Skip to main content
Search

Tehran University of Medical Sciences

4 related articles

Subscribe to updates
  1. bioRxiv

    Sparse autoencoder features get a ground-truth ruler: seed reproducibility is not concept alignment, and a five-seed consensus reaches 78–98%

    Sparse autoencoders (SAEs) are widely used to pull interpretable features from biological foundation-model embeddings, and reproducibility across random seeds has served as the trust test. On embeddings with known concepts, single SAE fits reproduced only 27–46% of their features yet covered most concepts, while a consensus over five fits raised reproducibility to 78–98% at single-fit purity. The consensus covered fewer lineages than single fits, and all SAEs missed weak cell states.

  2. 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.

  3. Machine Learning for Noninvasive Anemia Diagnosis: A Systematic Review Based on CRISP-DM

    Following PRISMA, this review searched PubMed, Web of Science, and Scopus (January 1, 2019 to March 27, 2025), included 58 of 1923 records, and used the CRISP-DM phases (problem understanding, data understanding, data preparation, modeling, evaluation, deployment) to organize machine learning approaches to noninvasive anemia detection and hemoglobin estimation, covering algorithms, data sources, acquisition sites, light sources, evaluation metrics, and deployment, alongside a PROBAST appraisal of risk of bias and applicability.

  4. Artificial intelligence in trigeminal neuralgia: trigeminal nerve segmentation and neurovascular conflict detection: a systematic review and meta-analysis

    This systematic review and meta-analysis pooled 5 studies covering 577 patients with confirmed trigeminal neuralgia to evaluate deep learning and machine learning models for automated trigeminal nerve segmentation and neurovascular conflict detection on MRI, finding a pooled sensitivity of 71% (95% CI: 65-76%), specificity of 92% (95% CI: 88-94%), and AUC of 0.91 (95% CI: 0.88-0.93), suggesting high diagnostic accuracy for AI models in this task.

You’re all caught up