{
  "abstract": "Deep learning is the state-of-the-art approach for bioimage segmentation. However, it presents a paradox regarding image resolution: counterintuitively, deep learning segmentation performance can improve with lower image resolutions. This phenomenon is particularly significant in microscopy, where high-resolution acquisitions come with substantial costs in throughput, storage requirements and potential photodamage. We systematically evaluate how image resolution impacts segmentation by training popular architectures on datasets downsampled to 6-50% of their original resolution, mimicking lower-magnification acquisitions. Compared with models trained on native-resolution images, segmentation accuracy either improves (by up to 25% of mean Intersection over Union (IoU)) or degrades minimally (< 5% of mean IoU) when using images downsampled by up to fourfold (25% of the original resolution). Downsampling proportionally increases information throughput while reducing storage requirements and inference time. These findings provide practical guidelines for creating efficient, sustainable and cost-effective bioimaging pipelines that reduce data and computing needs while optimising microscopy techniques.",
  "abstract_shown": true,
  "affiliations": [
    "AI-driven Optical Biology Laboratory, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa, Oeiras, Portugal.",
    "Bacterial Cell Biology Laboratory, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa, Oeiras, Portugal.",
    "AI-driven Optical Biology Laboratory, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa, Oeiras, Portugal. r.henriques@itqb.unl.pt.",
    "UCL Laboratory for Molecular Cell Biology, University College London, London, UK. r.henriques@itqb.unl.pt.",
    "AI-driven Optical Biology Laboratory, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa, Oeiras, Portugal. esti.gomezdemariscal@unl.pt.",
    "NOVA Institute for Medical Systems Biology (NIMSB), Universidade Nova de Lisboa, Lisboa, Portugal. esti.gomezdemariscal@unl.pt.",
    "iNOVA4Health, Programme in Translational Medicine, Lisboa, Portugal. esti.gomezdemariscal@unl.pt."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Mariana G Ferreira",
      "orcid": "0009-0002-2886-4612"
    },
    {
      "affs": [
        0
      ],
      "name": "Bruno M Saraiva",
      "orcid": "0000-0002-9151-5477"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "António D Brito",
      "orcid": "0009-0001-1769-2627"
    },
    {
      "affs": [
        1
      ],
      "name": "Mariana G Pinho",
      "orcid": "0000-0002-7132-8842"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Ricardo Henriques",
      "orcid": "0000-0002-2043-5234"
    },
    {
      "affs": [
        4,
        5,
        6
      ],
      "name": "Estibaliz Gómez-de-Mariscal",
      "orcid": "0000-0003-2082-3277"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8darq9crwy2qp.bib",
  "cited_by": 4,
  "doi": "10.1038/s41467-026-77930-1",
  "fulltext_url": "https://europepmc.org/articles/PMC13680607",
  "id": "8darq9crwy2qp",
  "issns": [
    "2041-1723"
  ],
  "landing_url": "https://europepmc.org/article/MED/42897196",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1304|Cell Image Analysis Techniques"
    ]
  ],
  "openalex": "W7213546408",
  "pdf_url": "https://europepmc.org/articles/PMC13680607?pdf=render",
  "pmcid": "PMC13680607",
  "pmid": "42897196",
  "published": "2026-09-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8darq9crwy2qp.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:41Z",
      "native_id": "MED:42897196",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42897196"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1304|Cell Image Analysis Techniques",
      "subfield": "biophysics"
    }
  ],
  "title": "ReScale4DL: balancing pixel and contextual information for enhanced bioimage segmentation.",
  "title_text": "ReScale4DL: balancing pixel and contextual information for enhanced bioimage segmentation.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:19:41Z",
  "url": "https://research.draconitic.com/paper/8darq9crwy2qp",
  "venue": "Nature communications",
  "versions": []
}