{
  "abstract": "Accurate segmentation of thin-wall organs-at-risk (OARs) in head-and-neck computed tomography (CT) is challenging because small contour deviations can substantially affect boundary agreement. We present FreqFuseNet, a segmentation architecture with a fast Fourier transform (FFT) primary branch and a frequency channel attention network (FcaNet) residual branch that explicitly aligns heterogeneous frequency-feature scales before bounded residual fusion. An initialization-time analysis revealed an approximately 863-fold activation-scale disparity between the two branches, corresponding to an approximately 43-fold unintended residual-to-primary magnitude ratio under naive fusion with a nominal coefficient of 0.05. FreqFuseNet uses per-sample, per-channel scale alignment to preserve the intended relative amplitude without additional normalization parameters. We evaluated 10 thin-wall OARs on SegRap2023 (84 training, 18 validation, and 18 testing CT cases) under a standardized binary per-OAR region-of-interest (ROI) protocol. In two training seeds, FreqFuseNet achieved Dice of 0.849 and 0.843, 95th-percentile Hausdorff distance (HD95) of 0.824 and 0.823 mm, and surface Dice at 1 mm of 0.959 and 0.957. In case-level paired comparisons for the primary seed (Wilcoxon signed-rank test, not corrected for multiple comparisons), FreqFuseNet showed significant improvements over 3D U-Net and MedNeXt-S, whereas differences versus an alternative learned fusion design (FixedFusion) and SegResNet were not statistically significant. These findings identify a practical feature-scale calibration issue in dual-frequency segmentation and demonstrate competitive boundary-sensitive performance of the proposed architecture within the evaluated ROI-based setting.",
  "abstract_shown": true,
  "affiliations": [
    "Chang Gung University and Linkou Chang Gung Memorial Hospital, Taoyuan, Taiwan"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "W.-Y. Chen"
    },
    {
      "name": "G.-Y. Lin"
    },
    {
      "affs": [
        0
      ],
      "name": "S.-Y. Wan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cwn05gs8pkdfy.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.07.09.26357642",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.07.09.26357642v3.full",
  "id": "cwn05gs8pkdfy",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.07.09.26357642v3",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "radiology and imaging"
    ],
    [
      "openalex",
      "1707|Medical Image Segmentation Techniques"
    ]
  ],
  "openalex": "W7168189864",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.07.09.26357642v3.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cwn05gs8pkdfy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:50Z",
      "native_id": "10.64898/2026.07.09.26357642",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.07.09.26357642v5"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:radiology and imaging",
      "subfield": "imaging"
    }
  ],
  "title": "FreqFuseNet: Scale-Normalized Dual-Frequency Fusion for Thin-Wall Head-and-Neck OAR Segmentation",
  "title_text": "FreqFuseNet: Scale-Normalized Dual-Frequency Fusion for Thin-Wall Head-and-Neck OAR Segmentation",
  "type": "preprint",
  "updated_at": "2026-11-06T00:20:52Z",
  "url": "https://research.draconitic.com/paper/cwn05gs8pkdfy",
  "venue": "medRxiv",
  "versions": []
}