File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: RECIST-Induced Reliable Learning: Geometry-Driven Label Propagation for Universal Lesion Segmentation

TitleRECIST-Induced Reliable Learning: Geometry-Driven Label Propagation for Universal Lesion Segmentation
Authors
KeywordsRECIST
semi-supervised learning
Universal lesion segmentation
weakly-supervised learning
Issue Date12-Jul-2023
PublisherInstitute of Electrical and Electronics Engineers
Citation
IEEE Transactions on Medical Imaging, 2023, v. 43, n. 1, p. 149-161 How to Cite?
AbstractAutomatic universal lesion segmentation (ULS) from Computed Tomography (CT) images can ease the burden of radiologists and provide a more accurate assessment than the current Response Evaluation Criteria In Solid Tumors (RECIST) guideline measurement. However, this task is underdeveloped due to the absence of large-scale pixel-wise labeled data. This paper presents a weakly-supervised learning framework to utilize the large-scale existing lesion databases in hospital Picture Archiving and Communication Systems (PACS) for ULS. Unlike previous methods to construct pseudo surrogate masks for fully supervised training through shallow interactive segmentation techniques, we propose to unearth the implicit information from RECIST annotations and thus design a unified RECIST-induced reliable learning (RiRL) framework. Particularly, we introduce a novel label generation procedure and an on-the-fly soft label propagation strategy to avoid noisy training and poor generalization problems. The former, named RECIST-induced geometric labeling, uses clinical characteristics of RECIST to preliminarily and reliably propagate the label. With the labeling process, a trimap divides the lesion slices into three regions, including certain foreground, background, and unclear regions, which consequently enables a strong and reliable supervision signal on a wide region. A topological knowledge-driven graph is built to conduct the on-the-fly label propagation for the optimal segmentation boundary to further optimize the segmentation boundary. Experimental results on a public benchmark dataset demonstrate that the proposed method surpasses the SOTA RECIST-based ULS methods by a large margin. Our approach surpasses SOTA approaches over 2.0%, 1.5%, 1.4%, and 1.6% Dice with ResNet101, ResNet50, HRNet, and ResNest50 backbones.
Persistent Identifierhttp://hdl.handle.net/10722/345766
ISSN
2023 Impact Factor: 8.9
2023 SCImago Journal Rankings: 3.703

 

DC FieldValueLanguage
dc.contributor.authorZhou, Lianyu-
dc.contributor.authorYu, Lequan-
dc.contributor.authorWang, Liansheng-
dc.date.accessioned2024-08-28T07:40:34Z-
dc.date.available2024-08-28T07:40:34Z-
dc.date.issued2023-07-12-
dc.identifier.citationIEEE Transactions on Medical Imaging, 2023, v. 43, n. 1, p. 149-161-
dc.identifier.issn0278-0062-
dc.identifier.urihttp://hdl.handle.net/10722/345766-
dc.description.abstractAutomatic universal lesion segmentation (ULS) from Computed Tomography (CT) images can ease the burden of radiologists and provide a more accurate assessment than the current Response Evaluation Criteria In Solid Tumors (RECIST) guideline measurement. However, this task is underdeveloped due to the absence of large-scale pixel-wise labeled data. This paper presents a weakly-supervised learning framework to utilize the large-scale existing lesion databases in hospital Picture Archiving and Communication Systems (PACS) for ULS. Unlike previous methods to construct pseudo surrogate masks for fully supervised training through shallow interactive segmentation techniques, we propose to unearth the implicit information from RECIST annotations and thus design a unified RECIST-induced reliable learning (RiRL) framework. Particularly, we introduce a novel label generation procedure and an on-the-fly soft label propagation strategy to avoid noisy training and poor generalization problems. The former, named RECIST-induced geometric labeling, uses clinical characteristics of RECIST to preliminarily and reliably propagate the label. With the labeling process, a trimap divides the lesion slices into three regions, including certain foreground, background, and unclear regions, which consequently enables a strong and reliable supervision signal on a wide region. A topological knowledge-driven graph is built to conduct the on-the-fly label propagation for the optimal segmentation boundary to further optimize the segmentation boundary. Experimental results on a public benchmark dataset demonstrate that the proposed method surpasses the SOTA RECIST-based ULS methods by a large margin. Our approach surpasses SOTA approaches over 2.0%, 1.5%, 1.4%, and 1.6% Dice with ResNet101, ResNet50, HRNet, and ResNest50 backbones.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers-
dc.relation.ispartofIEEE Transactions on Medical Imaging-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectRECIST-
dc.subjectsemi-supervised learning-
dc.subjectUniversal lesion segmentation-
dc.subjectweakly-supervised learning-
dc.titleRECIST-Induced Reliable Learning: Geometry-Driven Label Propagation for Universal Lesion Segmentation-
dc.typeArticle-
dc.identifier.doi10.1109/TMI.2023.3294824-
dc.identifier.pmid37436855-
dc.identifier.scopuseid_2-s2.0-85164687654-
dc.identifier.volume43-
dc.identifier.issue1-
dc.identifier.spage149-
dc.identifier.epage161-
dc.identifier.eissn1558-254X-
dc.identifier.issnl0278-0062-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats