Matches in SemOpenAlex for { <https://semopenalex.org/work/W3049636721> ?p ?o ?g. }
- W3049636721 endingPage "770" @default.
- W3049636721 startingPage "759" @default.
- W3049636721 abstract "Objective: The segmentation of the breast from the chest wall is an important first step in the analysis of breast magnetic resonance images. 3D U-Nets have been shown to obtain high segmentation accuracy and appear to generalize well when trained on one scanner type and tested on another scanner, provided that a very similar MR protocol is used. There has, however, been little work addressing the problem of domain adaptation when image intensities or patient orientation differ markedly between the training set and an unseen test set. In this work we aim to address this domain shift problem. Method: We propose to apply extensive intensity augmentation in addition to geometric augmentation during training. We explored both style transfer and a novel intensity remapping approach as intensity augmentation strategies. For our experiments, we trained a 3D U-Net on T1-weighted scans. We tested our network on T2-weighted scans from the same dataset as well as on an additional independent test set acquired with a T1-weighted TWIST sequence and a different coil configuration. Results: By applying intensity augmentation we increased segmentation performance for the T2-weighted scans from a Dice of 0.71 to 0.88. This performance is very close to the baseline performance of training with T2-weighted scans (0.92). On the T1-weighted dataset we obtained a performance increase from 0.77 to 0.85. Conclusion: Our results show that the proposed intensity augmentation increases segmentation performance across different datasets. Significance: The proposed method can improve whole breast segmentation of clinical MR scans acquired with different protocols." @default.
- W3049636721 created "2020-08-21" @default.
- W3049636721 creator A5008103968 @default.
- W3049636721 creator A5019860753 @default.
- W3049636721 creator A5029260213 @default.
- W3049636721 creator A5033904033 @default.
- W3049636721 date "2021-03-01" @default.
- W3049636721 modified "2023-10-06" @default.
- W3049636721 title "Intensity Augmentation to Improve Generalizability of Breast Segmentation Across Different MRI Scan Protocols" @default.
- W3049636721 cites W1651094700 @default.
- W3049636721 cites W2032558189 @default.
- W3049636721 cites W2098698341 @default.
- W3049636721 cites W2105722841 @default.
- W3049636721 cites W2126731819 @default.
- W3049636721 cites W2127890285 @default.
- W3049636721 cites W2148347694 @default.
- W3049636721 cites W2157727387 @default.
- W3049636721 cites W2167465004 @default.
- W3049636721 cites W2346062110 @default.
- W3049636721 cites W2475287302 @default.
- W3049636721 cites W2592929672 @default.
- W3049636721 cites W2593768305 @default.
- W3049636721 cites W2603777577 @default.
- W3049636721 cites W2605102758 @default.
- W3049636721 cites W2618530766 @default.
- W3049636721 cites W2756073160 @default.
- W3049636721 cites W2895926103 @default.
- W3049636721 cites W2908173197 @default.
- W3049636721 cites W2912415791 @default.
- W3049636721 cites W2953627578 @default.
- W3049636721 cites W2963525668 @default.
- W3049636721 cites W2964152645 @default.
- W3049636721 cites W2969278648 @default.
- W3049636721 cites W2982516712 @default.
- W3049636721 cites W3100715778 @default.
- W3049636721 doi "https://doi.org/10.1109/tbme.2020.3016602" @default.
- W3049636721 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32790624" @default.
- W3049636721 hasPublicationYear "2021" @default.
- W3049636721 type Work @default.
- W3049636721 sameAs 3049636721 @default.
- W3049636721 citedByCount "10" @default.
- W3049636721 countsByYear W30496367212020 @default.
- W3049636721 countsByYear W30496367212021 @default.
- W3049636721 countsByYear W30496367212022 @default.
- W3049636721 countsByYear W30496367212023 @default.
- W3049636721 crossrefType "journal-article" @default.
- W3049636721 hasAuthorship W3049636721A5008103968 @default.
- W3049636721 hasAuthorship W3049636721A5019860753 @default.
- W3049636721 hasAuthorship W3049636721A5029260213 @default.
- W3049636721 hasAuthorship W3049636721A5033904033 @default.
- W3049636721 hasConcept C105795698 @default.
- W3049636721 hasConcept C121332964 @default.
- W3049636721 hasConcept C121608353 @default.
- W3049636721 hasConcept C124504099 @default.
- W3049636721 hasConcept C126322002 @default.
- W3049636721 hasConcept C126838900 @default.
- W3049636721 hasConcept C143409427 @default.
- W3049636721 hasConcept C153180895 @default.
- W3049636721 hasConcept C154945302 @default.
- W3049636721 hasConcept C169903167 @default.
- W3049636721 hasConcept C27158222 @default.
- W3049636721 hasConcept C2777111374 @default.
- W3049636721 hasConcept C2779751349 @default.
- W3049636721 hasConcept C2780472235 @default.
- W3049636721 hasConcept C31972630 @default.
- W3049636721 hasConcept C33923547 @default.
- W3049636721 hasConcept C41008148 @default.
- W3049636721 hasConcept C530470458 @default.
- W3049636721 hasConcept C62520636 @default.
- W3049636721 hasConcept C71924100 @default.
- W3049636721 hasConcept C89600930 @default.
- W3049636721 hasConcept C93038891 @default.
- W3049636721 hasConceptScore W3049636721C105795698 @default.
- W3049636721 hasConceptScore W3049636721C121332964 @default.
- W3049636721 hasConceptScore W3049636721C121608353 @default.
- W3049636721 hasConceptScore W3049636721C124504099 @default.
- W3049636721 hasConceptScore W3049636721C126322002 @default.
- W3049636721 hasConceptScore W3049636721C126838900 @default.
- W3049636721 hasConceptScore W3049636721C143409427 @default.
- W3049636721 hasConceptScore W3049636721C153180895 @default.
- W3049636721 hasConceptScore W3049636721C154945302 @default.
- W3049636721 hasConceptScore W3049636721C169903167 @default.
- W3049636721 hasConceptScore W3049636721C27158222 @default.
- W3049636721 hasConceptScore W3049636721C2777111374 @default.
- W3049636721 hasConceptScore W3049636721C2779751349 @default.
- W3049636721 hasConceptScore W3049636721C2780472235 @default.
- W3049636721 hasConceptScore W3049636721C31972630 @default.
- W3049636721 hasConceptScore W3049636721C33923547 @default.
- W3049636721 hasConceptScore W3049636721C41008148 @default.
- W3049636721 hasConceptScore W3049636721C530470458 @default.
- W3049636721 hasConceptScore W3049636721C62520636 @default.
- W3049636721 hasConceptScore W3049636721C71924100 @default.
- W3049636721 hasConceptScore W3049636721C89600930 @default.
- W3049636721 hasConceptScore W3049636721C93038891 @default.
- W3049636721 hasFunder F4320334506 @default.
- W3049636721 hasFunder F4320334593 @default.
- W3049636721 hasIssue "3" @default.
- W3049636721 hasLocation W30496367211 @default.