{
  "abstract": "Cardiovascular magnetic resonance (CMR) provides comprehensive cardiac assessment but remains underutilized because of the complexity of acquisition, post-processing, and interpretation. Existing artificial intelligence (AI) methods address isolated tasks, limiting clinical integration. We present ORION-CMR (On-scanner Reporting with Integrated fOunda-tioN Model), the first clinically evaluated scanner-native end-to-end CMR foundation model. Pretrained on 12,896,733 CMR images from 9,258 studies, ORION-CMR performs sequence classification, ventricular function assessment, late gadolinium enhancement (LGE) detection, binary and multiclass disease classification, and local large language model-based report generation in approximately 90 seconds. The framework. was evaluated on public benchmarks and clinically validated in a multi-vendor cohort of 68 subjects with normal examinations, congenital heart disease, dilated cardiomyopathy, and myocardial infarction. ORION-CMR outperformed supervised baselines and the previously published CMR foundation model (CMR-FM), achieving state-of-the-art performance for LGE classification and scar segmentation. Clinical evaluation achieved an AUC of 0.96 for normal-versus abnormal classification and 0.88 for multiclass disease classification, while generated reports demonstrated 81.4% agreement with expert interpretation. These results demonstrate the feasibility of real-time scanner-native AI-assisted CMR analysis and automated report generation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.23950",
  "author_total": 18,
  "authors": [
    {
      "name": "Omer Burak Demirel"
    },
    {
      "name": "Kelly K. Horst"
    },
    {
      "name": "Alessio Perazzolo"
    },
    {
      "name": "Elisa Bruno"
    },
    {
      "name": "Kenan Kaya"
    },
    {
      "name": "Rongzhen Ouyang"
    },
    {
      "name": "Enas Ahmed"
    },
    {
      "name": "Jouke Smink"
    },
    {
      "name": "Spencer L. Waddle"
    },
    {
      "name": "Zainudeen Kallumpurath"
    },
    {
      "name": "Tzu Cheng Chao"
    },
    {
      "name": "Dinghui Wang"
    },
    {
      "name": "Steve G. Langer"
    },
    {
      "name": "Timothy L. Kline"
    },
    {
      "name": "Panagiotis Korfiatis"
    },
    {
      "name": "Jacinta Browne"
    },
    {
      "name": "Ivana Isgum"
    },
    {
      "name": "Tim Leiner"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6r92aw8f4350b.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.23950",
  "fulltext_url": null,
  "id": "6r92aw8f4350b",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.23950",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "arxiv",
      "physics.med-ph"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7214052034",
  "pdf_url": "https://arxiv.org/pdf/2609.23950",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6r92aw8f4350b.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:19Z",
      "native_id": "2609.23950",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.23950"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.med-ph",
      "subfield": "biological-medical"
    }
  ],
  "title": "ORION-CMR: On-scanner Reporting with Integrated Foundation Model for End-to-End Cardiac MRI Analysis and Interpretation",
  "title_text": "ORION-CMR: On-scanner Reporting with Integrated Foundation Model for End-to-End Cardiac MRI Analysis and Interpretation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:19Z",
  "url": "https://research.draconitic.com/paper/6r92aw8f4350b",
  "venue": "arXiv",
  "versions": []
}