File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Deep Neural Network with Consistency Regularization of Multi-Output Channels for Improved Tumor Detection and Delineation

TitleDeep Neural Network with Consistency Regularization of Multi-Output Channels for Improved Tumor Detection and Delineation
Authors
KeywordsArtificial intelligence
Cancer detection
Neural networks
Regularization
Residual learning // Segmentation
Issue Date2021
PublisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at https://ieee-tmi.org/
Citation
IEEE Transactions on Medical Imaging, 2021, v. 40 n. 12, p. 3369-3378 How to Cite?
AbstractDeep learning is becoming an indispensable tool for imaging applications, such as image segmentation, classification, and detection. In this work, we reformulate a standard deep learning problem into a new neural network architecture with multi-output channels, which reflects different facets of the objective, and apply the deep neural network to improve the performance of image segmentation. By adding one or more interrelated auxiliary-output channels, we impose an effective consistency regularization for the main task of pixelated classification (i.e., image segmentation). Specifically, multi-output-channel consistency regularization is realized by residual learning via additive paths that connect main-output channel and auxiliary-output channels in the network. The method is evaluated on the detection and delineation of lung and liver tumors with public data. The results clearly show that multi-output-channel consistency implemented by residual learning improves the standard deep neural network. The proposed framework is quite broad and should find widespread applications in various deep learning problems.
Persistent Identifierhttp://hdl.handle.net/10722/304010
ISSN
2023 Impact Factor: 8.9
2023 SCImago Journal Rankings: 3.703
PubMed Central ID
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorSeo, H-
dc.contributor.authorYu, L-
dc.contributor.authorRen, H-
dc.contributor.authorLi, X-
dc.contributor.authorShen, L-
dc.contributor.authorXing, L-
dc.date.accessioned2021-09-23T08:53:58Z-
dc.date.available2021-09-23T08:53:58Z-
dc.date.issued2021-
dc.identifier.citationIEEE Transactions on Medical Imaging, 2021, v. 40 n. 12, p. 3369-3378-
dc.identifier.issn0278-0062-
dc.identifier.urihttp://hdl.handle.net/10722/304010-
dc.description.abstractDeep learning is becoming an indispensable tool for imaging applications, such as image segmentation, classification, and detection. In this work, we reformulate a standard deep learning problem into a new neural network architecture with multi-output channels, which reflects different facets of the objective, and apply the deep neural network to improve the performance of image segmentation. By adding one or more interrelated auxiliary-output channels, we impose an effective consistency regularization for the main task of pixelated classification (i.e., image segmentation). Specifically, multi-output-channel consistency regularization is realized by residual learning via additive paths that connect main-output channel and auxiliary-output channels in the network. The method is evaluated on the detection and delineation of lung and liver tumors with public data. The results clearly show that multi-output-channel consistency implemented by residual learning improves the standard deep neural network. The proposed framework is quite broad and should find widespread applications in various deep learning problems.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at https://ieee-tmi.org/-
dc.relation.ispartofIEEE Transactions on Medical Imaging-
dc.rightsIEEE Transactions on Medical Imaging. Copyright © Institute of Electrical and Electronics Engineers.-
dc.rights©2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectArtificial intelligence-
dc.subjectCancer detection-
dc.subjectNeural networks-
dc.subjectRegularization-
dc.subjectResidual learning // Segmentation-
dc.titleDeep Neural Network with Consistency Regularization of Multi-Output Channels for Improved Tumor Detection and Delineation-
dc.typeArticle-
dc.identifier.emailYu, L: lqyu@hku.hk-
dc.identifier.authorityYu, L=rp02814-
dc.description.naturepostprint-
dc.identifier.doi10.1109/TMI.2021.3084748-
dc.identifier.pmid34048339-
dc.identifier.pmcidPMC8692166-
dc.identifier.scopuseid_2-s2.0-85107193146-
dc.identifier.hkuros325076-
dc.identifier.volume40-
dc.identifier.issue12-
dc.identifier.spage3369-
dc.identifier.epage3378-
dc.identifier.isiWOS:000724511900011-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats