radiology reports via differentiable abductive reasoning and active uncertainty minimization, raising BLEU-1 to 0.602 on IU X-ray and 0.487 on MIMIC-CXR

    The work presents NeuroSymb-MRG, a framework that maps image features to probabilistic clinical concepts, composes multi-hop abductive reasoning chains through a differentiable logic layer (product t-norm AND, probabilistic sum OR, learnable gating α), decodes those chains into roughly 120 clause templates augmented with retrieved evidence and constrained LLM paraphrasing, and drives clinician-in-the-loop review with active sampling based on rule-level predictive entropy (5 MC-dropout passes) plus k-center diversity (k=16 per round); on IU X-ray and MIMIC-CXR it improves BLEU-1 through BLEU-4, ROUGE-L and METEOR over the listed representative baselines, for example IU X-ray BLEU-1 of 0.602 and MIMIC-CXR BLEU-1 of 0.487.

  7. Artificial Intelligence Empowering Spinal Deformity Surgery: From Clinical Assessment to Decision Integration

    From a clinical-expert perspective, this article reviews the progress and value of artificial intelligence, especially deep learning, in core links of spinal deformity surgery such as imaging parameter measurement, surgical risk prediction, and individualized plan formulation, analyzes bottlenecks in technology promotion, and looks ahead to a "human-machine co-intelligence" direction, arguing that integrating AI with clinical experience can move the discipline from "standardized treatment" toward "individualized precision treatment" and build an intelligent diagnosis and treatment system.

  8. Minimal Clinically Important Difference in TETRAS Score for Essential Tremor

    Using data from the TRANQUIL multicenter randomized controlled trial, this study estimated minimal clinically important differences (MCIDs) for the modified activities of daily living (mADL) and mADL11 scales of TETRAS in essential tremor via anchor-based approaches (CGI-I and PGI-I) and ROC analyses, recommending patient-report-based MCIDs of -6.2 for mADL and -4.1 for mADL11.

  9. Non-invasive tests for early-stage liver fibrosis: current advances and challenges

    This review systematically evaluates established and emerging non-invasive tests for detecting early-stage liver fibrosis (F1–F2), spanning serum biomarkers, molecular imaging probes, AI-based analysis of conventional imaging, alternative biofluids such as urine, exhaled breath and saliva, gut microbiota-derived biomarkers, and multiomics-integrated models, concluding that these approaches show diagnostic promise but remain constrained by limited validation, absent standardization, and unclear integration into clinical pathways, and proposing a tiered diagnostic framework as a near-term implementation route.

You’re all caught up