Skip to main content
Search

University of Southern Denmark

5 related articles

Subscribe to updates
  1. bioRxiv

    Skip the cell-type labels: NetMap reads regulatory networks and cell identity together from mixed single-cell data

    Regulatory network inference no longer needs cell types called first. Earlier pipelines clustered cells, annotated types with marker genes, then inferred one network per cluster, so clustering and annotation errors propagated into the network. NetMap infers a gene regulatory network per cell before any clustering, uses GradientShap to attribute network edges to input genes, and reaches clustering scores of 1.0, 0.99 and 0.99 across three PBMC multiome evaluation cases.

  2. arXiv

    Ranking positions by chat structure lets auditors explain 5% of tokens and keep nearly all threat-detection success

    Across about 4.7 million natural language autoencoder (NLA) explanations on four models and four auditing datasets, the study compares thirteen position-scoring signals computable in a single forward pass against a ranker trained only on chat structure, finding that chat structure beats the best individual signal in twelve of fourteen model-dataset cells, that explaining just 5% of positions retains nearly all of the success rate from explaining every position on three of four datasets, and that pretrained verbalizers recover words a fine-tuned model learned to conceal without additional verbalizer training.

  3. medRxiv

    Uncoded Clinical Features from Multilingual Electronic Health Records in Catalonia: Development and Validation Study

    This study deployed the 3.8B-parameter open-weight small language model Phi4-mini (via Ollama) within an institutional firewall, combined with deterministic regular expression post-processing, to extract six uncoded urinary tract infection clinical features (fever, nitrites, leukocytes, lumbar pain, abdominal pain, and haematuria) from 15,498 Catalan/Spanish bilingual MEAP primary care narratives in the SIDIAP database in Catalonia, achieving 93.8% accuracy, 96.6% specificity, and 83.6% sensitivity in a double-blind clinician gold standard validation of 60 real patient records, and 87.2% accuracy, 99.5% specificity, and 99.2% positive predictive value in adversarial synthetic stress-testing of 720 notes, with no patient data leaving institutional servers.

  4. bioRxiv

    RSAUNet: A Hybrid Residual–Swin Transformer Design with Attention for Prostate Cancer Segmentation

    The study proposes RSAUNet, a deep learning architecture that combines residual convolutional blocks, Swin Transformer blocks, and attention mechanisms inside a U-Net backbone for MRI prostate cancer segmentation, reporting a Dice coefficient of 0.998 and a Jaccard index (IoU) of 0.965 on a public Kaggle prostate annotation dataset, together with an ablation study tracking loss, accuracy, Dice, and mean IoU as each component is added.

  5. FAR-POLYP-SEG: A Prospective Single-Center Colonoscopy Dataset for Colorectal Polyp Segmentation with Patient-Level Metadata and Baseline Cross-Dataset Evaluation

    This work prospectively collected 8,181 frames from 455 patients during routine colonoscopy at Farhikhtegan Hospital, Tehran, Iran, between February and December 2025 (432 polyp-positive frames with expert pixel-level segmentation masks and 7,749 normal-mucosa frames), linked patient-level metadata (age, sex, colonoscopy indication, BBPS score, and procedure duration) to every case, and trained and evaluated six segmentation architectures under one standardized protocol with patient-grouped five-fold cross-validation, finding that PraNet reached the highest internal Dice (0.755) and nnU-Net the highest internal IoU (0.665) and pixel accuracy, yet gated false-positive rates on normal mucosa ranged from 24.9% (YOLOv11m-seg) to 59.

You’re all caught up