{
  "abstract": "Magnetic resonance imaging and histopathology observe the same glioma at radically different scales. We present CrossScale-GLIO, a visual multimodal framework that represents MRI as a tumor-habitat graph and histology as a cell-niche graph, then aligns them with a structure-aware optimal transport objective anchored by diagnostic language. Across paired and external glioma cohorts, CrossScale-GLIO achieved a paired-test subtype macro-F1 of 0.789, IDH AUROC of 0.934, 1p/19q AUROC of 0.884, and MGMT AUROC of 0.802. The subtype gain over feature-only transport was 2.8 percentage points (95% CI: 1.2 to 4.4, adjusted p = 0.0019). Bidirectional patient retrieval reached Recall@1 values of 0.286 and 0.278, and Recall@5 values of 0.621 and 0.608. Pathologists rated 81.2% of high-mass habitat-niche pairs as biologically plausible. Deleting the highest-mass pair reduced correct-class probability by 0.184, compared with 0.049 under random deletion. Degree-preserving graph rewiring reduced subtype macro-F1 by 0.034 and retrieval Recall@1 by 0.090, directly confirming that preserved relational topology drives cross-scale correspondence.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.28524",
  "author_total": 6,
  "authors": [
    {
      "name": "Yantong Liu"
    },
    {
      "name": "Zheyu Zhang"
    },
    {
      "name": "Runpeng Liu"
    },
    {
      "name": "Mu Xitang"
    },
    {
      "name": "Seong-Yoon Shin"
    },
    {
      "name": "Hyun-Ae Lee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dny4bxpf9a3e6.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.28524",
  "fulltext_url": null,
  "id": "dny4bxpf9a3e6",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.28524",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "2716|Glioma Diagnosis and Treatment"
    ]
  ],
  "openalex": "W7214402741",
  "pdf_url": "https://arxiv.org/pdf/2609.28524",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dny4bxpf9a3e6.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:16Z",
      "native_id": "2609.28524",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.28524"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "CrossScale-GLIO: Topology-Preserving Vision-Language Alignment of MRI and Whole-Slide Histopathology for Diffuse Glioma",
  "title_text": "CrossScale-GLIO: Topology-Preserving Vision-Language Alignment of MRI and Whole-Slide Histopathology for Diffuse Glioma",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:16Z",
  "url": "https://research.draconitic.com/paper/dny4bxpf9a3e6",
  "venue": "arXiv",
  "versions": []
}