{
  "abstract": "Accurate classification of lung adenocarcinoma growth patterns from hematoxylin and eosin (H&E)-stained whole-slide images is essential for treatment planning and prognosis. We develop and evaluate an exponentially weighted ensemble deep learning approach that combines five architectures (EfficientNet-B3, DeiT3, Swin Transformer, Vision Transformer, ConvNeXt) with weights determined by a softmax transformation of per-model Quadratic Weighted Kappa (QWK) scores. Using 25,545 image patches at 40x magnification from the Dartmouth-Hitchcock dataset, we evaluated performance with stratified 5-fold cross-validation. Individual model performance ranged from Cohens kappa{kappa} = 0.5563 (Con-vNeXt) to{kappa} = 0.9561 (EfficientNet-B3). The ensemble achieved 96.52% accuracy and{kappa} = 0.9648, exceeding the best individual model by {Delta}{kappa} = +0.0087 with statistical significance (McNemars test,{chi} 2 = 50.84, p < 10-12; bootstrap 95% CI on {Delta}{kappa} [+0.0056, +0.0117]). Pairwise disagreement rates of 16.6-43.2% between architectures indicate that the models capture different aspects of tissue morphology, and the framework automatically down-weights unreliable components, as illustrated by ConvNeXt receiving only 5.7% ensemble weight despite a single-fold training failure. The approach offers a clinically grounded method for ensemble aggregation in digital pathology.",
  "abstract_shown": true,
  "affiliations": [
    "Roux Institute, Northeastern University"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "R. Korutla"
    },
    {
      "name": "M. N. Jain"
    },
    {
      "name": "T. M. Karkera"
    },
    {
      "name": "G. Tunik"
    },
    {
      "name": "S. T. Ryan"
    },
    {
      "name": "R. A. Christman"
    },
    {
      "affs": [
        0
      ],
      "name": "S. Amal"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/apn0q5gxrm23f.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.24.26363902",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.24.26363902v1.full",
  "id": "apn0q5gxrm23f",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.24.26363902v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "oncology"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7214582587",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.24.26363902v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/apn0q5gxrm23f.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:35Z",
      "native_id": "10.64898/2026.09.24.26363902",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.24.26363902v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:oncology",
      "subfield": "oncology"
    }
  ],
  "title": "Exponentially weighted ensemble deep learning for histologic growth pattern classification in lung adenocarcinoma",
  "title_text": "Exponentially weighted ensemble deep learning for histologic growth pattern classification in lung adenocarcinoma",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:35Z",
  "url": "https://research.draconitic.com/paper/apn0q5gxrm23f",
  "venue": "medRxiv",
  "versions": []
}