{
  "abstract": "Objective: To develop and evaluate an attention-guided 3D U-Net framework for liver tumor segmentation on contrast-enhanced CT images, with particular emphasis on improving segmentation performance under severe foreground-background imbalance caused by the sparse distribution of tumor regions. Methods: The 131 labeled LiTS cases were divided by patient into 92 training cases, 20 validation cases, and 19 held-out internal test cases. CT volumes were clipped to −160 to 240 HU, normalized to [0, 1], and cropped into 64 × 64 × 64 patches. Safe 3D augmentation was applied only to the training set. Attention gates were embedded in the skip connections of a 3D U-Net, and a hybrid Dice–binary cross-entropy loss was used to address foreground–background imbalance. The proposed model was compared with eight representative 3D segmentation networks using Dice, intersection over union (IoU), precision, and recall. Results: On the independent test set, on the held-out internal test subset of 19 LiTS patients, the proposed model achieved a Dice score of 0.841 (95% CI: 0.812–0.870) and IoU of 0.765 (95% CI: 0.731–0.799), outperforming all evaluated baseline models. Compared with the locally implemented vanilla 3D U-Net, Dice increased by 0.1401 (14.01 percentage points; 19.98% relative) and IoU increased by 0.1642 (16.42 percentage points; 27.34% relative). Qualitative examples suggested improved boundary continuity in selected difficult cases; this observation was not a prespecified subgroup analysis. Conclusion: The proposed framework improved liver tumor segmentation performance on the LiTS dataset under a controlled evaluation protocol. Further external multicenter validation is required to assess its generalizability across different clinical settings. Further multicenter validation is required before clinical application.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Radiology & Imaging Center, Hunan Cancer Hospital, Hunan, 410000, China",
    "Department of Cardiology, Hunan Provincial People's Hospital, China",
    "Endoscopy Diagnosis and Treatment Center, Hunan Cancer Hospital, Hunan, 410000, China",
    "Endoscopy Diagnosis and Treatment Center, Hunan Cancer Hospital, Hunan, 410000, China; Corresponding author."
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Min Gong"
    },
    {
      "affs": [
        1
      ],
      "name": "Jiaru Wu"
    },
    {
      "affs": [
        2
      ],
      "name": "Ang Qin"
    },
    {
      "affs": [
        3
      ],
      "name": "Yong Qiu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cr0bj96x44v7x.bib",
  "cited_by": 0,
  "doi": "10.1016/j.jrras.2026.102717",
  "fulltext_url": "http://www.sciencedirect.com/science/article/pii/S1687850726005601",
  "id": "cr0bj96x44v7x",
  "issns": [
    "2314-7164",
    "1687-8507"
  ],
  "landing_url": "https://doi.org/10.1016/j.jrras.2026.102717",
  "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",
      "R895-920"
    ],
    [
      "lcc",
      "TK9001-9401"
    ],
    [
      "openalex",
      "1707|Medical Image Segmentation Techniques"
    ]
  ],
  "openalex": "W7223243326",
  "pdf_url": "https://www.sciencedirect.com/science/article/pii/S1687850726005601/pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-30",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/cr0bj96x44v7x.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:44:32Z",
      "native_id": "75fb56524154419c852f3b0fd3a0343c",
      "source": "doaj",
      "url": "https://doi.org/10.1016/j.jrras.2026.102717"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "lcc:R895-920",
      "subfield": "general"
    }
  ],
  "title": "Automatic segmentation of liver tumors based on attention-guided 3D U-Net using LiTS dataset revision",
  "title_text": "Automatic segmentation of liver tumors based on attention-guided 3D U-Net using LiTS dataset revision",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:44:32Z",
  "url": "https://research.draconitic.com/paper/cr0bj96x44v7x",
  "venue": "Journal of Radiation Research and Applied Sciences",
  "versions": []
}