Deep learning with attention modules and residual transformations improves hepatocellular carcinoma (HCC) differentiation using multiphase CT.

Background: We hypothesize generative adversarial networks (GAN) combined with self‐attention (SA) and aggregated residual transformations (ResNeXt) perform better than conventional deep learning models in differentiating hepatocellular carcinoma (HCC). Attention modules facilitate concentrating on...

Descripción completa

Detalles Bibliográficos
Publicado en:Precision Radiation Oncology Vol. 9; no. 1; pp. 13 - 23
Autores principales: Wang, Yuenan, Jian, Wanwei, Yuan, Zhidong, Guan, Fada, Carlson, David
Formato: research tables/charts Journal Article
Publicado: Wiley-Blackwell Mar2025
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=184139648&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 184139648
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        23987324
        L3KI
      jtl: Precision Radiation Oncology
      issn: 23987324
      maglogo: N
    pubinfo:
      dt: Mar2025
      vid: 9
      iid: 1
      pid: 480
      pub: Wiley-Blackwell
      place: Malden, Massachusetts
    artinfo:
      ui:
        184139648
        183891208
        184139648
        184139648
        10.1002/pro6.70003
        184139648
      ppf: 13
      ppct: 10
      formats:
      tig:
        atl: Deep learning with attention modules and residual transformations improves hepatocellular carcinoma (HCC) differentiation using multiphase CT.
      aug:
        au:
          Wang, Yuenan
          Jian, Wanwei
          Yuan, Zhidong
          Guan, Fada
          Carlson, David
        affil: Department of Therapeutic Radiology, Yale University School of Medicine, New Haven Connecticut,, USA
      sug:
        subj:
          Carcinoma, Hepatocellular Diagnosis
          Deep Learning
          Prediction Models
          Tomography, X-Ray Computed
          Human
          Sensitivity and Specificity
          Retrospective Design
          Descriptive Statistics
          Data Analysis Software
          Male
          Female
          Adult
          Middle Age
          Adult: 19-44 years
          Middle Aged: 45-64 years
          Male
          Female
      ab: Background: We hypothesize generative adversarial networks (GAN) combined with self‐attention (SA) and aggregated residual transformations (ResNeXt) perform better than conventional deep learning models in differentiating hepatocellular carcinoma (HCC). Attention modules facilitate concentrating on salient features and suppressing redundancies, while residual transformations can reuse relevant features. Therefore, we aim to propose a GAN+SA+ResNeXt deep learning model to improve HCC prediction accuracy. Methods: 228 multiphase CTs from 57 patients were retrospectively analyzed with local IRB's approval, where 30 patients were pathologically confirmed with HCC and the rest 27 were non‐HCC. Pre‐processing of automatic liver segmentation and Hounsfield unit (HU) normalization was performed, followed by deep learning training with five‐fold cross validation in a conventional 3D GAN, a 3D GAN+A, and a 3D GAN+A+ ResNeXt, respectively (training: testing ∼ 4:1). Area under receiver operating characteristics curves (AUROC), accuracy, sensitivity and specificity of HCC prediction were evaluated. Results: Results showed the proposed method had larger AUROC (95%), better accuracy (91%) and sensitivity (93%) with acceptable specificity (88%) and prediction time (0.04s). Deep GAN with attentions and residual transformations for HCC diagnosis using multiphase CT is feasible and favorable with improved accuracy and efficiency, which harbors clinical potentials in differentiating HCC from other benign or malignant liver lesions.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N