Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses

被引:8
|
作者
Nakata, Norio [1 ]
Siina, Tsuyoshi [2 ]
机构
[1] Jikei Univ, Ctr Integrated Med Res, Sch Med, Div Artificial Intelligence Med, 3-25-8 Nishi Shinbashi,Minato Ku, Tokyo 1058461, Japan
[2] Shibaura Inst Technol, Grad Sch Sci & Engn, 3-7-5 Toyosu,Koto Ku, Tokyo 1358548, Japan
来源
BIOENGINEERING-BASEL | 2023年 / 10卷 / 01期
关键词
ensemble learning; deep learning; convolutional neural network; liver; ultrasonography; artificial intelligence;
D O I
10.3390/bioengineering10010069
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
Ultrasound (US) is often used to diagnose liver masses. Ensemble learning has recently been commonly used for image classification, but its detailed methods are not fully optimized. The purpose of this study is to investigate the usefulness and comparison of some ensemble learning and ensemble pruning techniques using multiple convolutional neural network (CNN) trained models for image classification of liver masses in US images. Dataset of the US images were classified into four categories: benign liver tumor (BLT) 6320 images, liver cyst (LCY) 2320 images, metastatic liver cancer (MLC) 9720 images, primary liver cancer (PLC) 7840 images. In this study, 250 test images were randomly selected for each class, for a total of 1000 images, and the remaining images were used as the training. 16 different CNNs were used for training and testing ultrasound images. The ensemble learning used soft voting (SV), weighted average voting (WAV), weighted hard voting (WHV) and stacking (ST). All four types of ensemble learning (SV, ST, WAV, and WHV) showed higher values of accuracy than the single CNN. All four types also showed significantly higher deep learning (DL) performance than ResNeXt101 alone. For image classification of liver masses using US images, ensemble learning improved the performance of DL over a single CNN.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Classification of Ultrasound Breast Images Using Fused Ensemble of Deep Learning Classifiers
    Nehary, E. A.
    Rajan, Sreeraman
    [J]. 2022 IEEE INTERNATIONAL SYMPOSIUM ON MEDICAL MEASUREMENTS AND APPLICATIONS (MEMEA 2022), 2022,
  • [2] Multiclass Skin Cancer Classification Using Ensemble of Fine-Tuned Deep Learning Models
    Kausar, Nabeela
    Hameed, Abdul
    Sattar, Mohsin
    Ashraf, Ramiza
    Imran, Ali Shariq
    ul Abidin, Muhammad Zain
    Ali, Ammara
    [J]. APPLIED SCIENCES-BASEL, 2021, 11 (22):
  • [3] Joint segmentation and classification of hepatic lesions in ultrasound images using deep learning
    Ryu, Hwaseong
    Shin, Seung Yeon
    Lee, Jae Young
    Lee, Kyoung Mu
    Kang, Hyo-jin
    Yi, Jonghyon
    [J]. EUROPEAN RADIOLOGY, 2021, 31 (11) : 8733 - 8742
  • [4] Joint segmentation and classification of hepatic lesions in ultrasound images using deep learning
    Hwaseong Ryu
    Seung Yeon Shin
    Jae Young Lee
    Kyoung Mu Lee
    Hyo-jin Kang
    Jonghyon Yi
    [J]. European Radiology, 2021, 31 : 8733 - 8742
  • [5] Automatic Classification of Hepatic Cystic Echinococcosis Using Ultrasound Images and Deep Learning
    Wu, Miao
    Yan, Chuanbo
    Wang, Xiaorong
    Liu, Qian
    Liu, Zhihua
    Song, Tao
    [J]. JOURNAL OF ULTRASOUND IN MEDICINE, 2022, 41 (01) : 163 - 174
  • [6] Deep Learning Approaches for Data Augmentation and Classification of Breast Masses using Ultrasound Images
    Al-Dhabyani, Walid
    Fahmy, Aly
    Gomaa, Mohammed
    Khaled, Hussien
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2019, 10 (05) : 618 - 627
  • [7] Deep learning approaches for data augmentation and classification of breast masses using ultrasound images
    Al-Dhabyani, Walid
    Fahmy, Aly
    Gomaa, Mohammed
    Khaled, Hussien
    [J]. International Journal of Advanced Computer Science and Applications, 2019, 10 (05): : 618 - 627
  • [8] Multiclass Classification of UML Diagrams from Images Using Deep Learning
    Shcherban, Sergei
    Liang, Peng
    Li, Zengyang
    Yang, Chen
    [J]. INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING, 2021, 31 (11N12) : 1683 - 1698
  • [9] Classification of Multiclass Histopathological Breast Images Using Residual Deep Learning
    Eltoukhy, Mohamed Meselhy
    Hosny, Khalid M.
    Kassem, Mohamed A.
    [J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
  • [10] MULTICLASS CLASSIFICATION OF REMOTE SENSING IMAGES USING DEEP LEARNING TECHNIQUES
    Arshad, Tahir
    Zhang Junping
    Qingyan Wang
    [J]. IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 7234 - 7237