{
  "id": 18107848,
  "title": "2D U-NET Deep Learning Architecture for Atherosclerotic Lesion Segmentation and Quantification",
  "url": "https://urgent.news/2026/11/04/2d-u-net-deep-learning-architecture-for-atherosclerotic-lesion",
  "topic": "science",
  "section": "Science",
  "published": "2026-11-04T00:00:00.000Z",
  "source": {
    "name": "bioRxiv",
    "slug": "biorxiv",
    "url": "https://www.biorxiv.org/content/10.64898/2026.10.31.763364v1?rss=1"
  },
  "original_language": "en",
  "account": "Researchers have developed a deep learning model utilizing the 2D U-NET architecture to accurately segment and quantify atherosclerotic lesions in mouse aortic root cross-sections. This automated process significantly outperforms manual measurement in terms of speed and precision. Aortic cross-sections were prepared from genetically diverse F2 mice on a Western diet and stained with Oil Red O and hematoxylin, capturing images for analysis. Manual segmentation was performed on 2553 images using Zeiss AxioVision, which were divided into training, validation, and testing sets. When tested on unseen images, the model showed exceptional performance marked by a high F1 score of 0.82, Jaccard score of 0.72, recall of 0.80, precision of 0.87, and a near-perfect correlation coefficient of 0.98. This represents a substantial reduction in measurement time, cutting down from around 5 minutes per image to just three seconds. This new 2D U-NET model offers a promising tool for swift and precise quantification of atherosclerotic lesion sizes, streamlining the process for future research.",
  "summary": "Mice are commonly used for experimental atherosclerosis research, and a common procedure involves morphometric analysis of atherosclerotic lesions on Oil Red O-stained cross-sections of the aortic root. However, manual measurement of atherosclerotic lesion sizes on numerous histological sections is tedious and time-consuming. Here, we developed a deep learning model based on convolutional neural…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}