Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386003448> ?p ?o ?g. }
- W4386003448 endingPage "102934" @default.
- W4386003448 startingPage "102934" @default.
- W4386003448 abstract "Most current deep learning based approaches for image segmentation require annotations of large datasets, which limits their application in clinical practice. We observe a mismatch between the voxelwise ground-truth that is required to optimize an objective at a voxel level and the commonly used, less time-consuming clinical annotations seeking to characterize the most important information about the patient (diameters, counts, etc.). In this study, we propose to bridge this gap for the case of multiple nested star-shaped objects (e.g., a blood vessel lumen and its outer wall) by optimizing a deep learning model based on diameter annotations. This is achieved by extracting in a differentiable manner the boundary points of the objects at training time, and by using this extraction during the backpropagation. We evaluate the proposed approach on segmentation of the carotid artery lumen and wall from multisequence MR images, thus reducing the annotation burden to only four annotated landmarks required to measure the diameters in the direction of the vessel’s maximum narrowing. Our experiments show that training based on diameter annotations produces state-of-the-art weakly supervised segmentations and performs reasonably compared to full supervision. We made our code publicly available at https://gitlab.com/radiology/aim/carotid-artery-image-analysis/nested-star-shaped-objects." @default.
- W4386003448 created "2023-08-20" @default.
- W4386003448 creator A5009602483 @default.
- W4386003448 creator A5023677285 @default.
- W4386003448 creator A5051576018 @default.
- W4386003448 creator A5057382610 @default.
- W4386003448 creator A5059145563 @default.
- W4386003448 creator A5080311936 @default.
- W4386003448 creator A5089667544 @default.
- W4386003448 date "2023-12-01" @default.
- W4386003448 modified "2023-10-12" @default.
- W4386003448 title "Nested star-shaped objects segmentation using diameter annotations" @default.
- W4386003448 cites W1641498739 @default.
- W4386003448 cites W1783315696 @default.
- W4386003448 cites W1901129140 @default.
- W4386003448 cites W2008712865 @default.
- W4386003448 cites W2022427932 @default.
- W4386003448 cites W2033004960 @default.
- W4386003448 cites W2071617033 @default.
- W4386003448 cites W2115949557 @default.
- W4386003448 cites W2221898772 @default.
- W4386003448 cites W2292574432 @default.
- W4386003448 cites W2337429362 @default.
- W4386003448 cites W2373606074 @default.
- W4386003448 cites W2396622801 @default.
- W4386003448 cites W2568368793 @default.
- W4386003448 cites W2592929672 @default.
- W4386003448 cites W2612334191 @default.
- W4386003448 cites W2763160469 @default.
- W4386003448 cites W2786531692 @default.
- W4386003448 cites W2799738340 @default.
- W4386003448 cites W2884402480 @default.
- W4386003448 cites W2931291299 @default.
- W4386003448 cites W2962731543 @default.
- W4386003448 cites W2963198662 @default.
- W4386003448 cites W2966272446 @default.
- W4386003448 cites W2967968231 @default.
- W4386003448 cites W3090112028 @default.
- W4386003448 cites W3111268119 @default.
- W4386003448 cites W3112701542 @default.
- W4386003448 cites W3136562050 @default.
- W4386003448 cites W3159178846 @default.
- W4386003448 cites W3199507899 @default.
- W4386003448 cites W3202876959 @default.
- W4386003448 cites W4232492418 @default.
- W4386003448 doi "https://doi.org/10.1016/j.media.2023.102934" @default.
- W4386003448 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37688981" @default.
- W4386003448 hasPublicationYear "2023" @default.
- W4386003448 type Work @default.
- W4386003448 citedByCount "0" @default.
- W4386003448 crossrefType "journal-article" @default.
- W4386003448 hasAuthorship W4386003448A5009602483 @default.
- W4386003448 hasAuthorship W4386003448A5023677285 @default.
- W4386003448 hasAuthorship W4386003448A5051576018 @default.
- W4386003448 hasAuthorship W4386003448A5057382610 @default.
- W4386003448 hasAuthorship W4386003448A5059145563 @default.
- W4386003448 hasAuthorship W4386003448A5080311936 @default.
- W4386003448 hasAuthorship W4386003448A5089667544 @default.
- W4386003448 hasBestOaLocation W43860034481 @default.
- W4386003448 hasConcept C108583219 @default.
- W4386003448 hasConcept C134306372 @default.
- W4386003448 hasConcept C146849305 @default.
- W4386003448 hasConcept C153180895 @default.
- W4386003448 hasConcept C154945302 @default.
- W4386003448 hasConcept C184898388 @default.
- W4386003448 hasConcept C2776321320 @default.
- W4386003448 hasConcept C31972630 @default.
- W4386003448 hasConcept C33923547 @default.
- W4386003448 hasConcept C41008148 @default.
- W4386003448 hasConcept C54170458 @default.
- W4386003448 hasConcept C62354387 @default.
- W4386003448 hasConcept C89600930 @default.
- W4386003448 hasConceptScore W4386003448C108583219 @default.
- W4386003448 hasConceptScore W4386003448C134306372 @default.
- W4386003448 hasConceptScore W4386003448C146849305 @default.
- W4386003448 hasConceptScore W4386003448C153180895 @default.
- W4386003448 hasConceptScore W4386003448C154945302 @default.
- W4386003448 hasConceptScore W4386003448C184898388 @default.
- W4386003448 hasConceptScore W4386003448C2776321320 @default.
- W4386003448 hasConceptScore W4386003448C31972630 @default.
- W4386003448 hasConceptScore W4386003448C33923547 @default.
- W4386003448 hasConceptScore W4386003448C41008148 @default.
- W4386003448 hasConceptScore W4386003448C54170458 @default.
- W4386003448 hasConceptScore W4386003448C62354387 @default.
- W4386003448 hasConceptScore W4386003448C89600930 @default.
- W4386003448 hasFunder F4320321642 @default.
- W4386003448 hasFunder F4320321800 @default.
- W4386003448 hasFunder F4320323596 @default.
- W4386003448 hasFunder F4320328233 @default.
- W4386003448 hasLocation W43860034481 @default.
- W4386003448 hasLocation W43860034482 @default.
- W4386003448 hasOpenAccess W4386003448 @default.
- W4386003448 hasPrimaryLocation W43860034481 @default.
- W4386003448 hasRelatedWork W2218034408 @default.
- W4386003448 hasRelatedWork W2263699433 @default.
- W4386003448 hasRelatedWork W2358755282 @default.
- W4386003448 hasRelatedWork W2361861616 @default.
- W4386003448 hasRelatedWork W2377979023 @default.