FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4223436296> ?p ?o ?g. }

• W4223436296 endingPage "102454" @default.
• W4223436296 startingPage "102454" @default.
• W4223436296 abstract "Convolutional neural networks (CNNs) have achieved state-of-the-art performance for white matter (WM) tract segmentation based on diffusion magnetic resonance imaging (dMRI). The training of the CNN-based segmentation model generally requires a large number of manual delineations of WM tracts, which can be expensive and time-consuming. Although it is possible to carefully curate abundant training data for a set of WM tracts of interest, there can also be novel WM tracts-i.e., WM tracts that are not included in the existing annotated WM tracts-that are specific to a new scientific problem, and it is desired that the novel WM tracts can be segmented without repeating the laborious collection of a large number of manual delineations for these tracts. One possible solution to the problem is to transfer the knowledge learned for segmenting existing WM tracts to the segmentation of novel WM tracts with a fine-tuning strategy, where a CNN pretrained for segmenting existing WM tracts is fine-tuned with only a few annotated scans to segment the novel WM tracts. However, in classic fine-tuning, the information in the last task-specific layer for segmenting existing WM tracts is completely discarded. In this work, based on the pretraining and fine-tuning framework, we propose an improved transfer learning approach to the segmentation of novel WM tracts in the few-shot setting, where all knowledge in the pretrained model is incorporated into the fine-tuning procedure. Specifically, from the weights of the pretrained task-specific layer for segmenting existing WM tracts, we derive a better initialization of the last task-specific layer for the target model that segments novel WM tracts. In addition, to allow further improvement of the initialization of the last layer and thus the segmentation performance in the few-shot setting, we develop a simple yet effective data augmentation strategy that generates synthetic annotated images with tract-aware image mixing. To validate the proposed method, we performed experiments on brain dMRI scans from public and private datasets under various experimental settings, and the results indicate that our method improves the performance of few-shot segmentation of novel WM tracts." @default.
• W4223436296 created "2022-04-14" @default.
• W4223436296 creator A5026413332 @default.
• W4223436296 creator A5034288299 @default.
• W4223436296 creator A5040190038 @default.
• W4223436296 creator A5043036223 @default.
• W4223436296 creator A5045721425 @default.
• W4223436296 creator A5048043623 @default.
• W4223436296 creator A5060451647 @default.
• W4223436296 creator A5080655703 @default.
• W4223436296 creator A5081033387 @default.
• W4223436296 date "2022-07-01" @default.
• W4223436296 modified "2023-10-16" @default.
• W4223436296 title "A transfer learning approach to few-shot segmentation of novel white matter tracts" @default.
• W4223436296 cites W1945319319 @default.
• W4223436296 cites W1965018875 @default.
• W4223436296 cites W1965894642 @default.
• W4223436296 cites W1983208069 @default.
• W4223436296 cites W1984453610 @default.
• W4223436296 cites W1986756161 @default.
• W4223436296 cites W2001611992 @default.
• W4223436296 cites W2024729467 @default.
• W4223436296 cites W2041990454 @default.
• W4223436296 cites W2067214598 @default.
• W4223436296 cites W2067703807 @default.
• W4223436296 cites W2092497652 @default.
• W4223436296 cites W2114856020 @default.
• W4223436296 cites W2127309075 @default.
• W4223436296 cites W2129397798 @default.
• W4223436296 cites W2130254828 @default.
• W4223436296 cites W2142900310 @default.
• W4223436296 cites W2170480020 @default.
• W4223436296 cites W2344337444 @default.
• W4223436296 cites W2346062110 @default.
• W4223436296 cites W2735700022 @default.
• W4223436296 cites W2766639217 @default.
• W4223436296 cites W2803890652 @default.
• W4223436296 cites W2804460770 @default.
• W4223436296 cites W2911926566 @default.
• W4223436296 cites W2912944597 @default.
• W4223436296 cites W2919011512 @default.
• W4223436296 cites W2970898057 @default.
• W4223436296 cites W2979808779 @default.
• W4223436296 cites W3011265095 @default.
• W4223436296 cites W3021595307 @default.
• W4223436296 cites W3030958193 @default.
• W4223436296 cites W3036595745 @default.
• W4223436296 cites W3044040952 @default.
• W4223436296 cites W3087322336 @default.
• W4223436296 cites W3092593892 @default.
• W4223436296 cites W3106083666 @default.
• W4223436296 cites W3113743199 @default.
• W4223436296 cites W3127252307 @default.
• W4223436296 cites W3131362130 @default.
• W4223436296 cites W3131999127 @default.
• W4223436296 cites W3138433874 @default.
• W4223436296 cites W3156041236 @default.
• W4223436296 cites W3160768770 @default.
• W4223436296 doi "https://doi.org/10.1016/j.media.2022.102454" @default.
• W4223436296 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35468555" @default.
• W4223436296 hasPublicationYear "2022" @default.
• W4223436296 type Work @default.
• W4223436296 citedByCount "9" @default.
• W4223436296 countsByYear W42234362962022 @default.
• W4223436296 countsByYear W42234362962023 @default.
• W4223436296 crossrefType "journal-article" @default.
• W4223436296 hasAuthorship W4223436296A5026413332 @default.
• W4223436296 hasAuthorship W4223436296A5034288299 @default.
• W4223436296 hasAuthorship W4223436296A5040190038 @default.
• W4223436296 hasAuthorship W4223436296A5043036223 @default.
• W4223436296 hasAuthorship W4223436296A5045721425 @default.
• W4223436296 hasAuthorship W4223436296A5048043623 @default.
• W4223436296 hasAuthorship W4223436296A5060451647 @default.
• W4223436296 hasAuthorship W4223436296A5080655703 @default.
• W4223436296 hasAuthorship W4223436296A5081033387 @default.
• W4223436296 hasConcept C108583219 @default.
• W4223436296 hasConcept C125308379 @default.
• W4223436296 hasConcept C126838900 @default.
• W4223436296 hasConcept C143409427 @default.
• W4223436296 hasConcept C144133560 @default.
• W4223436296 hasConcept C150899416 @default.
• W4223436296 hasConcept C153180895 @default.
• W4223436296 hasConcept C154945302 @default.
• W4223436296 hasConcept C162324750 @default.
• W4223436296 hasConcept C162853370 @default.
• W4223436296 hasConcept C187736073 @default.
• W4223436296 hasConcept C2780451532 @default.
• W4223436296 hasConcept C2781192897 @default.
• W4223436296 hasConcept C31972630 @default.
• W4223436296 hasConcept C41008148 @default.
• W4223436296 hasConcept C71924100 @default.
• W4223436296 hasConcept C81363708 @default.
• W4223436296 hasConcept C89600930 @default.
• W4223436296 hasConceptScore W4223436296C108583219 @default.
• W4223436296 hasConceptScore W4223436296C125308379 @default.
• W4223436296 hasConceptScore W4223436296C126838900 @default.
• W4223436296 hasConceptScore W4223436296C143409427 @default.
• W4223436296 hasConceptScore W4223436296C144133560 @default.

• next