HistoContours: a Framework for Visual Annotation of Histopathology Whole Slide Images

Simple item page
dc.contributor.authorAl-Thelaya, Khaleden_US
dc.contributor.authorJoad, Faaizen_US
dc.contributor.authorGilal, Nauman Ullahen_US
dc.contributor.authorMifsud, Williamen_US
dc.contributor.authorPintore, Giovannien_US
dc.contributor.authorGobbetti, Enricoen_US
dc.contributor.authorAgus, Marcoen_US
dc.contributor.authorSchneider, Jensen_US
dc.contributor.editorRenata G. Raidouen_US
dc.contributor.editorBjörn Sommeren_US
dc.contributor.editorTorsten W. Kuhlenen_US
dc.contributor.editorMichael Kroneen_US
dc.contributor.editorThomas Schultzen_US
dc.contributor.editorHsiang-Yun Wuen_US
dc.date.accessioned2022-09-19T11:46:32Z
dc.date.available2022-09-19T11:46:32Z
dc.date.issued2022
dc.description.abstractWe present an end-to-end framework for histopathological analysis of whole slide images (WSIs). Our framework uses deep learning-based localization & classification of cell nuclei followed by spatial data aggregation to propagate classes of sparsely distributed nuclei across the entire slide. We use YOLO (''You Only Look Once'') for localization instead of more costly segmentation approaches and show that using HistAuGAN boosts its performance. YOLO finds bounding boxes around nuclei at good accuracy, but the classification accuracy can be improved by other methods. To this end, we extract patches around nuclei from the WSI and consider models from the SqueezeNet, ResNet, and EfficientNet families for classification. Where we do not achieve a clear separation between highest and second-highest softmax activation of the classifier, we use YOLO's output as a secondary vote. The result is a sparse annotation of the WSI, which we turn dense by using kernel density estimation. The result is a full vector of per pixel probabilities for each class of nucleus we consider. This allows us to visualize our results using both color-coding and isocontouring, reducing visual clutter. Our novel nuclei-to-tissue coupling allows histopathologists to work at both the nucleus and the tissue level, a feature appreciated by domain experts in a qualitative user study.en_US
dc.description.sectionheadersVisual Analytics, Artificial Intelligence
dc.description.seriesinformationEurographics Workshop on Visual Computing for Biology and Medicine
dc.identifier.doi10.2312/vcbm.20221192
dc.identifier.isbn978-3-03868-177-9
dc.identifier.issn2070-5786
dc.identifier.pages99-109
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.2312/vcbm.20221192
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vcbm20221192
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Applied computing → Imaging; Computing methodologies → Object detection; Human-centered computing → Information visualization; Heat maps"
dc.subjectApplied computing → Imaging
dc.subjectComputing methodologies → Object detection
dc.subjectHuman
dc.subjectcentered computing → Information visualization
dc.subjectHeat maps"
dc.titleHistoContours: a Framework for Visual Annotation of Histopathology Whole Slide Imagesen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
099-109.pdf
Size:
24.22 MB
Format:
Adobe Portable Document Format
Download
Collections
VCBM 2022: Eurographics Workshop on Visual Computing for Biology and Medicine