File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Data Discernment for Affordable Training in Medical Image Segmentation

TitleData Discernment for Affordable Training in Medical Image Segmentation
Authors
Keywordsaffordable training
constrained nonlinear programming
Data discernment
medical image segmentation
Issue Date12-Dec-2022
PublisherInstitute of Electrical and Electronics Engineers
Citation
IEEE Transactions on Medical Imaging, 2023, v. 42, n. 5, p. 1431-1445 How to Cite?
AbstractCollecting sufficient high-quality training data for deep neural networks is often expensive or even unaffordable in medical image segmentation tasks. We thus propose to train the network by using external data that can be collected in a cheaper way, e.g., crowd-sourcing. We show that by data discernment, the network is able to mine valuable knowledge from external data, even though the data distribution is very different from that of the original (internal) data. We discern the external data by learning an importance weight for each of them, with the goal to enhance the contribution of informative external data to network updating, while suppressing the data that are 'useless' or even 'harmful'. An iterative algorithm that alternatively estimates the importance weight and updates the network is developed by formulating the data discernment as a constrained nonlinear programming problem. It estimates the importance weight according to the distribution discrepancy between the external data and the internal dataset, and imposes a constraint to drive the network to learn more effectively, compared with the network without using the external data. We evaluate the proposed algorithm on two tasks: abdominal CT image and cervical smear image segmentation, using totally 6 publicly available datasets. The effectiveness of the algorithm is demonstrated by extensive experiments. Source codes are available at: https://github.com/YouyiSong/Data-Discernment.
Persistent Identifierhttp://hdl.handle.net/10722/331043
ISSN
2023 Impact Factor: 8.9
2023 SCImago Journal Rankings: 3.703
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorSong, Y-
dc.contributor.authorYu, L-
dc.contributor.authorLei, B-
dc.contributor.authorChoi, KS-
dc.contributor.authorQin, J-
dc.date.accessioned2023-09-21T06:52:17Z-
dc.date.available2023-09-21T06:52:17Z-
dc.date.issued2022-12-12-
dc.identifier.citationIEEE Transactions on Medical Imaging, 2023, v. 42, n. 5, p. 1431-1445-
dc.identifier.issn0278-0062-
dc.identifier.urihttp://hdl.handle.net/10722/331043-
dc.description.abstractCollecting sufficient high-quality training data for deep neural networks is often expensive or even unaffordable in medical image segmentation tasks. We thus propose to train the network by using external data that can be collected in a cheaper way, e.g., crowd-sourcing. We show that by data discernment, the network is able to mine valuable knowledge from external data, even though the data distribution is very different from that of the original (internal) data. We discern the external data by learning an importance weight for each of them, with the goal to enhance the contribution of informative external data to network updating, while suppressing the data that are 'useless' or even 'harmful'. An iterative algorithm that alternatively estimates the importance weight and updates the network is developed by formulating the data discernment as a constrained nonlinear programming problem. It estimates the importance weight according to the distribution discrepancy between the external data and the internal dataset, and imposes a constraint to drive the network to learn more effectively, compared with the network without using the external data. We evaluate the proposed algorithm on two tasks: abdominal CT image and cervical smear image segmentation, using totally 6 publicly available datasets. The effectiveness of the algorithm is demonstrated by extensive experiments. Source codes are available at: https://github.com/YouyiSong/Data-Discernment.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers-
dc.relation.ispartofIEEE Transactions on Medical Imaging-
dc.subjectaffordable training-
dc.subjectconstrained nonlinear programming-
dc.subjectData discernment-
dc.subjectmedical image segmentation-
dc.titleData Discernment for Affordable Training in Medical Image Segmentation-
dc.typeArticle-
dc.identifier.doi10.1109/TMI.2022.3228316-
dc.identifier.scopuseid_2-s2.0-85144749653-
dc.identifier.volume42-
dc.identifier.issue5-
dc.identifier.spage1431-
dc.identifier.epage1445-
dc.identifier.eissn1558-254X-
dc.identifier.isiWOS:000982483400017-
dc.identifier.issnl0278-0062-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats