{
  "abstract": "Scarce medical images often prompt data augmentation. We ask when it earns its opportunity cost under a complete information budget. Across four collections, classical and GAN candidates are compared with real-only training, full-pool exposure, score adjustment and direct label use. Transformations reduce within-patient variation; source mismatch and between-patient uncertainty remain. Fixed 50-model ResNet50 ensembles with ranked classical candidates and probability averaging outperform equally adjusted real-only and full-pool ensembles at five sizes. We evaluate procedures in 50 paired draws at 50, 100, 150, 200 and 250 image-training patients. The design counts 200 regularization patients plus disjoint 100-patient selection and adjustment sets. Evaluation includes 38,743 CheXpert patients. At 250 patients, guidance reduces maximum group cross-entropy by 0.0442 versus real-only training (simultaneous 95% interval, 0.0048–0.0836). Adding the 100 selection patients to each original training cohort outperforms using their labels only to guide augmentation at 50–200 patients. Thus, use independent labels first when cohorts are smallest; consider selected augmentation once patient evidence, strong representation and aggregation are available. The 250-patient result marks the upper tested setting, not a universal threshold. AUROC remains stable while sensitivity and specificity shift, requiring operating-point review.",
  "abstract_shown": true,
  "affiliations": [
    "Institute for Optimization and Data Analysis (IODA), School of Engineering and Computer Science, Bern University of Applied Sciences, 2502 Biel/Bienne, Switzerland"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Murat Sariyar",
      "orcid": "0000-0003-3432-2860"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7w9x30h6y0kvf.bib",
  "cited_by": 0,
  "doi": "10.3390/math14203732",
  "fulltext_url": null,
  "id": "7w9x30h6y0kvf",
  "issns": [
    "2227-7390"
  ],
  "landing_url": "https://www.mdpi.com/2227-7390/14/20/3732",
  "language": null,
  "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",
      "2741|COVID-19 diagnosis using AI"
    ]
  ],
  "openalex": "W7221772905",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-14",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/7w9x30h6y0kvf.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:29Z",
      "native_id": "10.3390/math14203732",
      "source": "crossref",
      "url": "https://www.mdpi.com/2227-7390/14/20/3732"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2741|COVID-19 diagnosis using AI",
      "subfield": "imaging"
    }
  ],
  "title": "When Does Data Augmentation Help with Few Chest-Radiograph Training Patients?",
  "title_text": "When Does Data Augmentation Help with Few Chest-Radiograph Training Patients?",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:18:29Z",
  "url": "https://research.draconitic.com/paper/7w9x30h6y0kvf",
  "venue": "Mathematics",
  "versions": []
}