{
  "abstract": "Background: Gastric cancer remains one of the leading causes of cancer-related mortality worldwide, and accurate prediction of radiotherapy response is critical for personalized treatment planning. Contrast-enhanced computed tomography (CT) provides rich spatial and textural information that may serve as a non-invasive biomarker of tumor biology and treatment response. Objectives: This study aimed to develop and validate a CT-based radiomics model for predicting the response of locally advanced gastric cancer to concurrent chemoradiotherapy. Methods: Retrospective data from 212 patients with histologically confirmed gastric adenocarcinoma were collected from two tertiary-care institutions. Radiomic features were extracted from portal venous phase CT images acquired within two weeks prior to treatment initiation. The least absolute shrinkage and selection operator (LASSO) logistic regression was used for feature selection and model construction. Performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC), calibration analysis, and decision curve analysis. Results: A total of 1218 radiomic features were extracted per patient, from which 12 features were selected by LASSO. The radiomics model achieved AUC values of 0.886 (95% CI: 0.841–0.931) and 0.853 (95% CI: 0.792–0.914) in the training and validation cohorts, respectively. The model demonstrated good calibration and significant net benefit across clinically relevant threshold probabilities. Patients classified as responders by the model had significantly improved overall survival compared with non-responders (hazard ratio 0.41, 95% CI: 0.28–0.61, p < 0.001). Conclusions: The CT radiomics model developed in this study provides a robust, non-invasive tool for pretreatment prediction of radiotherapy response in gastric cancer. The model may facilitate individualized treatment stratification and has potential for integration into clinical decision-making workflows.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Medical Oncology, The Afliated Cancer Hospital of Nanjing Medical University, Jiangsu Cancer Hospital, Jiangsu Institute of Cancer Research, Nanjing, Jiangsu, 210009, China; Department of Oncology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China",
    "Department of Medical Oncology, The Afliated Cancer Hospital of Nanjing Medical University, Jiangsu Cancer Hospital, Jiangsu Institute of Cancer Research, Nanjing, Jiangsu, 210009, China; Corresponding author.",
    "Department of Oncology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China; Corresponding author."
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Xingwang Li"
    },
    {
      "affs": [
        1
      ],
      "name": "Pingping Wu"
    },
    {
      "affs": [
        2
      ],
      "name": "Yongmei Yin"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/990fsfkz6mqhw.bib",
  "cited_by": 0,
  "doi": "10.1016/j.jrras.2026.102736",
  "fulltext_url": "http://www.sciencedirect.com/science/article/pii/S1687850726005790",
  "id": "990fsfkz6mqhw",
  "issns": [
    "2314-7164",
    "1687-8507"
  ],
  "landing_url": "https://doi.org/10.1016/j.jrras.2026.102736",
  "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",
      "2741|Radiomics and Machine Learning in Medical Imaging"
    ]
  ],
  "openalex": "W7223463594",
  "pdf_url": "https://www.sciencedirect.com/science/article/pii/S1687850726005790/pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-30",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/990fsfkz6mqhw.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:47:18Z",
      "native_id": "34544484d5994d45ae6550c5d49d695d",
      "source": "doaj",
      "url": "https://doi.org/10.1016/j.jrras.2026.102736"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2741|Radiomics and Machine Learning in Medical Imaging",
      "subfield": "imaging"
    }
  ],
  "title": "Contrast-enhanced CT radiomics for predicting radiotherapy response in gastric cancer: Model development and validation",
  "title_text": "Contrast-enhanced CT radiomics for predicting radiotherapy response in gastric cancer: Model development and validation",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:47:18Z",
  "url": "https://research.draconitic.com/paper/990fsfkz6mqhw",
  "venue": "Journal of Radiation Research and Applied Sciences",
  "versions": []
}