FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384570068> ?p ?o ?g. }

• W4384570068 endingPage "13" @default.
• W4384570068 startingPage "3" @default.
• W4384570068 abstract "Human ratings are abstract representations of segmentation quality. To approximate human quality ratings on scarce expert data, we train surrogate quality estimation models. We evaluate on a complex multi-class segmentation problem, specifically glioma segmentation, following the BraTS annotation protocol. The training data features quality ratings from 15 expert neuroradiologists on a scale ranging from 1 to 6 stars for various computer-generated and manual 3D annotations. Even though the networks operate on 2D images and with scarce training data, we can approximate segmentation quality within a margin of error comparable to human intra-rater reliability. Segmentation quality prediction has broad applications. While an understanding of segmentation quality is imperative for successful clinical translation of automatic segmentation quality algorithms, it can play an essential role in training new segmentation models. Due to the split-second inference times, it can be directly applied within a loss function or as a fully-automatic dataset curation mechanism in a federated learning setting." @default.
• W4384570068 created "2023-07-18" @default.
• W4384570068 creator A5002068604 @default.
• W4384570068 creator A5003938965 @default.
• W4384570068 creator A5004716871 @default.
• W4384570068 creator A5005966038 @default.
• W4384570068 creator A5018632773 @default.
• W4384570068 creator A5028279799 @default.
• W4384570068 creator A5031248347 @default.
• W4384570068 creator A5039935645 @default.
• W4384570068 creator A5039985608 @default.
• W4384570068 creator A5043497448 @default.
• W4384570068 creator A5049197829 @default.
• W4384570068 creator A5058605780 @default.
• W4384570068 creator A5067149506 @default.
• W4384570068 creator A5074336328 @default.
• W4384570068 creator A5077697378 @default.
• W4384570068 creator A5085027983 @default.
• W4384570068 creator A5085312364 @default.
• W4384570068 date "2023-01-01" @default.
• W4384570068 modified "2023-09-25" @default.
• W4384570068 title "Deep Quality Estimation: Creating Surrogate Models for Human Quality Ratings" @default.
• W4384570068 cites W1641498739 @default.
• W4384570068 cites W2594608309 @default.
• W4384570068 cites W2887513492 @default.
• W4384570068 cites W2902154261 @default.
• W4384570068 cites W2963446712 @default.
• W4384570068 cites W2979387929 @default.
• W4384570068 cites W2980024001 @default.
• W4384570068 cites W3012412627 @default.
• W4384570068 cites W3023290769 @default.
• W4384570068 cites W3090148481 @default.
• W4384570068 cites W3093606981 @default.
• W4384570068 cites W3103276002 @default.
• W4384570068 cites W3138480930 @default.
• W4384570068 cites W3195072348 @default.
• W4384570068 cites W3208968703 @default.
• W4384570068 cites W4200326083 @default.
• W4384570068 cites W4225888845 @default.
• W4384570068 cites W4285505489 @default.
• W4384570068 doi "https://doi.org/10.1007/978-3-031-33842-7_1" @default.
• W4384570068 hasPublicationYear "2023" @default.
• W4384570068 type Work @default.
• W4384570068 citedByCount "0" @default.
• W4384570068 crossrefType "book-chapter" @default.
• W4384570068 hasAuthorship W4384570068A5002068604 @default.
• W4384570068 hasAuthorship W4384570068A5003938965 @default.
• W4384570068 hasAuthorship W4384570068A5004716871 @default.
• W4384570068 hasAuthorship W4384570068A5005966038 @default.
• W4384570068 hasAuthorship W4384570068A5018632773 @default.
• W4384570068 hasAuthorship W4384570068A5028279799 @default.
• W4384570068 hasAuthorship W4384570068A5031248347 @default.
• W4384570068 hasAuthorship W4384570068A5039935645 @default.
• W4384570068 hasAuthorship W4384570068A5039985608 @default.
• W4384570068 hasAuthorship W4384570068A5043497448 @default.
• W4384570068 hasAuthorship W4384570068A5049197829 @default.
• W4384570068 hasAuthorship W4384570068A5058605780 @default.
• W4384570068 hasAuthorship W4384570068A5067149506 @default.
• W4384570068 hasAuthorship W4384570068A5074336328 @default.
• W4384570068 hasAuthorship W4384570068A5077697378 @default.
• W4384570068 hasAuthorship W4384570068A5085027983 @default.
• W4384570068 hasAuthorship W4384570068A5085312364 @default.
• W4384570068 hasBestOaLocation W43845700682 @default.
• W4384570068 hasConcept C111472728 @default.
• W4384570068 hasConcept C119857082 @default.
• W4384570068 hasConcept C121332964 @default.
• W4384570068 hasConcept C124101348 @default.
• W4384570068 hasConcept C138885662 @default.
• W4384570068 hasConcept C153180895 @default.
• W4384570068 hasConcept C154945302 @default.
• W4384570068 hasConcept C162324750 @default.
• W4384570068 hasConcept C163258240 @default.
• W4384570068 hasConcept C176217482 @default.
• W4384570068 hasConcept C21547014 @default.
• W4384570068 hasConcept C24756922 @default.
• W4384570068 hasConcept C2776214188 @default.
• W4384570068 hasConcept C2776321320 @default.
• W4384570068 hasConcept C2779530757 @default.
• W4384570068 hasConcept C41008148 @default.
• W4384570068 hasConcept C43214815 @default.
• W4384570068 hasConcept C62520636 @default.
• W4384570068 hasConcept C774472 @default.
• W4384570068 hasConcept C89600930 @default.
• W4384570068 hasConceptScore W4384570068C111472728 @default.
• W4384570068 hasConceptScore W4384570068C119857082 @default.
• W4384570068 hasConceptScore W4384570068C121332964 @default.
• W4384570068 hasConceptScore W4384570068C124101348 @default.
• W4384570068 hasConceptScore W4384570068C138885662 @default.
• W4384570068 hasConceptScore W4384570068C153180895 @default.
• W4384570068 hasConceptScore W4384570068C154945302 @default.
• W4384570068 hasConceptScore W4384570068C162324750 @default.
• W4384570068 hasConceptScore W4384570068C163258240 @default.
• W4384570068 hasConceptScore W4384570068C176217482 @default.
• W4384570068 hasConceptScore W4384570068C21547014 @default.
• W4384570068 hasConceptScore W4384570068C24756922 @default.
• W4384570068 hasConceptScore W4384570068C2776214188 @default.
• W4384570068 hasConceptScore W4384570068C2776321320 @default.
• W4384570068 hasConceptScore W4384570068C2779530757 @default.

• next