{
  "abstract": "Text-driven medical image segmentation demands unified models based on multi-modal learning, capable of processing diverse imaging modalities while providing spatially reliable prediction estimates for clinical practice. Nevertheless, existing vision-language model solutions suffer from poor domain generalization and exhibit limited capability for uncertainty estimation to model the cumulative unreliability of cross-modal alignment across network layers. In this paper, we propose UniMedSeg, a unified vision-language framework for multi-modal medical image segmentation built upon frozen pre-trained vision-language backbones. Our framework incorporates modality-aware adaptation, cross-layer uncertainty-guided encoding, and a frequency-spatial dual-prompt decoder, wherein the progressive uncertainty propagation mechanism of the encoder suppresses misleading cross-modal features, whereas the decoder disentangles anatomical structure and boundary details in the frequency domain under dual textual prompts. Auxiliary losses further sharpen boundary representations and calibrate pixel-wise uncertainty maps. Extensive experiments demonstrate that UniMedSeg preserves competitive in-domain segmentation performance, improves domain generalization, and yields clinically useful spatial risk estimation.",
  "abstract_shown": true,
  "affiliations": [
    "City University of Macau"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "J. Zhang"
    },
    {
      "name": "S. t. Zheng"
    },
    {
      "name": "X. f. Liu"
    },
    {
      "name": "W. Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "J. Gu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c18b71qg790sv.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.03.755900",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.03.755900v1.full",
  "id": "c18b71qg790sv",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.03.755900v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "pathology"
    ],
    [
      "openalex",
      "1707|Medical Image Segmentation Techniques"
    ]
  ],
  "openalex": "W7221440089",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.03.755900v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/c18b71qg790sv.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:59Z",
      "native_id": "10.64898/2026.10.03.755900",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.03.755900v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "biorxiv:pathology",
      "subfield": "general"
    }
  ],
  "title": "UniMedSeg: Unified Multi-Modal Medical Image Segmentation via Uncertainty Guided Encoding and Frequency-Spatial Dual-Prompt Decoding",
  "title_text": "UniMedSeg: Unified Multi-Modal Medical Image Segmentation via Uncertainty Guided Encoding and Frequency-Spatial Dual-Prompt Decoding",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:59Z",
  "url": "https://research.draconitic.com/paper/c18b71qg790sv",
  "venue": "bioRxiv",
  "versions": []
}