Multi-stage domain-specific pretraining for improved detection and localization of Barrett's neoplasia: A comprehensive clinically validated study.

Patients suffering from Barrett's Esophagus (BE) are at an increased risk of developing esophageal adenocarcinoma and early detection is crucial for a good prognosis. To aid the endoscopists with the early detection for this preliminary stage of esophageal cancer, this work concentrates on the devel...

Descripción completa

Detalles Bibliográficos
Publicado en:Artificial Intelligence in Medicine Vol. 107
Autores principales: van der Putten, Joost, de Groof, Jeroen, Struyvenberg, Maarten, Boers, Tim, Fockens, Kiki, Curvers, Wouter, Schoon, Erik, Bergman, Jacques, van der Sommen, Fons, de With, Peter H.N.
Formato: research tables/charts Journal Article
Publicado: Elsevier B.V. Jul2020
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=145474623&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 145474623
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        09333657
        3HY
      jtl: Artificial Intelligence in Medicine
      issn: 09333657
      maglogo: N
    pubinfo:
      dt: Jul2020
      vid: 107
      pid: 1004
      pub: Elsevier B.V.
    artinfo:
      ui:
        145474623
        145474623
        NLM32828453
        145474623
        10.1016/j.artmed.2020.101914
        NLM32828453
        145474623
      ppct: 1
      formats:
      tig:
        atl: Multi-stage domain-specific pretraining for improved detection and localization of Barrett's neoplasia: A comprehensive clinically validated study.
      aug:
        au:
          van der Putten, Joost
          de Groof, Jeroen
          Struyvenberg, Maarten
          Boers, Tim
          Fockens, Kiki
          Curvers, Wouter
          Schoon, Erik
          Bergman, Jacques
          van der Sommen, Fons
          de With, Peter H.N.
        affil: Eindhoven University of Technology, VCA Group, Eindhoven, The Netherlands
      sug:
        subj:
          Esophageal Neoplasms Diagnosis
          Barrett Esophagus Diagnosis
          Adenocarcinoma
          Pilot Studies
          Esophagoscopy
          Scales
          Clinical Assessment Tools
      ab: Patients suffering from Barrett's Esophagus (BE) are at an increased risk of developing esophageal adenocarcinoma and early detection is crucial for a good prognosis. To aid the endoscopists with the early detection for this preliminary stage of esophageal cancer, this work concentrates on the development and extensive evaluation of a state-of-the-art computer-aided classification and localization algorithm for dysplastic lesions in BE. To this end, we have employed a large-scale endoscopic data set, consisting of 494,355 images, in combination with a novel semi-supervised learning algorithm to pretrain several instances of the proposed neural network architecture. Next, several Barrett-specific data sets that are increasingly closer to the target domain with significantly more data compared to other related work, were used in a multi-stage transfer learning strategy. Additionally, the algorithm was evaluated on two prospectively gathered external test sets and compared against 53 medical professionals. Finally, the model was also evaluated in a live setting without interfering with the current biopsy protocol. Results from the performed experiments show that the proposed model improves on the state-of-the-art on all measured metrics. More specifically, compared to the best performing state-of-the-art model, the specificity is improved by more than 20% points while simultaneously preserving high sensitivity and reducing the false positive rate substantially. Our algorithm yields similar scores on the localization metrics, where the intersection of all experts is correctly indicated in approximately 92% of the cases. Furthermore, the live pilot study shows great performance in a clinical setting with a patient level accuracy, sensitivity, and specificity of 90%. Finally, the proposed algorithm outperforms each individual medical expert by at least 5% and the average assessor by more than 10% over all assessor groups with respect to accuracy.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N