Show simple item record

dc.contributor.authorMatula, Jan
dc.date.accessioned2020-04-16T07:19:30Z
dc.date.available2020-04-16T07:19:30Z
dc.date.issued2019cs
dc.identifier.citationProceedings of the 25st Conference STUDENT EEICT 2019. s. 191-194. ISBN 978-80-214-5735-5cs
dc.identifier.isbn978-80-214-5735-5
dc.identifier.urihttp://hdl.handle.net/11012/186650
dc.description.abstractManual segmentation of cartilage tissue in micro CT images of mouse embryos is a very time-consuming process and significantly increases the time required for the research of mammal facial structure development. It is possible to solve this problem by using a fully-automatic segmentation algorithm. In this paper, a fully-automatic segmentation method is proposed using a convolutional neural network trained on manually segmented data. The architecture of the proposed convolutional network is based on the U-Net architecture with its encoding part substituted for the encoding part of the VGG16 classification convolutional neural network pre-trained on the ImageNet database of labelled images. The proposed network achieves average Dice coefficient 0.88 in comparison to manually segmented images.en
dc.formattextcs
dc.format.extent191-194cs
dc.format.mimetypeapplication/pdfen
dc.language.isoencs
dc.publisherVysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologiícs
dc.relation.ispartofProceedings of the 25st Conference STUDENT EEICT 2019en
dc.relation.urihttp://www.feec.vutbr.cz/EEICT/cs
dc.rights© Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologiícs
dc.subjectsegmentationen
dc.subjectcartilageen
dc.subjectconvolutional neural networksen
dc.subjectdeep learningen
dc.titleSegmentation Of Cartilage Tissue In Micro Ct Images Of Mouse Embryos With Modified U-Net Convolutional Neural Networken
eprints.affiliatedInstitution.departmentFakulta elektrotechniky a komunikačních technologiícs
but.event.date25.04.2019cs
but.event.titleStudent EEICT 2019cs
dc.rights.accessopenAccessen
dc.type.driverconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record