Show simple item record

dc.contributor.authorChen, Feiyang
dc.contributor.authorJiang, Ying
dc.contributor.authorZeng, Xiangrui
dc.contributor.authorZhang, Jing
dc.contributor.authorGao, Xin
dc.contributor.authorXu, Min
dc.date.accessioned2020-05-21T10:50:59Z
dc.date.available2020-05-21T10:50:59Z
dc.date.issued2020-05-19
dc.date.submitted2020-04-19
dc.identifier.citationChen, F., Jiang, Y., Zeng, X., Zhang, J., Gao, X., & Xu, M. (2020). PUB-SalNet: A Pre-Trained Unsupervised Self-Aware Backpropagation Network for Biomedical Salient Segmentation. Algorithms, 13(5), 126. doi:10.3390/a13050126
dc.identifier.issn1999-4893
dc.identifier.doi10.3390/a13050126
dc.identifier.urihttp://hdl.handle.net/10754/662899
dc.description.abstractSalient segmentation is a critical step in biomedical image analysis, aiming to cut out regions that are most interesting to humans. Recently, supervised methods have achieved promising results in biomedical areas, but they depend on annotated training data sets, which requires labor and proficiency in related background knowledge. In contrast, unsupervised learning makes data-driven decisions by obtaining insights directly from the data themselves. In this paper, we propose a completely unsupervised self-aware network based on pre-training and attentional backpropagation for biomedical salient segmentation, named as PUB-SalNet. Firstly, we aggregate a new biomedical data set from several simulated Cellular Electron Cryo-Tomography (CECT) data sets featuring rich salient objects, different SNR settings, and various resolutions, which is called SalSeg-CECT. Based on the SalSeg-CECT data set, we then pre-train a model specially designed for biomedical tasks as a backbone module to initialize network parameters. Next, we present a U-SalNet network to learn to selectively attend to salient objects. It includes two types of attention modules to facilitate learning saliency through global contrast and local similarity. Lastly, we jointly refine the salient regions together with feature representations from U-SalNet, with the parameters updated by self-aware attentional backpropagation. We apply PUB-SalNet for analysis of 2D simulated and real images and achieve state-of-the-art performance on simulated biomedical data sets. Furthermore, our proposed PUB-SalNet can be easily extended to 3D images. The experimental results on the 2d and 3d data sets also demonstrate the generalization ability and robustness of our method.
dc.description.sponsorshipThis work was supported in part by U.S. National Institutes of Health (NIH) grant P41 GM103712. This work was supported by U.S. National Science Foundation (NSF) grants DBI-1949629 and IIS-2007595. X.Z. was supported by a fellowship from Carnegie Mellon University’s Center for Machine Learning and Health. This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. URF/1/2602-01 and URF/1/3007-01.
dc.publisherMDPI AG
dc.relation.urlhttps://www.mdpi.com/1999-4893/13/5/126
dc.relation.urlhttps://www.mdpi.com/1999-4893/13/5/126/pdf
dc.rightsThis article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titlePUB-SalNet: A Pre-Trained Unsupervised Self-Aware Backpropagation Network for Biomedical Salient Segmentation
dc.typeArticle
dc.contributor.departmentComputational Bioscience Research Center (CBRC)
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentStructural and Functional Bioinformatics Group
dc.identifier.journalAlgorithms
dc.eprint.versionPublisher's Version/PDF
dc.contributor.institutionCompututational Biology Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
dc.contributor.institutionDepartment of Computer Science, University of California Irvine, Irvine, CA 92697, USA.
dc.identifier.volume13
dc.identifier.issue5
dc.identifier.pages126
kaust.personGao, Xin
kaust.grant.numberURF/1/2602-01
kaust.grant.numberURF/1/3007-01
dc.date.accepted2020-05-15
refterms.dateFOA2020-05-21T10:51:47Z
kaust.acknowledged.supportUnitOffice of Sponsored Research
kaust.acknowledged.supportUnitOSR


Files in this item

Thumbnail
Name:
Articlefile1.pdf
Size:
4.842Mb
Format:
PDF
Description:
Publisher's Version/PDF

This item appears in the following Collection(s)

Show simple item record

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.
Except where otherwise noted, this item's license is described as This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.