Deep Convolutional Generative Adversarial Network for Improved Cardiac Image Classification in Heart Disease Diagnosis.

Heart disease is a fatal disease that causes significant mortality rates worldwide. The accurate and early detection of heart diseases is the most challenging task to save valuable lives. To avoid these issues, the Deep Convolutional Generative Adversarial Network (DCGAN) model is proposed that gene...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Imaging Informatics in Medicine Vol. 38; no. 4; pp. 2146 - 2170
Autores principales: S, Gurusubramani, B, Latha
Formato: diagnostic images research tables/charts Journal Article
Publicado: Springer Nature Aug2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=187278979&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 187278979
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        29482925
        NR3A
      jtl: Journal of Imaging Informatics in Medicine
      issn: 29482925
      maglogo: N
    pubinfo:
      dt: Aug2025
      vid: 38
      iid: 4
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        187278979
        187278979
        187278979
        10.1007/s10278-024-01343-z
        187278979
      ppf: 2146
      ppct: 24
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Deep Convolutional Generative Adversarial Network for Improved Cardiac Image Classification in Heart Disease Diagnosis.
      aug:
        au:
          S, Gurusubramani
          B, Latha
        affil: https://ror.org/01vv1bg04 Department of Computer Science and Engineering, Sri Sairam Engineering College, Anna University, Chennai, India
      sug:
        subj:
          Deep Learning
          Generative Adversarial Networks
          Image Interpretation, Computer Assisted
          Image Processing, Computer Assisted
          Heart Diseases Diagnosis
          Artificial Intelligence
          Diagnostic Imaging
          Human
          Resource Databases
          Algorithms
          Neural Networks (Computer)
          Sensitivity and Specificity
          Validity
          Precision
          Time
          Machine Learning
          Magnetic Resonance Imaging
          Information Science
          Computer Simulation
          Benchmarking
      ab: Heart disease is a fatal disease that causes significant mortality rates worldwide. The accurate and early detection of heart diseases is the most challenging task to save valuable lives. To avoid these issues, the Deep Convolutional Generative Adversarial Network (DCGAN) model is proposed that generates synthetic cardiac images. Here, two types of heart disease datasets such as the Sunnybrook Cardiac Dataset (SCD) and the Automated Cardiac Diagnosis Challenge (ACDC) dataset are selected to choose real cardiac images for implementation. The quality and consistency of the cardiac images are enhanced by preprocessed real cardiac images. In the DCGAN model, the generator is used for converting real cardiac images into synthetic images and the discriminator is responsible for differentiating real and synthetic cardiac images by binary classification decisions. To enhance the model's robustness and generalization ability, diverse augmentation techniques are implemented. The VGG16 model is applied in this paper for the image classification task and fine-tuned its parameters to optimize model convergence. For experimental validation, some of the significance metrics such as accuracy, precision, diagnostic time, peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), false positive rate (FPR), false negative rate (FNR), and mean squared error (MSE) are utilized. The extensive experimental evaluations are carried out based on this metrics and attained a performance rate of the proposed method as 98.83%, 1.17%, 3.2%, 41.78, 4.52, 0.932, and 1.6 s from accuracy, FPR, FNR, PSNR, MSE, SSIM, and diagnostic time, respectively. The experimental evaluation results demonstrate that the proposed heart disease diagnosis model attains superior performances than state-of-the-art methods.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N