{
  "abstract": "Purpose: To compare four multimodal large language models (MLLMs) with radiologists of varying expertise in breast density assessment, BI-RADS assessment, biopsy candidacy determination, and continuous malignancy probability estimation using digital mammography (DM) and contrast-enhanced mammography (CEM). Methods: This study included 179 women with paired DM/CEM examinations and reference standards. Four MLLMs (ChatGPT-5.2, Gemini-3.1 Pro, Sonnet-4.6, Muse Spark) interpreted images with and without masks; three radiologists interpreted non-masked images. Results: For binary density classification on DM, radiologist accuracies ranged from 55.81% to 78.60%, exceeding most MLLM values (62.33%-71.63%), while masks added limited benefit. Five-category BI-RADS accuracies were higher for radiologists on DM (56.74-67.44%) and CEM (62.33-82.79%) compared with MLLMs (DM 31.16-45.12%; CEM 40.00-55.81%). Binary biopsy-candidacy accuracies were likewise higher for radiologists (DM 85.12-89.77%; CEM 86.98-92.09%) than for MLLMs (DM 61.39-75.35%; CEM 69.30-82.79%), although CEM improved performance across all readers. Lesion masks substantially improved MLLM continuous malignancy-probability accuracies from 64.65%-71.63% to 72.56-78.60% on DM and from 67.91%-77.21% to 72.56%-81.86% on CEM, approaching radiologist ranges (DM 63.72-82.79%; CEM 81.86-88.84%). The corresponding AUCs for the top masked models overlapped those of the human readers. Overall, Muse Spark, followed by Sonnet-4.6, demonstrated the strongest performance among the MLLMs across domains. Conclusion: Radiologists generally outperformed MLLMs in categorical tasks, while selected masked models approached human performance for continuous malignancy probability estimation, suggesting a potential adjunctive role.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.14676",
  "author_total": 14,
  "authors": [
    {
      "name": "Ali Abbasian Ardakani"
    },
    {
      "name": "Afshin Mohammadi"
    },
    {
      "name": "Taha Yusuf Kuzan"
    },
    {
      "name": "Beyza Nur Kuzan"
    },
    {
      "name": "Alisa Mohebbi"
    },
    {
      "name": "Masume Behruzi"
    },
    {
      "name": "Hamid Khorshidi"
    },
    {
      "name": "Ashkan Ghorbani"
    },
    {
      "name": "Elham Asadiara"
    },
    {
      "name": "Zeinab Khorshidi Lotfi"
    },
    {
      "name": "Ansar Rahman"
    },
    {
      "name": "Nedim Christoph Beste"
    },
    {
      "name": "U. Rajendra Acharya"
    },
    {
      "name": "Sepideh Hatamikia"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ddw8d00d6687x.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.14676",
  "fulltext_url": null,
  "id": "ddw8d00d6687x",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.14676",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "physics.med-ph"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7213361717",
  "pdf_url": "https://arxiv.org/pdf/2609.14676",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ddw8d00d6687x.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:25Z",
      "native_id": "2609.14676",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.14676"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.med-ph",
      "subfield": "biological-medical"
    }
  ],
  "title": "From Density to Biopsy Decisions and Malignancy Prediction: A Benchmark Study of Multimodal Large Language Models Against Radiologists in Digital and Contrast-Enhanced Mammography",
  "title_text": "From Density to Biopsy Decisions and Malignancy Prediction: A Benchmark Study of Multimodal Large Language Models Against Radiologists in Digital and Contrast-Enhanced Mammography",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:25Z",
  "url": "https://research.draconitic.com/paper/ddw8d00d6687x",
  "venue": "arXiv",
  "versions": []
}