File Download

There are no files associated with this item.

Supplementary

Conference Paper: Direct Pathology Detection and Characterization from MR K-Space Data Using Deep Learning

TitleDirect Pathology Detection and Characterization from MR K-Space Data Using Deep Learning
Authors
Issue Date2020
PublisherInternational Society of Magnetic Resonance Imaging (ISMRM) .
Citation
Proceedings of the 28th Annual Meeting & Exhibition of the International Society for Magnetic Resonance in Medicine (ISMRM), Virtual Conference, 8-14 August 2020, paper no. 3530 How to Cite?
AbstractPresent MRI diagnosis comprises two steps: (i) reconstruction of multi-slice 2D or 3D images from k-space data; and (ii) pathology identification from images. In this study, we propose a strategy of direct pathology detection and characterization from MR k-space data through deep learning. This concept bypasses the traditional MR image reconstruction prior to pathology diagnosis, and presents an alternative MR diagnostic paradigm that may lead to potentially more powerful new tools for automatic and effective pathology screening, detection and characterization. Our simulation results demonstrated that this image-free strategy could detect brain tumors and their sizes/locations with high sensitivity and specificity.
DescriptionDigital Poster Session: Acquisition, Reconstruction & Analysis: ML: Post Processing, Analysis, & Applications: Machine Learning: Disease, Diagnosis, Pathology & Treatment - paper no. 3530
Persistent Identifierhttp://hdl.handle.net/10722/289406

 

DC FieldValueLanguage
dc.contributor.authorXiao, L-
dc.contributor.authorLiu, Y-
dc.contributor.authorZeng, P-
dc.contributor.authorLyu, M-
dc.contributor.authorMa, X-
dc.contributor.authorLeong, TL-
dc.contributor.authorWu, EX-
dc.date.accessioned2020-10-22T08:12:12Z-
dc.date.available2020-10-22T08:12:12Z-
dc.date.issued2020-
dc.identifier.citationProceedings of the 28th Annual Meeting & Exhibition of the International Society for Magnetic Resonance in Medicine (ISMRM), Virtual Conference, 8-14 August 2020, paper no. 3530-
dc.identifier.urihttp://hdl.handle.net/10722/289406-
dc.descriptionDigital Poster Session: Acquisition, Reconstruction & Analysis: ML: Post Processing, Analysis, & Applications: Machine Learning: Disease, Diagnosis, Pathology & Treatment - paper no. 3530-
dc.description.abstractPresent MRI diagnosis comprises two steps: (i) reconstruction of multi-slice 2D or 3D images from k-space data; and (ii) pathology identification from images. In this study, we propose a strategy of direct pathology detection and characterization from MR k-space data through deep learning. This concept bypasses the traditional MR image reconstruction prior to pathology diagnosis, and presents an alternative MR diagnostic paradigm that may lead to potentially more powerful new tools for automatic and effective pathology screening, detection and characterization. Our simulation results demonstrated that this image-free strategy could detect brain tumors and their sizes/locations with high sensitivity and specificity.-
dc.languageeng-
dc.publisherInternational Society of Magnetic Resonance Imaging (ISMRM) .-
dc.relation.ispartofProceedings of International Society of Magnetic Resonance in Medicine (ISMRM) Virtual Conference, 2020-
dc.titleDirect Pathology Detection and Characterization from MR K-Space Data Using Deep Learning-
dc.typeConference_Paper-
dc.identifier.emailLeong, TL: tlleong@hku.hk-
dc.identifier.emailWu, EX: ewu@eee.hku.hk-
dc.identifier.authorityLeong, TL=rp02483-
dc.identifier.authorityWu, EX=rp00193-
dc.identifier.hkuros316615-
dc.identifier.spage3530-
dc.identifier.epage3530-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats