dc.contributor.author
Aubreville, Marc
dc.contributor.author
Bertram, Christof A.
dc.contributor.author
Marzahl, Christian
dc.contributor.author
Gurtner, Corinne
dc.contributor.author
Dettwiler, Martina
dc.contributor.author
Bartenschlager, Florian
dc.contributor.author
Merz, Sophie
dc.contributor.author
Fragoso, Marco
dc.contributor.author
Kershaw, Olivia
dc.contributor.author
Klopfleisch, Robert
dc.date.accessioned
2020-11-16T12:43:37Z
dc.date.available
2020-11-16T12:43:37Z
dc.identifier.uri
https://refubium.fu-berlin.de/handle/fub188/28878
dc.identifier.uri
http://dx.doi.org/10.17169/refubium-28627
dc.description.abstract
Manual count of mitotic figures, which is determined in the tumor region with the highest mitotic activity, is a key parameter of most tumor grading schemes. It can be, however, strongly dependent on the area selection due to uneven mitotic figure distribution in the tumor section. We aimed to assess the question, how significantly the area selection could impact the mitotic count, which has a known high inter-rater disagreement. On a data set of 32 whole slide images of H&E-stained canine cutaneous mast cell tumor, fully annotated for mitotic figures, we asked eight veterinary pathologists (five board-certified, three in training) to select a field of interest for the mitotic count. To assess the potential difference on the mitotic count, we compared the mitotic count of the selected regions to the overall distribution on the slide. Additionally, we evaluated three deep learning-based methods for the assessment of highest mitotic density: In one approach, the model would directly try to predict the mitotic count for the presented image patches as a regression task. The second method aims at deriving a segmentation mask for mitotic figures, which is then used to obtain a mitotic density. Finally, we evaluated a two-stage object-detection pipeline based on state-of-the-art architectures to identify individual mitotic figures. We found that the predictions by all models were, on average, better than those of the experts. The two-stage object detector performed best and outperformed most of the human pathologists on the majority of tumor cases. The correlation between the predicted and the ground truth mitotic count was also best for this approach (0.963-0.979). Further, we found considerable differences in position selection between pathologists, which could partially explain the high variance that has been reported for the manual mitotic count. To achieve better interrater agreement, we propose to use a computer-based area selection for support of the pathologist in the manual mitotic count.
en
dc.format.extent
11 Seiten
dc.rights.uri
https://creativecommons.org/licenses/by/4.0/
dc.subject
digital image-analysis
en
dc.subject
breast-cancer
en
dc.subject
mitosis detection
en
dc.subject
proliferation
en
dc.subject
heterogeneity
en
dc.subject.ddc
600 Technik, Medizin, angewandte Wissenschaften::630 Landwirtschaft::630 Landwirtschaft und verwandte Bereiche
dc.title
Deep learning algorithms out-perform veterinary pathologists in detecting the mitotically most active tumor region
dc.type
Wissenschaftlicher Artikel
dcterms.bibliographicCitation.articlenumber
16447
dcterms.bibliographicCitation.doi
10.1038/s41598-020-73246-2
dcterms.bibliographicCitation.journaltitle
Scientific Reports
dcterms.bibliographicCitation.number
1
dcterms.bibliographicCitation.volume
10
dcterms.bibliographicCitation.url
https://doi.org/10.1038/s41598-020-73246-2
refubium.affiliation
Veterinärmedizin
refubium.affiliation.other
Institut für Tierpathologie
refubium.resourceType.isindependentpub
no
dcterms.accessRights.openaire
open access
dcterms.isPartOf.eissn
2045-2322
refubium.resourceType.provider
WoS-Alert