Primary Tumor Radiomic Model for Identifying Extrahepatic Metastasis of Hepatocellular Carcinoma Based on Contrast Enhanced Computed Tomography

被引:1
|
作者
Chan, Lawrence Wing Chi [1 ]
Wong, Sze Chuen Cesar [2 ]
Cho, William Chi Shing [3 ]
Huang, Mohan [1 ]
Zhang, Fei [1 ]
Chui, Man Lik [1 ]
Lai, Una Ngo Yin [1 ]
Chan, Tiffany Yuen Kwan [1 ]
Cheung, Zoe Hoi Ching [1 ]
Cheung, Jerry Chun Yin [1 ]
Tang, Kin Fu [1 ]
Tse, Man Long [1 ]
Wong, Hung Kit [1 ]
Kwok, Hugo Man Fung [1 ]
Shen, Xinping [4 ]
Zhang, Sailong [5 ]
Chiu, Keith Wan Hang [5 ,6 ]
机构
[1] Hong Kong Polytech Univ, Dept Hlth Technol & Informat, Hong Kong, Peoples R China
[2] Hong Kong Polytech Univ, Dept Appl Biol & Chem Technol, Hong Kong, Peoples R China
[3] Queen Elizabeth Hosp, Dept Clin Oncol, Hong Kong, Peoples R China
[4] Univ Hong Kong, Shenzhen Hosp, Dept Radiol, Shenzhen 518053, Peoples R China
[5] Univ Hong Kong, Dept Diagnost Radiol, Hong Kong, Peoples R China
[6] Queen Elizabeth Hosp, Dept Radiol & Imaging, Hong Kong, Peoples R China
关键词
computed tomography; radiomics; machine learning; clinical decision-making; hepatocellular carcinoma; extrahepatic metastasis; oversampling; PREOPERATIVE PREDICTION; MICROVASCULAR INVASION; CLINICAL-FEATURES; RISK; CT; SORAFENIB;
D O I
10.3390/diagnostics13010102
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
This study aimed to identify radiomic features of primary tumor and develop a model for indicating extrahepatic metastasis of hepatocellular carcinoma (HCC). Contrast-enhanced computed tomographic (CT) images of 177 HCC cases, including 26 metastatic (MET) and 151 non-metastatic (non-MET), were retrospectively collected and analyzed. For each case, 851 radiomic features, which quantify shape, intensity, texture, and heterogeneity within the segmented volume of the largest HCC tumor in arterial phase, were extracted using Pyradiomics. The dataset was randomly split into training and test sets. Synthetic Minority Oversampling Technique (SMOTE) was performed to augment the training set to 145 MET and 145 non-MET cases. The test set consists of six MET and six non-MET cases. The external validation set is comprised of 20 MET and 25 non-MET cases collected from an independent clinical unit. Logistic regression and support vector machine (SVM) models were identified based on the features selected using the stepwise forward method while the deep convolution neural network, visual geometry group 16 (VGG16), was trained using CT images directly. Grey-level size zone matrix (GLSZM) features constitute four of eight selected predictors of metastasis due to their perceptiveness to the tumor heterogeneity. The radiomic logistic regression model yielded an area under receiver operating characteristic curve (AUROC) of 0.944 on the test set and an AUROC of 0.744 on the external validation set. Logistic regression revealed no significant difference with SVM in the performance and outperformed VGG16 significantly. As extrahepatic metastasis workups, such as chest CT and bone scintigraphy, are standard but exhaustive, radiomic model facilitates a cost-effective method for stratifying HCC patients into eligibility groups of these workups.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Preoperatively predicting vessels encapsulating tumor clusters in hepatocellular carcinoma: Machine learning model based on contrast-enhanced computed tomography
    Zhang, Chao
    Zhong, Hai
    Zhao, Fang
    Ma, Zhen-Yu
    Dai, Zheng-Jun
    Pang, Guo-Dong
    WORLD JOURNAL OF GASTROINTESTINAL ONCOLOGY, 2024, 16 (03) : 857 - 874
  • [2] The arterial tumor enhancement pattern on contrast-enhanced computed tomography is associated with primary cancer death after radiofrequency ablation for small hepatocellular carcinoma
    Shimizu, Ryo
    Tamai, Hideyuki
    Mori, Yoshiyuki
    Shingaki, Naoki
    Maeshima, Shuya
    Nuta, Junya
    Maeda, Yoshimasa
    Moribata, Kosaku
    Muraki, Yosuke
    Deguchi, Hisanobu
    Inoue, Izumi
    Maekita, Takao
    Iguchi, Mikitaka
    Kato, Jun
    Ichinose, Masao
    HEPATOLOGY INTERNATIONAL, 2016, 10 (02) : 328 - 339
  • [3] Radiomics model based on contrast-enhanced computed tomography to predict early recurrence in patients with hepatocellular carcinoma after radical resection
    Li, Shu-Qun
    Su, Li-Li
    Xu, Ting-Feng
    Ren, Li-Ying
    Chen, Dong-Bo
    Qin, Wan-Ying
    Yan, Xuan-Zhi
    Fan, Jia-Xing
    Chen, Hong-Song
    Liao, Wei-Jia
    WORLD JOURNAL OF GASTROENTEROLOGY, 2023, 29 (26) : 4186 - 4199
  • [4] Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma
    Xu, Xun
    Zhang, Hai-Long
    Liu, Qiu-Ping
    Sun, Shu-Wen
    Zhang, Jing
    Zhu, Fei-Peng
    Yang, Guang
    Yan, Xu
    Zhang, Yu-Dong
    Liu, Xi-Sheng
    JOURNAL OF HEPATOLOGY, 2019, 70 (06) : 1133 - 1144
  • [5] Growth Rate of Primary Single Hepatocellular Carcinoma: Determining Optimal Screening Interval with Contrast Enhanced Computed Tomography
    Kazunori Kubota
    Hiroyasu Ina
    Yoichi Okada
    Tetsuya Irie
    Digestive Diseases and Sciences, 2003, 48 : 581 - 586
  • [6] Growth rate of primary single hepatocellular carcinoma - Determining optimal screening interval with contrast enhanced computed tomography
    Kubota, K
    Ina, H
    Okada, Y
    Irie, T
    DIGESTIVE DISEASES AND SCIENCES, 2003, 48 (03) : 581 - 586
  • [7] Can primary hepatocellular carcinoma histomorphology predict extrahepatic metastasis?
    Kumar, Deepika
    Hafez, Omeed
    Jain, Dhanpat
    Zhang, Xuchen
    HUMAN PATHOLOGY, 2021, 113 : 39 - 46
  • [8] Hepatocellular carcinoma presenting as extrahepatic mass on computed tomography
    Hironobu Kimura
    Tetsuya Inoue
    Kohji Konishi
    Atsushi Tsuneda
    Kenichi Tazawa
    Mitsuharu Earashi
    Kiichi Maeda
    Kazuhisa Yabushita
    Yoshitaka Kuroda
    Masahiko Tsuji
    Atsuo Miwa
    Journal of Gastroenterology, 1997, 32 : 260 - 263
  • [9] Hepatocellular carcinoma presenting as extrahepatic mass on computed tomography
    Kimura, H
    Inoue, T
    Konishi, K
    Tsuneda, A
    Tazawa, K
    Earashi, M
    Maeda, K
    Yabushita, K
    Kuroda, Y
    Tsuji, M
    Miwa, A
    JOURNAL OF GASTROENTEROLOGY, 1997, 32 (02) : 260 - 263
  • [10] Radiomic Feature-Based Predictive Model for Microvascular Invasion in Patients With Hepatocellular Carcinoma
    He, Mu
    Zhang, Peng
    Ma, Xiao
    He, Baochun
    Fang, Chihua
    Jia, Fucang
    FRONTIERS IN ONCOLOGY, 2020, 10