uu.seUppsala universitets publikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Detection of Breast Tumour Tissue Regions in Histopathological Images using Convolutional Neural Networks
QMUL, EECS, London, England.
QMUL, EECS, London, England.
Karolinska Inst, Dept Oncol Pathol, Stockholm, Sweden.
Karolinska Univ Hosp, Dept Clin Pathol Cytol, Stockholm, Sweden.
Vise andre og tillknytning
2018 (engelsk)Inngår i: 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS), IEEE, 2018, s. 98-103Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Ductal carcinoma in situ (DCIS) is considered a pre-invasive breast cancer and sometimes it can develop into an invasive ductal carcinoma. The analysis of histopathological images to detect tumour border of DCIS could provide important information for better diagnosis of patients. We present a deep learning based system to automatically identify DCIS in histopathological images. Specifically, a convolutional neural network (CNN) is first trained to predict labels of small patches cropped out of a histopathological whole slide image. Next, a sliding window method is used to produce a probability map of DCIS. Finally, given the probability map, a tumor border of DCIS is produced and delineated with the method of Marching Cubes to facilitate pathologists' review and assessment. Evaluation of cross validation demonstrates that the CNN model of GoogleNet performs well in histology image patch classification with an overall accuracy of (98.46 +/- 0.40)% and identifies the DCIS tissue patches with a Fl-score of (97.40 +/- 1.18)% (mean +/- variance). Moreover, around 95.6% tumour tissue within the enclosed tumour regions can be identified by our developed method. Finally, the goal of tumor border detection can be well achieved with a few post-processing steps.

sted, utgiver, år, opplag, sider
IEEE, 2018. s. 98-103
Emneord [en]
Histopathological Images Analysis, Convolutional Neural Network, Tumour Border Detection, Ductal Carcinoma in Situ (DCIS)
HSV kategori
Identifikatorer
URN: urn:nbn:se:uu:diva-390019DOI: 10.1109/IPAS.2018.8708869ISI: 000471844500017ISBN: 978-1-7281-0247-4 (digital)OAI: oai:DiVA.org:uu-390019DiVA, id: diva2:1340190
Konferanse
3rd IEEE International Conference on Image Processing, Applications and Systems (IPAS), Inria Sophia Antipolis, France, December 12-14, 2018
Tilgjengelig fra: 2019-08-02 Laget: 2019-08-02 Sist oppdatert: 2019-08-02bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekst

Personposter BETA

Wärnberg, Fredrik

Søk i DiVA

Av forfatter/redaktør
Wärnberg, Fredrik
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 6 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf