Federated Fusion of Magnified Histopathological Images for Breast Tumor Classification in the Internet of Medical Things

被引:14
作者
Agbley, Bless Lord Y. [1 ]
Li, Jian Ping [1 ]
Haq, Amin Ul [1 ]
Bankas, Edem Kwedzo [2 ]
Mawuli, Cobbinah Bernard [1 ]
Ahmad, Sultan [3 ]
Khan, Shakir [4 ,5 ]
Khan, Ahmad Raza [6 ]
机构
[1] Univ Elect Sci & Technol China, Chengdu 611731, Peoples R China
[2] C K Tedam Univ Technol & Appl Sci, Sch Comp & Informat Sci, Dept Business Comp, Box 24, Navrongo, Ghana
[3] Prince Sattam Bin Abdulaziz Univ, Coll Comp Engn Sci, Dept Comp Sci, Alkharj 11942, Saudi Arabia
[4] Imam Mohammad Ibn Saud Islamic Univ IMSIU, Coll Comp Sci & Informat Sci, Riyadh 11432, Saudi Arabia
[5] Chandigarh Univ, Univ Ctr Res & Dev, Dept Comp Sci & Engn, Mohali 140413, India
[6] Majmaah Univ, Coll Comp & Informat Sci, Informat Technol Dept, Majmaah 11952, Saudi Arabia
基金
中国国家自然科学基金;
关键词
Deep learning; information fusion; internet of medical things; medical image analysis; magnification; CANCER;
D O I
10.1109/JBHI.2023.3256974
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Breast tumor detection and classification on the Internet of Medical Things (IoMT) can be automated with the potential of Artificial Intelligence (AI). Deep learning models rely on large datasets, however, challenges arise when dealing with sensitive medical data. Restrictions on sharing these medical data result in limited publicly available datasets thereby impacting the performance of the deep learning models. To address this issue, we propose an approach that combines different magnification factors of histopathological images using a residual network and information fusion in Federated Learning (FL). FL is employed to preserve the privacy of patient data, while enabling the creation of a global model. Using the BreakHis dataset, we compare the performance of FL with centralized learning (CL). We also performed visualizations for explainable AI. The final models obtained become available for deployment on internal IoMT systems in healthcare institutions for timely diagnosis and treatment. Our results demonstrate that the proposed approach outperforms existing works in the literature on multiple metrics.
引用
收藏
页码:3389 / 3400
页数:12
相关论文
共 43 条
  • [1] Histopathological Breast Cancer Image Classification by Deep Neural Network Techniques Guided by Local Clustering
    Abdullah-Al Nahid
    Mehrabi, Mohamad Ali
    Kong, Yinan
    [J]. BIOMED RESEARCH INTERNATIONAL, 2018, 2018
  • [2] Abu Samah A, 2017, IEEE I C SIGNAL IMAG, P102, DOI 10.1109/ICSIPA.2017.8120587
  • [3] FEDERATED APPROACH FOR LUNG AND COLON CANCER CLASSIFICATION
    Agbley, Bless Lord Y.
    Li, Jianping
    Ul Haq, Amin
    Bankas, Edem Kwedzo
    Adjorlolo, Gideon
    Agyemang, Isaac Osei
    Ayekai, Browne Judith
    Effah, Derrick
    Adjeimensah, Isaac
    Khan, Jalaluddin
    [J]. 2022 19TH INTERNATIONAL COMPUTER CONFERENCE ON WAVELET ACTIVE MEDIA TECHNOLOGY AND INFORMATION PROCESSING (ICCWAMTIP), 2022,
  • [4] Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images
    Agbley, Bless Lord Y.
    Li, Jianping
    Hossin, Md Altab
    Nneji, Grace Ugochi
    Jackson, Jehoiada
    Monday, Happy Nkanta
    James, Edidiong Christopher
    [J]. DIAGNOSTICS, 2022, 12 (07)
  • [5] Transitioning Between Convolutional and Fully Connected Layers in Neural Networks
    Akbar, Shazia
    Peikari, Mohammad
    Salama, Sherine
    Nofech-Mozes, Sharon
    Martel, Anne
    [J]. DEEP LEARNING IN MEDICAL IMAGE ANALYSIS AND MULTIMODAL LEARNING FOR CLINICAL DECISION SUPPORT, 2017, 10553 : 143 - 150
  • [6] [Anonymous], 2023, Breast Cancer Statistics
  • [7] Medical Image Classification with Hand-Designed or Machine-Designed Texture Descriptors: A Performance Evaluation
    Badejo, Joke A.
    Adetiba, Emmanuel
    Akinrinmade, Adekunle
    Akanle, Matthew B.
    [J]. BIOINFORMATICS AND BIOMEDICAL ENGINEERING (IWBBIO 2018), PT II, 2019, 10814 : 266 - 275
  • [8] Bayramoglu N, 2016, INT C PATT RECOG, P2440, DOI 10.1109/ICPR.2016.7900002
  • [9] Benhammou Y., 2018, P INT C LEARN OPT AL, P1
  • [10] Cascianelli S., 2018, Intelligent Interactive Multimedia Systems and Services, P21, DOI 10.1007/978-3-319-59480-4_3