EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Challenges Developing Deep Learning Algorithms in Cytology

Ewen David McAlpine, Liron Pantanowitz, Pamela M Michelow

Acta Cytologica · 2021 · 65 (4) · 301-309

DOI: 10.1159/000510991 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Acta Cytologica, online erschienen am 02.11.2020. Verfasst von Ewen David McAlpine und 2 weiteren Autor:innen. Beteiligte Einrichtung: Division of Anatomical Pathology, School of Pathology, University of the Witwatersrand and National Health Laboratory Service, Johannesburg, South Af…. Hauptthemen laut MEDLINE: Cytodiagnosis, Deep Learning, Diagnosis, Computer-Assisted, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 20 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background: The incorporation of digital pathology into routine pathology practice is becoming more widespread. Definite advantages exist with respect to the implementation of artificial intelligence (AI) and deep learning in pathology, including cytopathology. However, there are also unique challenges in this regard. Summary: This review discusses cytology-specific challenges, including the need to implement digital cytology prior to AI; the large file sizes and increased acquisition times for whole slide images in cytology; the routine use of multiple stains, such as Papanicolaou and Romanowsky stains; the lack of high-quality annotated datasets on which to train algorithms; and the considerable computer resources required, in terms of both computer infrastructure and skilled personnel, for computing and storage of data. Global concerns regarding AI that are certainly applicable to cytology include the need for model validation and continued quality assurance, ethical issues such as the use of patient data in developing algorithms, the need to develop regulatory frameworks regarding what type of data can be utilized and ensuring cybersecurity during data collection and storage, and algorithm development. Key Messages: While AI will likely play a role in cytology practice in the future, applying this technology to cytology poses a unique set of challenges. A broad understanding of digital pathology and algorithm development is desirable to guide the development of algorithms, as well as the need to be cognizant of potential pitfalls to avoid when incorporating the technology in practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CytodiagnosisDeep LearningDiagnosis, Computer-AssistedImage Interpretation, Computer-AssistedPathologyAutomation, LaboratoryComputer SecurityHumansPredictive Value of TestsQuality Indicators, Health CareReproducibility of Results

Stichwörter der Autor:innen

AlgorithmsArtificial intelligenceDeep learningDigital cytologyDigital pathology

Autor:innen und Institutionen

  • Division of Anatomical Pathology, School of Pathology, University of the Witwatersrand and National Health Laboratory Service, Johannesburg, South Africa, ewen.mcalpine@wits.ac.za.
  • Department of Pathology, University of Michigan, Ann Arbor, Michigan, USA.
  • Division of Anatomical Pathology, School of Pathology, University of the Witwatersrand and National Health Laboratory Service, Johannesburg, South Africa.

Zitieren

APA

McAlpine, E. D., Pantanowitz, L., & Michelow, P. M. (2021). Challenges Developing Deep Learning Algorithms in Cytology. Acta Cytologica, 65(4), 301-309. https://doi.org/10.1159/000510991

Vancouver

McAlpine ED, Pantanowitz L, Michelow PM. Challenges Developing Deep Learning Algorithms in Cytology. Acta Cytologica. 2021;65(4):301-309. doi:10.1159/000510991

BibTeX
@article{McAlpine2021,
  author = {McAlpine, Ewen David and Pantanowitz, Liron and Michelow, Pamela M},
  title = {Challenges Developing Deep Learning Algorithms in Cytology},
  journal = {Acta Cytologica},
  year = {2021},
  volume = {65},
  number = {4},
  pages = {301--309},
  doi = {10.1159/000510991}
}
Kostenlos starten →