Content-based gastric image retrieval using convolutional neural networks

被引：13
|
作者：
Hu, Huiyi [1 ]
Zheng, Wenfang [2 ,3 ]
Zhang, Xu [1 ]
Zhang, Xinsen [1 ]
Liu, Jiquan [1 ]
Hu, Weiling [2 ,3 ]
Duan, Huilong [1 ]
Si, Jianmin [2 ,3 ]
机构：
[1] Zhejiang Univ, Coll Biomed Engn & Instrument Sci, Minist Educ, Key Lab Biomed Engn, Hangzhou, Peoples R China
[2] Zhejiang Univ, Sir Run Run Shaw Hosp, Med Sch, Dept Gastroenterol, Hangzhou, Peoples R China
[3] Zhejiang Univ, Inst Gastroenterol, Hangzhou, Peoples R China
来源：
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY | 2021年 / 31卷 / 01期
基金：
中国国家自然科学基金;
关键词：
clinical aided diagnosis; content-based image retrieval; convolutional neural networks; gastric precancerous diseases; gastric-map; CLASSIFICATION;
D O I：
10.1002/ima.22470
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
The endoscopy procedure has demonstrated great efficiency in detecting stomach lesions, with extensive numbers of endoscope images produced globally each day. The content-based gastric image retrieval (CBGIR) system has demonstrated substantial potential in gastric image analysis. Gastric precancerous diseases (GPD) have higher prevalence in gastric cancer patients. Thus, effective intervention is crucial at the GPD stage. In this paper, a CBGIR method is proposed using a modified ResNet-18 to generate binary hash codes for a rapid and accurate image retrieval process. We tested several popular models (AlexNet, VGGNet and ResNet), with ResNet-18 determined as the optimum option. Our proposed method was valued using a GPD data set, resulting in a classification accuracy of96.21 +/- 0.66%and a mean average precision of0.927 +/- 0.006, outperforming other state-of-art conventional methods. Furthermore, we constructed a Gastric-Map (GM) based on feature representations in order to visualize the retrieval results. This work has great auxiliary significance for endoscopists in terms of understanding the typical GPD characteristics and improving aided diagnosis.
引用
收藏
页码：439 / 449
页数：11
相关论文
共 50 条
  • [1] Content-Based Image Retrieval using Convolutional Neural Networks
    Rian, Zakhayu
    Christanti, Viny
    Hendryli, Janson
    2019 IEEE INTERNATIONAL CONFERENCE ON SIGNALS AND SYSTEMS (ICSIGSYS), 2019, : 1 - 7
  • [2] Toward Content-Based Image Retrieval with Deep Convolutional Neural Networks
    Sklan, Judah E. S.
    Plassard, Andrew J.
    Fabbri, Daniel
    Landman, Bennett A.
    MEDICAL IMAGING 2015: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING, 2015, 9417
  • [3] Content-Based Image Retrieval Using Customized Convolutional Neural Network
    Nilawar, A. P.
    Dethe, C. G.
    Jaiswal, A.
    Kene, J. D.
    BIOSCIENCE BIOTECHNOLOGY RESEARCH COMMUNICATIONS, 2020, 13 (14): : 467 - 470
  • [4] Content-based image retrieval by combining convolutional neural networks and sparse representation
    Amir Sezavar
    Hassan Farsi
    Sajad Mohamadzadeh
    Multimedia Tools and Applications, 2019, 78 : 20895 - 20912
  • [5] Content-based image retrieval by combining convolutional neural networks and sparse representation
    Sezavar, Amir
    Farsi, Hassan
    Mohamadzadeh, Sajad
    MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (15) : 20895 - 20912
  • [6] Content-based image categorization and retrieval using neural networks
    Zhu, Yuhua
    Liu, Xiuwen
    Mio, Washington
    2007 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-5, 2007, : 528 - 531
  • [7] Content Based Image Retrieval by Convolutional Neural Networks
    Hamreras, Safa
    Benitez-Rochel, Rafaela
    Boucheham, Bachir
    Molina-Cabello, Miguel A.
    Lopez-Rubio, Ezequiel
    FROM BIOINSPIRED SYSTEMS AND BIOMEDICAL APPLICATIONS TO MACHINE LEARNING, PT II, 2019, 11487 : 277 - 286
  • [8] Fast content-based image retrieval using Convolutional Neural Network and hash function
    Varga, Domonkos
    Sziranyi, Tamas
    2016 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2016, : 2636 - 2640
  • [9] Interactive Content-Based Image Retrieval with Deep Neural Networks
    Pyykko, Joel
    Glowacka, Dorota
    SYMBIOTIC INTERACTION (SYMBIOTIC 2016), 2017, 9961 : 77 - 88
  • [10] A powerful method for interactive content-based image retrieval by variable compressed convolutional info neural networks
    Mahalle, Vishwanath S.
    Kandoi, Narendra M.
    Patil, Santosh B.
    VISUAL COMPUTER, 2024, 40 (08): : 5259 - 5285
12345