{
  "abstract": "Introduction: Plant-cell measurements require adjacent cells to remain separated, yet few-shot segmentation is usually assessed mainly by foreground overlap.\n\nMethods: We developed domain-aware topology prompt adaptation (DTPA), which trains a small topology head over a frozen microscopy-specific Segment Anything backbone. We evaluated matched 10-shot segmentation on a leakage-free RiceCell split, conducted a secondary eight-image audit, and assessed label-free routing and selective correction on locked external tests.\n\nResults: DTPA improved boundary F1 and reduced cell-count error relative to ConvNeXt, while reducing Dice. The boundary advantage persisted across one- to five-pixel tolerances and against two matched instance baselines. The secondary audit linked this trade-off to improved cell-count and typical-cell-area fidelity, but not to every image-derived measurement. The label-free router reduced severe under-counting on a locked PlantSeg root test. Selective correction was less reliable under the tested tissue shifts: 14 of 45 accepted Ovules retries were harmful, and the only accepted floral-meristem retry was harmful.\n\nDiscussion: Topology-aware prompting and routing are computational tools for plant microscopy, not evidence of biological discovery or universal model superiority. A correction-abstention rule derived after the external audit is only a deployment proposal and requires prospective target-domain validation.",
  "abstract_shown": true,
  "affiliations": [
    "School of Big Data and Artificial Intelligence, Nanning College of Technology"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Gaixing Wei"
    },
    {
      "affs": [
        0
      ],
      "name": "Da Zeng"
    },
    {
      "affs": [
        0
      ],
      "name": "Shenglin Qin"
    },
    {
      "affs": [
        0
      ],
      "name": "Dezhen Zeng"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dzf6e4dwyyk98.bib",
  "cited_by": 0,
  "doi": "10.3389/fpls.2026.1950986",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13710281/",
  "id": "dzf6e4dwyyk98",
  "issns": [
    "1664-462X"
  ],
  "landing_url": "https://www.frontiersin.org/articles/10.3389/fpls.2026.1950986/full",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Original Research"
    ],
    [
      "openalex",
      "1304|Cell Image Analysis Techniques"
    ]
  ],
  "openalex": "W7221704958",
  "pdf_url": "https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2026.1950986/pdf",
  "pmcid": "PMC13710281",
  "pmid": "42947817",
  "published": "2026-10-13",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/dzf6e4dwyyk98.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:25Z",
      "native_id": "10.3389/fpls.2026.1950986",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fpls.2026.1950986/full"
    },
    {
      "first_seen": "2026-10-31T12:21:17Z",
      "native_id": "PMC13710281",
      "source": "pmc",
      "url": "https://doi.org/10.3389/fpls.2026.1950986"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1304|Cell Image Analysis Techniques",
      "subfield": "biophysics"
    }
  ],
  "title": "Topology-aware few-shot segmentation improves rice leaf-cell boundary and count fidelity, while correction is risky under tested domain shifts",
  "title_text": "Topology-aware few-shot segmentation improves rice leaf-cell boundary and count fidelity, while correction is risky under tested domain shifts",
  "type": "peer-reviewed",
  "updated_at": "2026-10-31T12:21:17Z",
  "url": "https://research.draconitic.com/paper/dzf6e4dwyyk98",
  "venue": "Frontiers in Plant Science",
  "versions": []
}