Advertisement
Research Article|Articles in Press

A real-time interpretable artificial intelligence model for the cholangioscopic diagnosis of malignant biliary stricture

  • Xiang Zhang
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Dehua Tang
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China

    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Jindong Zhou
    Affiliations
    National Institute of Healthcare Data Science at Nanjing University, Nanjing, Jiangsu 210008, China

    National Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Muhan Ni
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Peng Yan
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Zhenyu Zhang
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Tao Yu
    Affiliations
    Departments of Gastroenterology, Qilu Hospital of Shandong University, Jinan, Shandong 250012, China
    Search for articles by this author
  • Qiang Zhan
    Affiliations
    Department of Gastroenterology, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, Jiangsu 214023, China
    Search for articles by this author
  • Yonghua Shen
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China

    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Lin Zhou
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China

    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Ruhua Zheng
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China

    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Xiaoping Zou
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China

    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China

    Department of Gastroenterology, Taikang Xianlin Drum Tower Hospital, Nanjing, Jiangsu 210046, China
    Search for articles by this author
  • Bin Zhang
    Correspondence
    Corresponding author information: Bin Zhang, MD, PhD, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China; Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, 321 Zhongshan Road, Nanjing, Jiangsu 210008, China
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China

    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Wu-Jun Li
    Correspondence
    Corresponding author information: Wu-Jun Li, PhD, National Institute of Healthcare Data Science at Nanjing University, Nanjing, Jiangsu 210008, China; National Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University, Nanjing, Jiangsu 210008, China; Center for Medical Big Data, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China.
    Affiliations
    National Institute of Healthcare Data Science at Nanjing University, Nanjing, Jiangsu 210008, China

    National Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University, Nanjing, Jiangsu 210008, China

    Center for Medical Big Data, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
  • Lei Wang
    Correspondence
    Corresponding author information: Lei Wang, MD, PhD, Department of Gastroenterology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China; Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, 321 Zhongshan Road, Nanjing, Jiangsu 210008, China,
    Affiliations
    Department of Gastroenterology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing Medical University, Nanjing, Jiangsu 210008, China

    Department of Gastroenterology, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210008, China
    Search for articles by this author
Published:February 25, 2023DOI:https://doi.org/10.1016/j.gie.2023.02.026
      This paper is only available as a PDF. To read, Please Download here.

      Abstract

      Background and aims

      It is crucial to accurately determine malignant biliary strictures (MBSs) for early curative treatment. The study aimed to develop a real-time interpretable artificial intelligent (AI) system to predict MBSs under digital single-operator cholangioscopy (DSOC).

      Methods

      A novel interpretable AI system called MBSDeiT was developed, consisting of two models to identify qualified images and then predict MBS in real time. The overall efficiency of MBSDeiT was validated at the image level on internal, external, prospective testing datasets and subgroups analyses, and at the video level on the prospective datasets, and compared with that of endoscopists. The association between AI predictions and endoscopic features was evaluated to increase the interpretability.

      Results

      MBSDeiT can first automatically select qualified DSOC images with an AUC of 0.904 and 0.921–0.927 on the internal testing dataset and the external testing datasets, and then identify MBSs with an AUC of 0.971 on the internal testing dataset, an AUC of 0.978–0.999 on the external testing datasets, and an AUC of 0.976 on the prospective testing dataset, respectively. MBSDeiT accurately identified 92.3% MBS in prospective testing videos. Subgroups analyses confirmed the stability and robustness of MBSDeiT. MBSDeiT achieved superior performance to that of expert and novice endoscopists. The AI predictions were significantly associated with four endoscopic features (nodular mass; friability; raised intraductal lesion; and abnormal vessels; P < 0.05) under DSOC, which is consistent with the endoscopists’ predictions.

      Conclusions

      The findings suggest that MBSDeiT could be a promising approach for the accurate diagnosis of MBS under DSOC.

      Keywords

      Abbreviations:

      AI (Artificial intelligent), MBS (Malignant biliary stricture), DSOC (Digital single-operator cholangioscopy), AUC (Area under the curve), ERCP (Endoscopic retrograde cholangiopancreatography), FISH (Fluorescent in situ hybridization), EUS (Endoscopic ultrasound), IDUS (Intraductal ultrasound), NGS (Next-generation sequencing), VI (Visual impression), DB (Direct biopsy), CI (Confidence interval), PPV (Positive predictive value), NPV (Negative predictive value)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Gastrointestinal Endoscopy
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect