Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385954713> ?p ?o ?g. }
- W4385954713 abstract "Semantic segmentation is one of the most significant tasks in medical image computing, whereby deep neural networks have shown great success. Unfortunately, supervised approaches are very data-intensive, and obtaining reliable annotations is time-consuming and expensive. Sparsely labeled approaches, such as bounding boxes, have shown some success in reducing the annotation time. However, in 3D volume data, each slice must still be manually labeled.We evaluate approaches that reduce the annotation effort by reducing the number of slices that need to be labeled in a 3D volume. In a two-step process, a similarity metric is used to select slices that should be annotated by a trained radiologist. In the second step, a predictor is used to predict the segmentation mask for the rest of the slices. We evaluate different combinations of selectors and predictors on medical CT and MRI volumes. Thus we can determine that combination works best, and how far slice annotations can be reduced.Our results show that for instance for the Medical Segmentation Decathlon-heart dataset, some selector, and predictor combinations allow for a Dice score 0.969 when only annotating 20% of slices per volume. Experiments on other datasets show a similarly positive trend.We evaluate a method that supports experts during the labeling of 3D medical volumes. Our approach makes it possible to drastically reduce the number of slices that need to be manually labeled. We present a recommendation in which selector predictor combination to use for different tasks and goals." @default.
- W4385954713 created "2023-08-18" @default.
- W4385954713 creator A5010048557 @default.
- W4385954713 creator A5019206085 @default.
- W4385954713 creator A5055878070 @default.
- W4385954713 creator A5061059879 @default.
- W4385954713 creator A5082113824 @default.
- W4385954713 date "2023-08-17" @default.
- W4385954713 modified "2023-10-05" @default.
- W4385954713 title "Medical volume segmentation by overfitting sparsely annotated data" @default.
- W4385954713 cites W1535417994 @default.
- W4385954713 cites W1641498739 @default.
- W4385954713 cites W1683159118 @default.
- W4385954713 cites W1901129140 @default.
- W4385954713 cites W1981670016 @default.
- W4385954713 cites W2026616100 @default.
- W4385954713 cites W2064076387 @default.
- W4385954713 cites W2108598243 @default.
- W4385954713 cites W2156010062 @default.
- W4385954713 cites W2194775991 @default.
- W4385954713 cites W2533218643 @default.
- W4385954713 cites W2549139847 @default.
- W4385954713 cites W2592929672 @default.
- W4385954713 cites W2594608309 @default.
- W4385954713 cites W2962785568 @default.
- W4385954713 cites W2963015987 @default.
- W4385954713 cites W2963518130 @default.
- W4385954713 cites W2971013993 @default.
- W4385954713 cites W2998097997 @default.
- W4385954713 cites W3014795415 @default.
- W4385954713 cites W3088226460 @default.
- W4385954713 cites W3125779006 @default.
- W4385954713 cites W3132817419 @default.
- W4385954713 cites W3135857383 @default.
- W4385954713 cites W3172681723 @default.
- W4385954713 cites W3183302989 @default.
- W4385954713 cites W3211326549 @default.
- W4385954713 cites W611457968 @default.
- W4385954713 doi "https://doi.org/10.1117/1.jmi.10.4.044007" @default.
- W4385954713 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37600751" @default.
- W4385954713 hasPublicationYear "2023" @default.
- W4385954713 type Work @default.
- W4385954713 citedByCount "0" @default.
- W4385954713 crossrefType "journal-article" @default.
- W4385954713 hasAuthorship W4385954713A5010048557 @default.
- W4385954713 hasAuthorship W4385954713A5019206085 @default.
- W4385954713 hasAuthorship W4385954713A5055878070 @default.
- W4385954713 hasAuthorship W4385954713A5061059879 @default.
- W4385954713 hasAuthorship W4385954713A5082113824 @default.
- W4385954713 hasConcept C103278499 @default.
- W4385954713 hasConcept C108583219 @default.
- W4385954713 hasConcept C115961682 @default.
- W4385954713 hasConcept C119857082 @default.
- W4385954713 hasConcept C121332964 @default.
- W4385954713 hasConcept C147037132 @default.
- W4385954713 hasConcept C153180895 @default.
- W4385954713 hasConcept C154945302 @default.
- W4385954713 hasConcept C162324750 @default.
- W4385954713 hasConcept C176217482 @default.
- W4385954713 hasConcept C20556612 @default.
- W4385954713 hasConcept C21547014 @default.
- W4385954713 hasConcept C22019652 @default.
- W4385954713 hasConcept C2776321320 @default.
- W4385954713 hasConcept C41008148 @default.
- W4385954713 hasConcept C50644808 @default.
- W4385954713 hasConcept C62520636 @default.
- W4385954713 hasConcept C71924100 @default.
- W4385954713 hasConcept C81363708 @default.
- W4385954713 hasConcept C89600930 @default.
- W4385954713 hasConceptScore W4385954713C103278499 @default.
- W4385954713 hasConceptScore W4385954713C108583219 @default.
- W4385954713 hasConceptScore W4385954713C115961682 @default.
- W4385954713 hasConceptScore W4385954713C119857082 @default.
- W4385954713 hasConceptScore W4385954713C121332964 @default.
- W4385954713 hasConceptScore W4385954713C147037132 @default.
- W4385954713 hasConceptScore W4385954713C153180895 @default.
- W4385954713 hasConceptScore W4385954713C154945302 @default.
- W4385954713 hasConceptScore W4385954713C162324750 @default.
- W4385954713 hasConceptScore W4385954713C176217482 @default.
- W4385954713 hasConceptScore W4385954713C20556612 @default.
- W4385954713 hasConceptScore W4385954713C21547014 @default.
- W4385954713 hasConceptScore W4385954713C22019652 @default.
- W4385954713 hasConceptScore W4385954713C2776321320 @default.
- W4385954713 hasConceptScore W4385954713C41008148 @default.
- W4385954713 hasConceptScore W4385954713C50644808 @default.
- W4385954713 hasConceptScore W4385954713C62520636 @default.
- W4385954713 hasConceptScore W4385954713C71924100 @default.
- W4385954713 hasConceptScore W4385954713C81363708 @default.
- W4385954713 hasConceptScore W4385954713C89600930 @default.
- W4385954713 hasIssue "04" @default.
- W4385954713 hasLocation W43859547131 @default.
- W4385954713 hasLocation W43859547132 @default.
- W4385954713 hasOpenAccess W4385954713 @default.
- W4385954713 hasPrimaryLocation W43859547131 @default.
- W4385954713 hasRelatedWork W1574414179 @default.
- W4385954713 hasRelatedWork W2776054962 @default.
- W4385954713 hasRelatedWork W2949303564 @default.
- W4385954713 hasRelatedWork W3039174484 @default.
- W4385954713 hasRelatedWork W3163786145 @default.
- W4385954713 hasRelatedWork W4287728368 @default.