ISSN 0253-2778

CN 34-1054/N

open
Free to Publish. Free to Read.
Open AccessOpen Access JUSTC Life Science, Info. & Intelligence 18 January 2023

Preoperative diagnosis of hepatocellular carcinoma patients with bile duct tumor thrombus using deep learning method

  • 1.

    School of Management, University of Science and Technology of China, Hefei 230026, China

  • 2.

    Department of Hepatobiliary Pancreatic Surgery, Fujian Provincial Hospital, Fuzhou 350001, China

Cite this:
https://doi.org/10.52396/JUSTC-2022-0057
More Information
  • Author Bio:

    Jinming Liu is a postgraduate student under the tutelage of Prof. Hong Zhang at the University of Science and Technology of China. His research interests focus on pattern recognition and natural language processing

    Hong Zhang is a Professor with the University of Science and Technology of China (USTC). He received his Bachalor’s degree in Mathematics and Ph.D. degree in Statistics from USTC in 1997 and 2003, respectively. His major research interests include statistical genetics, causal inference, and machine learning

  • Corresponding author: E-mail: zhangh@ustc.edu.cn
  • Received Date: 27 March 2022
  • Accepted Date: 31 May 2022
    • Available Online: 18 January 2023
    Abstract

  • Abstract

    Preoperative diagnosis of bile duct tumor thrombus (BDTT) is clinically important as the surgical prognosis of hepatocellular carcinoma (HCC) patients with BDTT is significantly different from that of patients without BDTT. Although dilated bile ducts (DBDs) can act as biomarkers for diagnosing BDTT, it is easy for doctors to ignore DBDs when reporting the imaging scan result, leading to a high missed diagnosis rate in practice. This study aims to develop an artificial intelligence (AI) pipeline for automatically diagnosing HCC patients with BDTT using medical images. The proposed AI pipeline includes two stages. First, the object detection neural network Faster R-CNN was adopted to identify DBDs; then, an HCC patient was diagnosed with BDTT if the proportion of images with at least one identified DBD exceeded some threshold value. Based on 2354 CT images collected from 32 HCC patients (16 with BDTT and 16 without BDTT, 1∶1 matched), the proposed AI pipeline achieves an average true positive rate of 0.92 for identifying DBDs per patient and a patient-level true positive rate of 0.81 for diagnosing BDTT. The AUC value of the patient-level diagnosis of BDTT is 0.94 (95% CI: 0.87, 1.00), compared with 0.71 (95% CI: 0.51, 0.90) achieved by random forest based on preoperative clinical variables. The high accuracies demonstrate that the proposed AI pipeline is successful in the diagnosis and localization of BDTT using CT images.

    Graphical abstract

    Overview of the proposed computer-aided diagnosis process for BDTT.

    Abstract

    Preoperative diagnosis of bile duct tumor thrombus (BDTT) is clinically important as the surgical prognosis of hepatocellular carcinoma (HCC) patients with BDTT is significantly different from that of patients without BDTT. Although dilated bile ducts (DBDs) can act as biomarkers for diagnosing BDTT, it is easy for doctors to ignore DBDs when reporting the imaging scan result, leading to a high missed diagnosis rate in practice. This study aims to develop an artificial intelligence (AI) pipeline for automatically diagnosing HCC patients with BDTT using medical images. The proposed AI pipeline includes two stages. First, the object detection neural network Faster R-CNN was adopted to identify DBDs; then, an HCC patient was diagnosed with BDTT if the proportion of images with at least one identified DBD exceeded some threshold value. Based on 2354 CT images collected from 32 HCC patients (16 with BDTT and 16 without BDTT, 1∶1 matched), the proposed AI pipeline achieves an average true positive rate of 0.92 for identifying DBDs per patient and a patient-level true positive rate of 0.81 for diagnosing BDTT. The AUC value of the patient-level diagnosis of BDTT is 0.94 (95% CI: 0.87, 1.00), compared with 0.71 (95% CI: 0.51, 0.90) achieved by random forest based on preoperative clinical variables. The high accuracies demonstrate that the proposed AI pipeline is successful in the diagnosis and localization of BDTT using CT images.

    • Public Summary

    • We proposed the first AI pipeline for the diagnosis and evaluation of BDTT through indentifying DBDs on CT images.
    • Our AI pipeline achieved a high AUC of 0.94 (95% CI: 0.87, 1.00) in the application to a real dataset.

    FullText(HTML)
  • loading
    • References(46)
  • [1]
    Navadgi S, Chang C C, Bartlett A, et al. Systematic review and meta-analysis of outcomes after liver resection in patients with hepatocellular carcinoma (HCC) with and without bile duct thrombus. HPB, 2016, 18 (4): 312–316. doi: 10.1016/j.hpb.2015.12.003
    [2]
    Lu W, Tang H, Yang Z, et al. A proposed modification for the Barcelona clinic liver cancer staging system: Adding bile duct tumor thrombus status in patients with hepatocellular carcinoma. The American Journal of Surgery, 2020, 220 (4): 965–971. doi: 10.1016/j.amjsurg.2020.04.003
    [3]
    Meng K W, Dong M, Zhang W G, et al. Clinical characteristics and surgical prognosis of hepatocellular carcinoma with bile duct invasion. Gastroenterology Research and Practice, 2014, 2014: 604971. doi: 10.1155/2014/604971
    [4]
    Wang D D, Wu L Q, Wang Z S. Prognosis of hepatocellular carcinoma with bile duct tumor thrombus after R0 resection: A matched study. Hepatobiliary & Pancreatic Diseases International, 2016, 15 (6): 626–632. doi: 10.1016/S1499-3872(16)60143-1
    [5]
    Wang C, Yang Y, Sun D, et al. Prognosis of hepatocellular carcinoma patients with bile duct tumor thrombus after hepatic resection or liver transplantation in Asian populations: A meta-analysis. PLoS One, 2017, 12 (5): e0176827. doi: 10.1371/journal.pone.0176827
    [6]
    Shao W, Sui C, Liu Z, et al. Surgical outcome of hepatocellular carcinoma patients with biliary tumor thrombi. World Journal of Surgical Oncology, 2011, 9: 2. doi: 10.1186/1477-7819-9-2
    [7]
    Rammohan A, Sathyanesan J, Rajendran K, et al. Bile duct thrombi in hepatocellular carcinoma: Is aggressive surgery worthwhile? HPB, 2015, 17 (6): 508–513. doi: 10.1111/hpb.12383
    [8]
    Shiomi M, Kamiya J, Nagino M, et al. Hepatocellular carcinoma with biliary tumor thrombi: Aggressive operative approach after appropriate preoperative management. Surgery, 2001, 129 (6): 692–698. doi: 10.1067/msy.2001.113889
    [9]
    Zhou X, Wang J, Tang M, et al. Hepatocellular carcinoma with hilar bile duct tumor thrombus versus hilar Cholangiocarcinoma on enhanced computed tomography: A diagnostic challenge. BMC Cancer, 2020, 20 (1): 54. doi: 10.1186/s12885-020-6539-7
    [10]
    Liu Q Y, Zhang W D, Chen J Y, et al. Hepatocellular carcinoma with bile duct tumor thrombus: Dynamic computed tomography findings and histopatholo