{
  "abstract": "Introduction: Banana diseases impose severe production losses in tropical smallholder farming systems, yet accurate in-field visual diagnosis remains difficult because symptom expression varies across cultivars and growth stages and several diseases produce morphologically overlapping foliar signs. We therefore developed a probabilistic image-recognition framework for detecting five economically important banana diseases from in-field photographs without disease-specific fine-tuning of the vision backbone.\n\nMethods: Frozen 1,152-dimensional embeddings were extracted from the DINOv3 vision foundation model and coupled with a conditional normalizing flow. The model was trained on four publicly available datasets comprising approximately 95,000 images across eight classes spanning diseased banana plants, healthy tissue, non-banana vegetation, and general natural imagery.\n\nResults: On an independent test set, the model achieved F1 scores exceeding 0.98, average precision values of 0.9678-0.9998, and AUROC values of 0.9967-0.9998 across all five diseases evaluated as binary detection problems. Multi-class accuracy was nearperfect, with limited confusion between Yellow Sigatoka and Black Sigatoka. Because the normalizing flow estimates explicit conditional probability densities rather than decision boundaries, two complementary log-likelihood ratios were derived: a disease ratio comparing each disease class against healthy banana, and a plant ratio comparing banana against non-banana imagery.\n\nDiscussion: Together, these likelihood ratios define an interpretable two-dimensional diagnostic space that simultaneously quantifies evidence for disease presence and image relevance, cleanly separating diseased plants, healthy plants, and out-ofdistribution images while flagging uncertain predictions for confirmatory testing. Batched inference costs 6.4 ms per image on a single TPU core, supporting deployment at surveillance-programme scale and providing a scalable, uncertainty-aware diagnostic tool for smallholder farming systems.",
  "abstract_shown": true,
  "affiliations": [
    "Independent Researcher",
    "Epidemiology and Modelling Group, Department of Plant Sciences, University of Cambridge"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Alisa Prusokiene"
    },
    {
      "affs": [
        0
      ],
      "name": "Augustinas Prusokas"
    },
    {
      "affs": [
        1
      ],
      "name": "Renata Retkute"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/24av6wdaagtw5.bib",
  "cited_by": 0,
  "doi": "10.3389/fpls.2026.1937900",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13690962/?tool=EBI",
  "id": "24av6wdaagtw5",
  "issns": [
    "1664-462X"
  ],
  "landing_url": "https://www.frontiersin.org/articles/10.3389/fpls.2026.1937900/full",
  "language": "eng",
  "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": [
    [
      "openalex",
      "1110|Smart Agriculture and AI"
    ]
  ],
  "openalex": "W7221074828",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13690962/pdf/?tool=EBI",
  "pmcid": "PMC13690962",
  "pmid": null,
  "published": "2026-10-09",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/24av6wdaagtw5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:25Z",
      "native_id": "10.3389/fpls.2026.1937900",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fpls.2026.1937900/full"
    },
    {
      "first_seen": "2026-10-30T12:19:59Z",
      "native_id": "PMC:PMC13690962",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13690962"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "openalex:1110|Smart Agriculture and AI",
      "subfield": "plant-biology"
    }
  ],
  "title": "Vision normalizing flows for the probability-informed detection of banana diseases from in-field images",
  "title_text": "Vision normalizing flows for the probability-informed detection of banana diseases from in-field images",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:19:59Z",
  "url": "https://research.draconitic.com/paper/24av6wdaagtw5",
  "venue": "Frontiers in Plant Science",
  "versions": []
}