FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200501385> ?p ?o ?g. }

• W3200501385 endingPage "106419" @default.
• W3200501385 startingPage "106419" @default.
• W3200501385 abstract "Accurately and reliably defining organs at risk (OARs) and tumors are the cornerstone of radiation therapy (RT) treatment planning for lung cancer. Almost all segmentation networks based on deep learning techniques rely on fully annotated data with strong supervision. However, existing public imaging datasets encountered in the RT domain frequently include singly labelled tumors or partially labelled organs because annotating full OARs and tumors in CT images is both rigorous and tedious. To utilize labelled data from different sources, we proposed a dual-path semi-supervised conditional nnU-Net for OARs and tumor segmentation that is trained on a union of partially labelled datasets. The framework employs the nnU-Net as the base model and introduces a conditioning strategy by incorporating auxiliary information as an additional input layer into the decoder. The conditional nnU-Net efficiently leverages prior conditional information to classify the target class at the pixelwise level. Specifically, we employ the uncertainty-aware mean teacher (UA-MT) framework to assist in OARs segmentation, which can effectively leverage unlabelled data (images from a tumor labelled dataset) by encouraging consistent predictions of the same input under different perturbations. Furthermore, we individually design different combinations of loss functions to optimize the segmentation of OARs (Dice loss and cross-entropy loss) and tumors (Dice loss and focal loss) in a dual path. The proposed method is evaluated on two publicly available datasets of the spinal cord, left and right lung, heart, esophagus, and lung tumor, in which satisfactory segmentation performance has been achieved in term of both the region-based Dice similarity coefficient (DSC) and the boundary-based Hausdorff distance (HD). The proposed semi-supervised conditional nnU-Net breaks down the barriers between nonoverlapping labelled datasets and further alleviates the problem of “data hunger” and “data waste” in multi-class segmentation. The method has the potential to help radiologists with RT treatment planning in clinical practice." @default.
• W3200501385 created "2021-09-27" @default.
• W3200501385 creator A5021742831 @default.
• W3200501385 creator A5051143140 @default.
• W3200501385 creator A5066201147 @default.
• W3200501385 creator A5078610546 @default.
• W3200501385 creator A5080038308 @default.
• W3200501385 date "2021-11-01" @default.
• W3200501385 modified "2023-10-12" @default.
• W3200501385 title "Automatic segmentation of organs at risk and tumors in CT images of lung cancer from partially labelled datasets with a semi-supervised conditional nnU-Net" @default.
• W3200501385 cites W1988832131 @default.
• W3200501385 cites W2002489794 @default.
• W3200501385 cites W2016980154 @default.
• W3200501385 cites W2037362135 @default.
• W3200501385 cites W2118867739 @default.
• W3200501385 cites W2124618551 @default.
• W3200501385 cites W2126446504 @default.
• W3200501385 cites W2143944233 @default.
• W3200501385 cites W2146629016 @default.
• W3200501385 cites W2339408475 @default.
• W3200501385 cites W2554446720 @default.
• W3200501385 cites W2586834759 @default.
• W3200501385 cites W2732063980 @default.
• W3200501385 cites W2777281076 @default.
• W3200501385 cites W2883311907 @default.
• W3200501385 cites W2907576408 @default.
• W3200501385 cites W2909032019 @default.
• W3200501385 cites W2920206089 @default.
• W3200501385 cites W2936000280 @default.
• W3200501385 cites W2947415482 @default.
• W3200501385 cites W2949100858 @default.
• W3200501385 cites W2954725015 @default.
• W3200501385 cites W2975354219 @default.
• W3200501385 cites W2979907638 @default.
• W3200501385 cites W3009005803 @default.
• W3200501385 cites W3048266091 @default.
• W3200501385 cites W3079451754 @default.
• W3200501385 cites W3083707308 @default.
• W3200501385 cites W3112701542 @default.
• W3200501385 doi "https://doi.org/10.1016/j.cmpb.2021.106419" @default.
• W3200501385 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34563895" @default.
• W3200501385 hasPublicationYear "2021" @default.
• W3200501385 type Work @default.
• W3200501385 sameAs 3200501385 @default.
• W3200501385 citedByCount "7" @default.
• W3200501385 countsByYear W32005013852022 @default.
• W3200501385 countsByYear W32005013852023 @default.
• W3200501385 crossrefType "journal-article" @default.
• W3200501385 hasAuthorship W3200501385A5021742831 @default.
• W3200501385 hasAuthorship W3200501385A5051143140 @default.
• W3200501385 hasAuthorship W3200501385A5066201147 @default.
• W3200501385 hasAuthorship W3200501385A5078610546 @default.
• W3200501385 hasAuthorship W3200501385A5080038308 @default.
• W3200501385 hasConcept C142724271 @default.
• W3200501385 hasConcept C153180895 @default.
• W3200501385 hasConcept C154945302 @default.
• W3200501385 hasConcept C2776256026 @default.
• W3200501385 hasConcept C41008148 @default.
• W3200501385 hasConcept C71924100 @default.
• W3200501385 hasConcept C89600930 @default.
• W3200501385 hasConceptScore W3200501385C142724271 @default.
• W3200501385 hasConceptScore W3200501385C153180895 @default.
• W3200501385 hasConceptScore W3200501385C154945302 @default.
• W3200501385 hasConceptScore W3200501385C2776256026 @default.
• W3200501385 hasConceptScore W3200501385C41008148 @default.
• W3200501385 hasConceptScore W3200501385C71924100 @default.
• W3200501385 hasConceptScore W3200501385C89600930 @default.
• W3200501385 hasFunder F4320321001 @default.
• W3200501385 hasLocation W32005013851 @default.
• W3200501385 hasLocation W32005013852 @default.
• W3200501385 hasOpenAccess W3200501385 @default.
• W3200501385 hasPrimaryLocation W32005013851 @default.
• W3200501385 hasRelatedWork W1507687735 @default.
• W3200501385 hasRelatedWork W2005476934 @default.
• W3200501385 hasRelatedWork W2061502286 @default.
• W3200501385 hasRelatedWork W2510758617 @default.
• W3200501385 hasRelatedWork W2753174232 @default.
• W3200501385 hasRelatedWork W2754350655 @default.
• W3200501385 hasRelatedWork W2897195263 @default.
• W3200501385 hasRelatedWork W3095523211 @default.
• W3200501385 hasRelatedWork W4206076898 @default.
• W3200501385 hasRelatedWork W4226401448 @default.
• W3200501385 hasVolume "211" @default.
• W3200501385 isParatext "false" @default.
• W3200501385 isRetracted "false" @default.
• W3200501385 magId "3200501385" @default.
• W3200501385 workType "article" @default.