Uncertainty-Guided Semi-Automated Editing of CNN-based Retinal Layer Segmentations in Optical Coherence Tomography

Simple item page
dc.contributor.authorZadeh, Shekoufeh Gorgien_US
dc.contributor.authorWintergerst, Maximilian W. M.en_US
dc.contributor.authorSchultz, Thomasen_US
dc.contributor.editorPuig Puig, Anna and Schultz, Thomas and Vilanova, Anna and Hotz, Ingrid and Kozlikova, Barbora and Vázquez, Pere-Pauen_US
dc.date.accessioned2018-09-19T15:19:29Z
dc.date.available2018-09-19T15:19:29Z
dc.date.issued2018
dc.description.abstractConvolutional neural networks (CNNs) have enabled dramatic improvements in the accuracy of automated medical image segmentation. Despite this, in many cases, results are still not reliable enough to be trusted ''blindly''. Consequently, a human rater is responsible to check correctness of the final result and needs to be able to correct any segmentation errors that he or she might notice. For a particular use case, segmentation of the retinal pigment epithelium and Bruch's membrane from Optical Coherence Tomography, we develop a system that makes this process more efficient by guiding the rater to segmentations that are most likely to require attention from a human expert, and by developing semi-automated tools for segmentation correction that exploit intermediate representations from the CNN.We demonstrate that our automated ranking of segmentation uncertainty correlates well with a manual assessment of segmentation quality, and with distance to a ground truth segmentation. We also show that, when used together, uncertainty guidance and our semi-automated editing tools decrease the time required for segmentation correction by more than a factor of three.en_US
dc.description.sectionheadersDeep Learning
dc.description.seriesinformationEurographics Workshop on Visual Computing for Biology and Medicine
dc.identifier.doi10.2312/vcbm.20181235
dc.identifier.isbn978-3-03868-056-7
dc.identifier.issn2070-5786
dc.identifier.pages107-115
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vcbm20181235
dc.identifier.urihttps://doi.org/10.2312/vcbm.20181235
dc.publisherThe Eurographics Associationen_US
dc.titleUncertainty-Guided Semi-Automated Editing of CNN-based Retinal Layer Segmentations in Optical Coherence Tomographyen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
107-115.pdf
Size:
2.68 MB
Format:
Adobe Portable Document Format
Download
Collections
VCBM 18: Eurographics Workshop on Visual Computing for Biology and Medicine