File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: 3D Dissimilar-Siamese-U-Net for hyperdense middle cerebral artery sign segmentation

Title3D Dissimilar-Siamese-U-Net for hyperdense middle cerebral artery sign segmentation
Authors
KeywordsAcute ischemic stroke
Hyperdense Middle cerebral artery sign
Segmentation
Deep learning
Issue Date2021
PublisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/compmedimag
Citation
Computerized Medical Imaging and Graphics, 2021, v. 90, p. article no. 101898 How to Cite?
AbstractThe hyperdense middle cerebral artery sign (HMCAS) representing a thromboembolus has been declared as a vital CT finding for intravascular thrombus in the diagnosis of acute ischemia stroke. Early recognition of HMCAS can assist in patient triage and subsequent thrombolysis or thrombectomy treatment. A total of 624 annotated head non-contrast-enhanced CT (NCCT) image scans were retrospectively collected from multiple public hospitals in Hong Kong. In this study, we present a deep Dissimilar-Siamese-U-Net (DSU-Net) that is able to precisely segment the lesions by integrating Siamese and U-Net architectures. The proposed framework consists of twin sub-networks that allow inputs of left and right hemispheres in head NCCT images separately. The proposed Dissimilar block fully explores the feature representation of the differences between the bilateral hemispheres. Ablation studies were carried out to validate the performance of various components of the proposed DSU-Net. Our findings reveal that the proposed DSU-Net provides a novel approach for HMCAS automatic segmentation and it outperforms the baseline U-Net and many state-of-the-art models for clinical practice.
Persistent Identifierhttp://hdl.handle.net/10722/299120
ISSN
2020 Impact Factor: 4.79
2020 SCImago Journal Rankings: 1.033
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYOU, J-
dc.contributor.authorYu, PLH-
dc.contributor.authorTsang, ACO-
dc.contributor.authorTsui, ELH-
dc.contributor.authorWoo, PPS-
dc.contributor.authorLui, CSM-
dc.contributor.authorLeung, GKK-
dc.contributor.authorMahboobani, N-
dc.contributor.authorChu, CY-
dc.contributor.authorChong, WH-
dc.contributor.authorPoon, WL-
dc.date.accessioned2021-04-28T02:26:27Z-
dc.date.available2021-04-28T02:26:27Z-
dc.date.issued2021-
dc.identifier.citationComputerized Medical Imaging and Graphics, 2021, v. 90, p. article no. 101898-
dc.identifier.issn0895-6111-
dc.identifier.urihttp://hdl.handle.net/10722/299120-
dc.description.abstractThe hyperdense middle cerebral artery sign (HMCAS) representing a thromboembolus has been declared as a vital CT finding for intravascular thrombus in the diagnosis of acute ischemia stroke. Early recognition of HMCAS can assist in patient triage and subsequent thrombolysis or thrombectomy treatment. A total of 624 annotated head non-contrast-enhanced CT (NCCT) image scans were retrospectively collected from multiple public hospitals in Hong Kong. In this study, we present a deep Dissimilar-Siamese-U-Net (DSU-Net) that is able to precisely segment the lesions by integrating Siamese and U-Net architectures. The proposed framework consists of twin sub-networks that allow inputs of left and right hemispheres in head NCCT images separately. The proposed Dissimilar block fully explores the feature representation of the differences between the bilateral hemispheres. Ablation studies were carried out to validate the performance of various components of the proposed DSU-Net. Our findings reveal that the proposed DSU-Net provides a novel approach for HMCAS automatic segmentation and it outperforms the baseline U-Net and many state-of-the-art models for clinical practice.-
dc.languageeng-
dc.publisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/compmedimag-
dc.relation.ispartofComputerized Medical Imaging and Graphics-
dc.subjectAcute ischemic stroke-
dc.subjectHyperdense Middle cerebral artery sign-
dc.subjectSegmentation-
dc.subjectDeep learning-
dc.title3D Dissimilar-Siamese-U-Net for hyperdense middle cerebral artery sign segmentation-
dc.typeArticle-
dc.identifier.emailYu, PLH: plhyu@hku.hk-
dc.identifier.emailTsang, ACO: acotsang@hku.hk-
dc.identifier.emailLeung, GKK: gkkleung@hku.hk-
dc.identifier.authorityYu, PLH=rp00835-
dc.identifier.authorityTsang, ACO=rp01519-
dc.identifier.authorityLeung, GKK=rp00522-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.compmedimag.2021.101898-
dc.identifier.pmid33857830-
dc.identifier.scopuseid_2-s2.0-85103978344-
dc.identifier.hkuros322178-
dc.identifier.volume90-
dc.identifier.spagearticle no. 101898-
dc.identifier.epagearticle no. 101898-
dc.identifier.isiWOS:000657592100004-
dc.publisher.placeUnited Kingdom-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats