Multimodal Artificial Intelligence-Based Virtual Biopsy for Diagnosing Abdominal Lavage Cytology-Positive Gastric Cancer.

Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany)
PMID:

Abstract

Gastric cancer with peritoneal dissemination remains a significant clinical challenge due to its poor prognosis and difficulty in early detection. This study introduces a multimodal artificial intelligence-based risk stratification assessment (RSA) model, integrating radiomic and clinical data to predict peritoneal lavage cytology-positive (GC-CY1) in gastric cancer patients. The RSA model is trained and validated across retrospective, external, and prospective cohorts. In the training cohort, the RSA model achieved an area under the curve (AUC) of 0.866, outperforming traditional clinical and radiomic feature models. External validation cohorts confirmed its robustness, with AUC values of 0.883 and 0.823 for predicting peritoneal metastasis and recurrence, respectively. In a prospective validation involving 152 patients, the model maintained superior predictive performance (AUC = 0.835). The RSA model also demonstrated significant clinical benefits by effectively identifying high-risk patients likely to benefit from specific treatments, such as paclitaxel-based conversion therapy. These findings suggest that the RSA model offers a reliable, non-invasive diagnostic tool for gastric cancer, capable of improving early detection and treatment outcomes. Further prospective studies are warranted to explore its full clinical potential.

Authors

  • Ping'an Ding
    The Third Department of Surgery, the Fourth Hospital of Hebei Medical University, Shijiazhuang, 050011, China.
  • Jiaxuan Yang
    The Third Department of Surgery, the Fourth Hospital of Hebei Medical University, Shijiazhuang, 050011, China.
  • Honghai Guo
    The Third Department of Surgery, the Fourth Hospital of Hebei Medical University, Shijiazhuang, 050011, China.
  • Jiaxiang Wu
    Tencent AI Lab, Shenzhen, China.
  • Haotian Wu
    Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
  • Tongkun Li
    The Third Department of Surgery, the Fourth Hospital of Hebei Medical University, Shijiazhuang, 050011, China.
  • Renjun Gu
    School of Chinese Medicine & School of Integrated Chinese and Western Medicine, Nanjing, University of Chinese Medicine, Nanjing, China.
  • Lilong Zhang
    Department of General Surgery, Renmin Hospital of Wuhan University, Wuhan, Hubei, 430065, China.
  • Jinchen He
    The Third Department of Surgery, the Fourth Hospital of Hebei Medical University, Shijiazhuang, 050011, China.
  • Peigang Yang
    The Third Department of Surgery, the Fourth Hospital of Hebei Medical University, Shijiazhuang, 050011, China.
  • Yuan Tian
    Department of Geriatrics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China.
  • Ning Meng
    Department of Thyroid and Breast Surgery, Affiliated Hospital of Hangzhou Normal University, Hangzhou, Zhejiang Province, China.
  • Xiaolong Li
    Auckland Tongji Medical & Rehabilitation Equipment Research Centre, Tongji Zhejiang College, Jiaxing, China.
  • Zhenjiang Guo
    General Surgery Department, Hengshui People's Hospital, Hengshui, Hebei, 053099, China.
  • Lingjiao Meng
    Research Center and Tumor Research Institute, the Fourth Hospital of Hebei Medical University, Shijiazhuang, 050011, China.
  • Qun Zhao
    Department of Paediatric Orthopaedics, Shengjing Hospital of China Medical University, Shenyang, Liaoning Province, China.