{
  "abstract": "Background: Postoperative recurrence is the leading cause of treatment failure in oral squamous cell carcinoma (OSCC), yet current risk-stratification schemes offer only modest predictive performance. We developed a Transformer-based multimodal fusion framework integrating computed tomography (CT), histopathology, and clinical variables for individualized recurrence prediction. Methods: A total of 134 patients with OSCC were retrospectively enrolled. Using a dual-stream strategy, deep semantic representations were derived from preoperative contrast-enhanced CT and haematoxylin and eosin-stained histopathological images via MnasNet-0.5, while quantitative radiomic descriptors were extracted using PyRadiomics. Together with structured clinical variables, these constituted five parallel feature streams, which – after dimensional harmonization – were passed through a three-layer Transformer encoder employing self-attention and learnable modality weights for nonlinear cross-modal integration. Performance was assessed by fivefold stratified cross-validation. Results: The full-modality TransformerFusion model achieved an AUC of 0.909 ± 0.069, with a sensitivity of 0.791, specificity of 0.834, and precision of 0.854. Decision curve analysis demonstrated superior net clinical benefit over logistic regression and the treat-none strategy across threshold probabilities of 0.20 to 0.70. Ablation experiments revealed that the pathology dual-stream, CT dual-stream, and clinical-only submodels attained AUCs of 0.840, 0.751, and 0.773, respectively – each inferior to the integrated model. Self-attention-based fusion (AUC = 0.909) also outperformed feature concatenation (AUC = 0.854). Conclusion: The proposed framework captures complementary prognostic signals across CT, histopathology, and clinical variables, outperforming single-modality counterparts in recurrence prediction. As it relies solely on routine preoperative CT and standard haematoxylin and eosin slides, it offers a clinically deployable tool for postoperative risk stratification in OSCC.",
  "abstract_shown": true,
  "affiliations": [
    "Department Oral & Maxillofacial Surgery, The Second Hospital of Dalian Medical University, Dalian Medical University, Dalian, Liaoning, China",
    "Department Oral & Maxillofacial Surgery, The First Hospital of Dalian Medical University, Dalian Medical University, Dalian, Liaoning, China"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Shuwen Yang"
    },
    {
      "affs": [
        0
      ],
      "name": "Fuyong Sui"
    },
    {
      "affs": [
        0
      ],
      "name": "Zhuang Liang"
    },
    {
      "affs": [
        0
      ],
      "name": "Qilin Liu"
    },
    {
      "affs": [
        0
      ],
      "name": "Binyang Fu"
    },
    {
      "affs": [
        0
      ],
      "name": "Hui Dong"
    },
    {
      "affs": [
        1
      ],
      "name": "Zhen Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e8jxdyd07x8v5.bib",
  "cited_by": 0,
  "doi": "10.1016/j.identj.2026.111098",
  "fulltext_url": "http://www.sciencedirect.com/science/article/pii/S0020653926016904",
  "id": "e8jxdyd07x8v5",
  "issns": [
    "0020-6539",
    "1875-595X"
  ],
  "landing_url": "https://doi.org/10.1016/j.identj.2026.111098",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "RK1-715"
    ],
    [
      "openalex",
      "2741|Radiomics and Machine Learning in Medical Imaging"
    ]
  ],
  "openalex": "W7213578929",
  "pdf_url": "https://www.sciencedirect.com/science/article/pii/S0020653926016904/pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-31",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/e8jxdyd07x8v5.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T14:21:48Z",
      "native_id": "12b954b3ac2144f48a511198502a1bcf",
      "source": "doaj",
      "url": "https://doi.org/10.1016/j.identj.2026.111098"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2741|Radiomics and Machine Learning in Medical Imaging",
      "subfield": "imaging"
    }
  ],
  "title": "Transformer-Based Multimodal Fusion Integrating Computed Tomography, Pathology, and Clinical Features for Oral Squamous Cell Carcinoma Recurrence Prediction",
  "title_text": "Transformer-Based Multimodal Fusion Integrating Computed Tomography, Pathology, and Clinical Features for Oral Squamous Cell Carcinoma Recurrence Prediction",
  "type": "peer-reviewed",
  "updated_at": "2026-10-31T14:21:48Z",
  "url": "https://research.draconitic.com/paper/e8jxdyd07x8v5",
  "venue": "International Dental Journal",
  "versions": []
}