{
  "id": 17537763,
  "title": "MiniMAP: An automatic pipeline for paediatric lower limb musculoskeletal model generation",
  "url": "https://urgent.news/2026/10/31/minimap-an-automatic-pipeline-for-paediatric-lower-limb",
  "topic": "science",
  "section": "Science",
  "published": "2026-10-31T00:00:00.000Z",
  "source": {
    "name": "bioRxiv",
    "slug": "biorxiv",
    "url": "https://www.biorxiv.org/content/10.64898/2026.10.26.761767v1?rss=1"
  },
  "original_language": "en",
  "account": "The research team has developed a new automated pipeline called MiniMAP for creating pediatric lower limb musculoskeletal models. Generating these models can be challenging due to a balance between data availability, accuracy, and computation time. However, MiniMAP utilizes statistical shape models and articulated shape models to address these issues.\n\nMiniMAP generates bone geometries for use in musculoskeletal modeling based on demographic factors such as age, height, mass, and sex, linear bone measurements like bone widths and lengths, and 12 skin surface landmarks. These landmarks include the left/right ASIS, PSIS, medial/lateral epicondyles, and medial/lateral malleoli.\n\nTo account for skin padding - the distance between the bone and skin surface - the researchers created a random forest algorithm for predicting skin padding for these 12 landmarks. The study assessed the model prediction accuracy using a leave-one-out analysis, examining landmark errors, bone surface errors, and clinical bone measurement errors (both linear measurements and angular values).\n\nThe study involved motion capture and MRI data from two pediatric test cases. Skin padding values varied significantly, ranging from 3.4mm at the lateral malleolus to 25.9mm at the PSIS. The random forest algorithm proved most effective in predicting skin padding values, with an average root mean square error (RMSE) of 4.68mm.\n\nThe articulated shape model accurately predicted bone geometries from skin surface landmarks, with average bone surface root mean square errors (RMSEs) of 2.64 ± 0.99mm, 1.91 ± 0.59mm, and 1.69 ± 0.56mm for the pelvis, femora, and tibiae/fibulae, respectively. In the two unseen test cases, the average bone surface errors ranged from 1.64 ± 1.2mm to 3.41 ± 3.1mm.\n\nOverall, the MiniMAP study demonstrates the accuracy of this automated pipeline in generating custom pediatric musculoskeletal models rapidly.",
  "summary": "The generation of paediatric musculoskeletal models often requires compromise between data availability, accuracy, and computation time. Statistical shape models allow for rapid generation of bone geometries for use in musculoskeletal modelling. An articulated shape model allows for movement at the joints during optimisation to better fit to experimental data. Here we present a methodology for…",
  "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."
}