Reliable and Energy-Efficient Diabetic Retinopathy Screening Using Memristor-Based Neural Networks

被引:3
|
作者
Diware, Sumit [1 ]
Chilakala, Koteswararao [2 ]
Joshi, Rajiv V. [3 ]
Hamdioui, Said [1 ]
Bishnoi, Rajendra [1 ]
机构
[1] Delft Univ Technol, Comp Engn Lab, NL-2628 CD Delft, Netherlands
[2] Capgemini Engn, NL-5652 AA Eindhoven, Netherlands
[3] IBM Thomas J Watson Res Ctr, Yorktown Hts, NY 10598 USA
关键词
Diabetic retinopathy; neural networks; computation-in-memory; resistive random access memory; RRAM; memristor; edge computing; reliability; IMAGES;
D O I
10.1109/ACCESS.2024.3383014
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Diabetic retinopathy (DR) is a leading cause of permanent vision loss worldwide. It refers to irreversible retinal damage caused due to elevated glucose levels and blood pressure. Regular screening for DR can facilitate its early detection and timely treatment. Neural network-based DR classifiers can be leveraged to achieve such screening in a convenient and automated manner. However, these classifiers suffer from reliability issue where they exhibit strong performance during development but degraded performance after deployment. Moreover, they do not provide supplementary information about the prediction outcome, which severely limits their widespread adoption. Furthermore, energy-efficient deployment of these classifiers on edge devices remains unaddressed, which is crucial to enhance their global accessibility. In this paper, we present a reliable and energy-efficient hardware for DR detection, suitable for deployment on edge devices. We first develop a DR classification model using custom training data that incorporates diverse image quality and image sources along with improved class balance. This enables our model to effectively handle both on-field variations in retinal images and minority DR classes, enhancing its post-deployment reliability. We then propose a pseudo-binary classification scheme to further improve the model performance and provide supplementary information about the model prediction. Additionally, we present an energy-efficient hardware design for our model using memristor-based computation-in-memory, to facilitate its deployment on edge devices. Our proposed approach achieves reliable DR classification with three orders of magnitude reduction in energy consumption over state-of-the-art hardware platforms.
引用
收藏
页码:47469 / 47482
页数:14
相关论文
共 50 条
  • [1] Efficient Techniques for Extending Service Time for Memristor-based Neural Networks
    Ma, Yu
    Zhang, Chengrui
    Zhou, Pingqiang
    2021 IEEE ASIA PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS (APCCAS 2021) & 2021 IEEE CONFERENCE ON POSTGRADUATE RESEARCH IN MICROELECTRONICS AND ELECTRONICS (PRIMEASIA 2021), 2021, : 81 - 84
  • [2] Energy-efficient and fast memristor-based serial multipliers applicable in image processing
    Fatemieh, Seyed Erfan
    Bagheralmoosavi, Bahareh
    Reshadinezhad, Mohammad Reza
    RESULTS IN ENGINEERING, 2025, 25
  • [3] Offline Training for Memristor-based Neural Networks
    Boquet, Guillem
    Macias, Edwar
    Morell, Antoni
    Serrano, Javier
    Miranda, Enrique
    Lopez Vicario, Jose
    28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 1547 - 1551
  • [4] Advances in Memristor-Based Neural Networks
    Xu, Weilin
    Wang, Jingjuan
    Yan, Xiaobing
    FRONTIERS IN NANOTECHNOLOGY, 2021, 3
  • [5] Efficient Techniques for Training the Memristor-based Spiking Neural Networks Targeting Better Speed, Energy and Lifetime
    Ma, Yu
    Zhou, Pingqiang
    2021 26TH ASIA AND SOUTH PACIFIC DESIGN AUTOMATION CONFERENCE (ASP-DAC), 2021, : 390 - 395
  • [6] On Memristor-Based Impulsive Neural Networks with Time-Delay
    Hu, Bin
    Guan, Zhi-Hong
    Liu, Zhi-Wei
    Jiang, Xiao-Wei
    2017 29TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC), 2017, : 4748 - 4753
  • [7] Equilibrium Propagation for Memristor-Based Recurrent Neural Networks
    Zoppo, Gianluca
    Marrone, Francesco
    Corinto, Fernando
    FRONTIERS IN NEUROSCIENCE, 2020, 14
  • [8] Memristor-based Neuromorphic Implementations for Artificial Neural Networks
    Zhao, Chun
    Zhou, Guang You
    Zhao, Ce Zhou
    Yang, Li
    Man, Ka Lok
    Lim, Eng Gee
    2018 INTERNATIONAL SOC DESIGN CONFERENCE (ISOCC), 2018, : 174 - 175
  • [9] Equilibrium Propagation and (Memristor-based) Oscillatory Neural Networks
    Zoppo, Gianluca
    Marrone, Francesco
    Bonnin, Michele
    Corinto, Fernando
    2022 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 22), 2022, : 639 - 643
  • [10] Hardware implementation of memristor-based artificial neural networks
    Aguirre, Fernando
    Sebastian, Abu
    Le Gallo, Manuel
    Song, Wenhao
    Wang, Tong
    Yang, J. Joshua
    Lu, Wei
    Chang, Meng-Fan
    Ielmini, Daniele
    Yang, Yuchao
    Mehonic, Adnan
    Kenyon, Anthony
    Villena, Marco A.
    Roldan, Juan B.
    Wu, Yuting
    Hsu, Hung-Hsi
    Raghavan, Nagarajan
    Sune, Jordi
    Miranda, Enrique
    Eltawil, Ahmed
    Setti, Gianluca
    Smagulova, Kamilya
    Salama, Khaled N.
    Krestinskaya, Olga
    Yan, Xiaobing
    Ang, Kah-Wee
    Jain, Samarth
    Li, Sifan
    Alharbi, Osamah
    Pazos, Sebastian
    Lanza, Mario
    NATURE COMMUNICATIONS, 2024, 15 (01)