Acute Lymphoblastic Leukemia Detection Using Hypercomplex-Valued Convolutional Neural Networks

被引:3
|
作者
Vieira, Guilherme [1 ]
Valle, Marcos Eduardo [1 ]
机构
[1] Univ Estadual Campinas, Dept Appl Math, Campinas, Brazil
基金
巴西圣保罗研究基金会;
关键词
Convolutional neural network; hypercomplex algebras; Clifford algebras; Acute Lymphoblastic Leukemia; computer assisted diagnosis; COMPUTER-ASSISTED DIAGNOSIS;
D O I
10.1109/IJCNN55064.2022.9892036
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper features convolutional neural networks defined on hypercomplex algebras applied to classify lymphocytes in blood smear digital microscopic images. Such classification is helpful for the diagnosis of acute lymphoblast leukemia (ALL), a type of blood cancer. We perform the classification task using eight hypercomplex-valued convolutional neural networks (HvCNNs) along with real-valued convolutional networks. Our results show that HvCNNs perform better than the real-valued model, showcasing higher accuracy with a much smaller number of parameters. Moreover, we found that HvCNNs based on Clifford algebras processing HSV-encoded images attained the highest observed accuracies. Precisely, our HvCNN yielded an average accuracy rate of 96.6% using the ALL-IDB2 dataset with a 50% train-test split, a value extremely close to the state-of-the-art models but using a much simpler architecture with significantly fewer parameters.
引用
收藏
页数:8
相关论文
共 50 条
  • [31] QR Code Detection Using Convolutional Neural Networks
    Chou, Tzu-Han
    Ho, Chuan-Sheng
    Kuo, Yan-Fu
    [J]. 2015 INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS AND INTELLIGENT SYSTEMS (ARIS), 2015,
  • [32] Detection of Cattle Using Drones and Convolutional Neural Networks
    Rivas, Alberto
    Chamoso, Pablo
    Gonzalez-Briones, Alfonso
    Manuel Corchado, Juan
    [J]. SENSORS, 2018, 18 (07)
  • [33] Fingerprint Liveness Detection Using Convolutional Neural Networks
    Nogueira, Rodrigo Frassetto
    Lotufo, Roberto de Alencar
    Machado, Rubens Campos
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2016, 11 (06) : 1206 - 1213
  • [34] Melanoma Detection Using Regular Convolutional Neural Networks
    Abu Ali, Aya
    Al-Marzouqi, Hasan
    [J]. 2017 INTERNATIONAL CONFERENCE ON ELECTRICAL AND COMPUTING TECHNOLOGIES AND APPLICATIONS (ICECTA), 2017, : 363 - 367
  • [35] Stroke Lesion Detection Using Convolutional Neural Networks
    Pereira, Danillo Roberto
    Reboucas Filho, Pedro P.
    de Rosa, Gustavo Henrique
    Papa, Joao Paulo
    de Albuquerque, Victor Hugo C.
    [J]. 2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,
  • [36] Microaneurysm detection using fully convolutional neural networks
    Chudzik, Piotr
    Majumdar, Somshubra
    Caliva, Francesco
    Al-Diri, Bashir
    Hunter, Andrew
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2018, 158 : 185 - 192
  • [37] Facial Smile Detection Using Convolutional Neural Networks
    Dinh Viet Sang
    Le Tran Bao Cuong
    Do Phan Thuan
    [J]. 2017 9TH INTERNATIONAL CONFERENCE ON KNOWLEDGE AND SYSTEMS ENGINEERING (KSE 2017), 2017, : 136 - 141
  • [39] Android Botnet Detection using Convolutional Neural Networks
    Hojjatinia, Sina
    Hamzenejadi, Sajad
    Mohseni, Hadis
    [J]. 2020 28TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2020, : 674 - 679
  • [40] Fall detection using mixtures of convolutional neural networks
    Thao V. Ha
    Hoang M. Nguyen
    Son H. Thanh
    Binh T. Nguyen
    [J]. Multimedia Tools and Applications, 2024, 83 : 18091 - 18118