File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Automatic Brain Tumor Segmentation with Domain Adaptation

TitleAutomatic Brain Tumor Segmentation with Domain Adaptation
Authors
KeywordsBrain tumor
Confusion loss
Domain adaptation
Encoder-decoder network
Segmentation
Issue Date2019
PublisherSpringer. The proceedings' web site is located at https://www.springer.com/gp/book/9783030117252
Citation
4th International MICCAI Brainlesion Workshop: Brain-Lesion Workshop (BrainLes), in conjunction with Medical Image Computing for Computer Assisted Intervention (MICCAI) Conference 2018, Granada, Spain, 16-20 September 2018, Revised Selected Papers, Part II. In Crimi, A ... (et al) (eds.), Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (BrainLes 2018), p. 380-392. Cham: Springer, 2019 How to Cite?
AbstractDeep convolution neural networks, in particular, the encoder-decoder networks, have been extensively used in image segmentation. We develop a deep learning approach for tumor segmentation by combining a modified U-Net and its domain-adapted version (DAU-Net). We divide training samples into two domains according to preliminary segmentation results, and then equip the modified U-Net with domain adaptation structure to obtain a domain invariant feature representation. Our proposed segmentation approach is applied to the BraTS 2018 challenge for brain tumor segmentation, and achieves the mean dice score of 0.91044, 0.85057 and 0.80536 for whole tumor, tumor core and enhancing tumor, respectively, on the challenge’s validation data set.
Persistent Identifierhttp://hdl.handle.net/10722/278803
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
ISI Accession Number ID
Series/Report no.Lecture Notes in Computer Science ; v. 11384

 

DC FieldValueLanguage
dc.contributor.authorDai, L-
dc.contributor.authorLi, T-
dc.contributor.authorShu, H-
dc.contributor.authorZhong, L-
dc.contributor.authorShen, H-
dc.contributor.authorZhu, H-
dc.date.accessioned2019-10-21T02:14:20Z-
dc.date.available2019-10-21T02:14:20Z-
dc.date.issued2019-
dc.identifier.citation4th International MICCAI Brainlesion Workshop: Brain-Lesion Workshop (BrainLes), in conjunction with Medical Image Computing for Computer Assisted Intervention (MICCAI) Conference 2018, Granada, Spain, 16-20 September 2018, Revised Selected Papers, Part II. In Crimi, A ... (et al) (eds.), Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (BrainLes 2018), p. 380-392. Cham: Springer, 2019-
dc.identifier.isbn978-3-030-11725-2-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/278803-
dc.description.abstractDeep convolution neural networks, in particular, the encoder-decoder networks, have been extensively used in image segmentation. We develop a deep learning approach for tumor segmentation by combining a modified U-Net and its domain-adapted version (DAU-Net). We divide training samples into two domains according to preliminary segmentation results, and then equip the modified U-Net with domain adaptation structure to obtain a domain invariant feature representation. Our proposed segmentation approach is applied to the BraTS 2018 challenge for brain tumor segmentation, and achieves the mean dice score of 0.91044, 0.85057 and 0.80536 for whole tumor, tumor core and enhancing tumor, respectively, on the challenge’s validation data set.-
dc.languageeng-
dc.publisherSpringer. The proceedings' web site is located at https://www.springer.com/gp/book/9783030117252-
dc.relation.ispartof4th International MICCAI Brainlesion Workshop, BrainLes 2018-
dc.relation.ispartofseriesLecture Notes in Computer Science ; v. 11384-
dc.subjectBrain tumor-
dc.subjectConfusion loss-
dc.subjectDomain adaptation-
dc.subjectEncoder-decoder network-
dc.subjectSegmentation-
dc.titleAutomatic Brain Tumor Segmentation with Domain Adaptation-
dc.typeConference_Paper-
dc.identifier.emailShen, H: haipeng@hku.hk-
dc.identifier.authorityShen, H=rp02082-
dc.identifier.doi10.1007/978-3-030-11726-9_34-
dc.identifier.scopuseid_2-s2.0-85063466383-
dc.identifier.hkuros307577-
dc.identifier.spage380-
dc.identifier.epage392-
dc.identifier.eissn1611-3349-
dc.identifier.isiWOS:000612997700034-
dc.publisher.placeCham-
dc.identifier.issnl0302-9743-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats