SwePub
Sök i LIBRIS databas

  Utökad sökning

WFRF:(Lundström Karl)
 

Sökning: WFRF:(Lundström Karl) > Training nuclei det...

  • Kost, HenningFraunhofer-Institut fur Bildgestutzte Medizin MEVIS,Fraunhofer Mevis (författare)

Training nuclei detection algorithms with simple annotations

  • Artikel/kapitelEngelska2017

Förlag, utgivningsår, omfång ...

  • Elsevier BV,2017
  • electronicrdacarrier

Nummerbeteckningar

  • LIBRIS-ID:oai:research.chalmers.se:08b63972-dc92-47e0-9ef4-a9762bbc1531
  • https://research.chalmers.se/publication/508261URI
  • https://doi.org/10.4103/jpi.jpi_3_17DOI
  • https://research.chalmers.se/publication/254086URI
  • https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-140749URI

Kompletterande språkuppgifter

  • Språk:engelska
  • Sammanfattning på:engelska

Ingår i deldatabas

Klassifikation

  • Ämneskategori:art swepub-publicationtype
  • Ämneskategori:ref swepub-contenttype

Anmärkningar

  • Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. Methods: We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. Results: A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. Conclusions: With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.

Ämnesord och genrebeteckningar

Biuppslag (personer, institutioner, konferenser, titlar ...)

  • Homeyer, AndréFraunhofer-Institut fur Bildgestutzte Medizin MEVIS,Fraunhofer Mevis (författare)
  • Molin, Jesper,1987Sectra AB,Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)mjesper (författare)
  • Lundström, Claes,1973-Linköpings universitet,Medie- och Informationsteknik,Centrum för medicinsk bildvetenskap och visualisering, CMIV,Tekniska fakulteten(Swepub:liu)clalu03 (författare)
  • Hahn, Horst KarlFraunhofer-Institut fur Bildgestutzte Medizin MEVIS,Fraunhofer Mevis (författare)
  • Fraunhofer-Institut fur Bildgestutzte Medizin MEVISFraunhofer Mevis (creator_code:org_t)

Sammanhörande titlar

  • Ingår i:Journal of Pathology Informatics: Elsevier BV8:12229-50892153-3539

Internetlänk

Hitta via bibliotek

Till lärosätets databas

Sök utanför SwePub

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy