Generalization of Deep Learning in Digital Pathology: Experience in Breast Cancer Metastasis Detection.

Simple Summary: Pathology is a cornerstone in cancer diagnostics, and digital pathology and artificial intelligence-driven image analysis could potentially save time and enhance diagnostic accuracy. For clinical implementation of artificial intelligence, a major question is whether the computer mode...

Descripción completa

Detalles Bibliográficos
Publicado en:Cancers Vol. 14; no. 21; pp. 5424 - 5442
Autores principales: Jarkman, Sofia, Karlberg, Micael, Pocevičiūtė, Milda, Bodén, Anna, Bándi, Péter, Litjens, Geert, Lundström, Claes, Treanor, Darren, van der Laak, Jeroen
Formato: pictorial research tables/charts Journal Article
Publicado: MDPI Nov2022
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=160147462&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 160147462
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        20726694
        B74B
      jtl: Cancers
      issn: 20726694
      maglogo: N
    pubinfo:
      dt: Nov2022
      vid: 14
      iid: 21
      pid: 97109
      pub: MDPI
    artinfo:
      ui:
        160147462
        160147462
        160147462
        10.3390/cancers14215424
        160147462
      ppf: 5424
      ppct: 18
      formats:
      tig:
        atl: Generalization of Deep Learning in Digital Pathology: Experience in Breast Cancer Metastasis Detection.
      aug:
        au:
          Jarkman, Sofia
          Karlberg, Micael
          Pocevičiūtė, Milda
          Bodén, Anna
          Bándi, Péter
          Litjens, Geert
          Lundström, Claes
          Treanor, Darren
          van der Laak, Jeroen
        affil: Department of Clinical Pathology, and Department of Biomedical and Clinical Sciences, Linköping University, 581 83 Linköping, Sweden
      sug:
        subj:
          Deep Learning
          Pathology, Clinical
          Breast Neoplasms Diagnosis
          Neoplasm Metastasis Diagnosis
          Lymph Nodes Pathology
          Lymphatic Diseases Diagnosis
          Cancer Screening
          Human
          Artificial Intelligence
          Multicenter Studies
          Descriptive Statistics
          Confidence Intervals
          Qualitative Studies
          Pathologists
      ab: Simple Summary: Pathology is a cornerstone in cancer diagnostics, and digital pathology and artificial intelligence-driven image analysis could potentially save time and enhance diagnostic accuracy. For clinical implementation of artificial intelligence, a major question is whether the computer models maintain high performance when applied to new settings. We tested the generalizability of a highly accurate deep learning model for breast cancer metastasis detection in sentinel lymph nodes from, firstly, unseen sentinel node data and, secondly, data with a small change in surgical indication, in this case lymph nodes from axillary dissections. Model performance dropped in both settings, particularly on axillary dissection nodes. Retraining of the model was needed to mitigate the performance drop. The study highlights the generalization challenge of clinical implementation of AI models, and the possibility that retraining might be necessary. Poor generalizability is a major barrier to clinical implementation of artificial intelligence in digital pathology. The aim of this study was to test the generalizability of a pretrained deep learning model to a new diagnostic setting and to a small change in surgical indication. A deep learning model for breast cancer metastases detection in sentinel lymph nodes, trained on CAMELYON multicenter data, was used as a base model, and achieved an AUC of 0.969 (95% CI 0.926–0.998) and FROC of 0.838 (95% CI 0.757–0.913) on CAMELYON16 test data. On local sentinel node data, the base model performance dropped to AUC 0.929 (95% CI 0.800–0.998) and FROC 0.744 (95% CI 0.566–0.912). On data with a change in surgical indication (axillary dissections) the base model performance indicated an even larger drop with a FROC of 0.503 (95%CI 0.201–0.911). The model was retrained with addition of local data, resulting in about a 4% increase for both AUC and FROC for sentinel nodes, and an increase of 11% in AUC and 49% in FROC for axillary nodes. Pathologist qualitative evaluation of the retrained model´s output showed no missed positive slides. False positives, false negatives and one previously undetected micro-metastasis were observed. The study highlights the generalization challenge even when using a multicenter trained model, and that a small change in indication can considerably impact the model´s performance.
      pubtype: Academic Journal
      doctype:
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N