{
  "abstract": "The limited availability of imaging data for uncommon cardiovascular phenotypes constrains the development of robust imaging models. We evaluated whether class-conditional diffusion models can generate synthetic transthoracic echocardiograms that improve downstream cardiac imaging tasks. The primary application was cardiac amyloidosis detection in a Duke University cohort using a two-step classifier, with external analyses using EchoNet-Dynamic for image-fidelity assessment and EchoNet-LVH for wall-thickness phenotype classification. The Duke cohort was partitioned at the patient-encounter level into 70% training, 15% validation, and 15% test sets; generators were trained only on the training partition, augmentation levels were selected using validation AUROC, and final evaluation used held-out real test data. In the Duke all-view two-step analysis, adding synthetic images increased AUROC from 0.883 to 0.924, with an AUROC difference of 0.041 (95% CI, 0.013-0.069); in EchoNet-LVH, AUROC increased from 0.832 to 0.864, with an AUROC difference of 0.032 (95% CI, 0.021-0.044). Expert review found that synthetic images were sometimes difficult to identify as synthetic, but rated them lower for diagnostic adequacy. These findings suggest that diffusion-generated echocardiograms may provide a practical approach to augmenting limited training data for selected cardiac imaging tasks and motivate further evaluation across clinical settings.",
  "abstract_shown": true,
  "affiliations": [
    "Duke University"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "name": "P. Lyu"
    },
    {
      "name": "R. Henao"
    },
    {
      "name": "L. C. Kwee"
    },
    {
      "name": "F. Z. Peng"
    },
    {
      "name": "S. Vemulapalli"
    },
    {
      "name": "S. H. Shah"
    },
    {
      "name": "M. G. Khouri"
    },
    {
      "affs": [
        0
      ],
      "name": "A. Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4w60425jtk6h0.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.14.26363024",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.14.26363024v1.full",
  "id": "4w60425jtk6h0",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.14.26363024v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "health informatics"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7213368969",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.14.26363024v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4w60425jtk6h0.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:39Z",
      "native_id": "10.64898/2026.09.14.26363024",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.14.26363024v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Synthetic Echocardiograms from Diffusion Models in Rare Cardiovascular Disease",
  "title_text": "Synthetic Echocardiograms from Diffusion Models in Rare Cardiovascular Disease",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:39Z",
  "url": "https://research.draconitic.com/paper/4w60425jtk6h0",
  "venue": "medRxiv",
  "versions": []
}