Matches in SemOpenAlex for { <https://semopenalex.org/work/W2978920910> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2978920910 abstract "In this work, we attempt the segmentation of cardiac structures in late gadolinium-enhanced (LGE) magnetic resonance images (MRI) using only minimal supervision in a two-step approach. In the first step, we register a small set of five LGE cardiac magnetic resonance (CMR) images with ground truth labels to a set of 40 target LGE CMR images without annotation. Each manually annotated ground truth provides labels of the myocardium and the left ventricle (LV) and right ventricle (RV) cavities, which are used as atlases. After multi-atlas label fusion by majority voting, we possess noisy labels for each of the targeted LGE images. A second set of manual labels exists for 30 patients of the target LGE CMR images, but are annotated on different MRI sequences (bSSFP and T2-weighted). Again, we use multi-atlas label fusion with a consistency constraint to further refine our noisy labels if additional annotations in other modalities are available for a given patient. In the second step, we train a deep convolutional network for semantic segmentation on the target data while using data augmentation techniques to avoid over-fitting to the noisy labels. After inference and simple post-processing, we achieve our final segmentation for the targeted LGE CMR images, resulting in an average Dice of 0.890, 0.780, and 0.844 for LV cavity, LV myocardium, and RV cavity, respectively." @default.
- W2978920910 created "2019-10-10" @default.
- W2978920910 creator A5031003824 @default.
- W2978920910 creator A5031854562 @default.
- W2978920910 creator A5039608149 @default.
- W2978920910 creator A5043710204 @default.
- W2978920910 creator A5052339079 @default.
- W2978920910 date "2019-10-02" @default.
- W2978920910 modified "2023-10-14" @default.
- W2978920910 title "Cardiac Segmentation of LGE MRI with Noisy Labels" @default.
- W2978920910 cites W1488403342 @default.
- W2978920910 cites W1667869507 @default.
- W2978920910 cites W2105456967 @default.
- W2978920910 cites W2107956652 @default.
- W2978920910 cites W2113576511 @default.
- W2978920910 cites W2152732304 @default.
- W2978920910 cites W2157380596 @default.
- W2978920910 cites W2194775991 @default.
- W2978920910 cites W2464708700 @default.
- W2978920910 cites W2525945566 @default.
- W2978920910 cites W2900237898 @default.
- W2978920910 cites W2962914239 @default.
- W2978920910 cites W2963046541 @default.
- W2978920910 cites W2769910914 @default.
- W2978920910 doi "https://doi.org/10.48550/arxiv.1910.01242" @default.
- W2978920910 hasPublicationYear "2019" @default.
- W2978920910 type Work @default.
- W2978920910 sameAs 2978920910 @default.
- W2978920910 citedByCount "0" @default.
- W2978920910 crossrefType "posted-content" @default.
- W2978920910 hasAuthorship W2978920910A5031003824 @default.
- W2978920910 hasAuthorship W2978920910A5031854562 @default.
- W2978920910 hasAuthorship W2978920910A5039608149 @default.
- W2978920910 hasAuthorship W2978920910A5043710204 @default.
- W2978920910 hasAuthorship W2978920910A5052339079 @default.
- W2978920910 hasBestOaLocation W29789209101 @default.
- W2978920910 hasConcept C126838900 @default.
- W2978920910 hasConcept C143409427 @default.
- W2978920910 hasConcept C146849305 @default.
- W2978920910 hasConcept C153180895 @default.
- W2978920910 hasConcept C154945302 @default.
- W2978920910 hasConcept C164705383 @default.
- W2978920910 hasConcept C2778921608 @default.
- W2978920910 hasConcept C31972630 @default.
- W2978920910 hasConcept C41008148 @default.
- W2978920910 hasConcept C71924100 @default.
- W2978920910 hasConcept C89600930 @default.
- W2978920910 hasConceptScore W2978920910C126838900 @default.
- W2978920910 hasConceptScore W2978920910C143409427 @default.
- W2978920910 hasConceptScore W2978920910C146849305 @default.
- W2978920910 hasConceptScore W2978920910C153180895 @default.
- W2978920910 hasConceptScore W2978920910C154945302 @default.
- W2978920910 hasConceptScore W2978920910C164705383 @default.
- W2978920910 hasConceptScore W2978920910C2778921608 @default.
- W2978920910 hasConceptScore W2978920910C31972630 @default.
- W2978920910 hasConceptScore W2978920910C41008148 @default.
- W2978920910 hasConceptScore W2978920910C71924100 @default.
- W2978920910 hasConceptScore W2978920910C89600930 @default.
- W2978920910 hasLocation W29789209101 @default.
- W2978920910 hasLocation W29789209102 @default.
- W2978920910 hasOpenAccess W2978920910 @default.
- W2978920910 hasPrimaryLocation W29789209101 @default.
- W2978920910 hasRelatedWork W1669643531 @default.
- W2978920910 hasRelatedWork W1982826852 @default.
- W2978920910 hasRelatedWork W2005437358 @default.
- W2978920910 hasRelatedWork W2008656436 @default.
- W2978920910 hasRelatedWork W2023558673 @default.
- W2978920910 hasRelatedWork W2110230079 @default.
- W2978920910 hasRelatedWork W2134924024 @default.
- W2978920910 hasRelatedWork W2517104666 @default.
- W2978920910 hasRelatedWork W2613186388 @default.
- W2978920910 hasRelatedWork W1967061043 @default.
- W2978920910 isParatext "false" @default.
- W2978920910 isRetracted "false" @default.
- W2978920910 magId "2978920910" @default.
- W2978920910 workType "article" @default.