Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319986059> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4319986059 abstract "The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training. However, acquiring and manually labeling a large medical image set is resource-intensive, expensive, and sometimes impractical due to data sharing and privacy issues. To address this challenge, we propose AdvChain, a generic adversarial data augmentation framework, aiming at improving both the diversity and effectiveness of training data for medical image segmentation tasks. AdvChain augments data with dynamic data augmentation, generating randomly chained photo-metric and geometric transformations to resemble realistic yet challenging imaging variations to expand training data. By jointly optimizing the data augmentation model and a segmentation network during training, challenging examples are generated to enhance network generalizability for the downstream task. The proposed adversarial data augmentation does not rely on generative networks and can be used as a plug-in module in general segmentation networks. It is computationally efficient and applicable for both low-shot supervised and semi-supervised learning. We analyze and evaluate the method on two MR image segmentation tasks: cardiac segmentation and prostate segmentation with limited labeled data. Results show that the proposed approach can alleviate the need for labeled data while improving model generalization ability, indicating its practical value in medical imaging applications." @default.
- W4319986059 created "2023-02-11" @default.
- W4319986059 creator A5006461848 @default.
- W4319986059 creator A5011487190 @default.
- W4319986059 creator A5028293439 @default.
- W4319986059 creator A5042974614 @default.
- W4319986059 creator A5051434566 @default.
- W4319986059 creator A5056261326 @default.
- W4319986059 creator A5059823739 @default.
- W4319986059 creator A5063253432 @default.
- W4319986059 creator A5074707604 @default.
- W4319986059 creator A5077334337 @default.
- W4319986059 date "2021-08-07" @default.
- W4319986059 modified "2023-09-22" @default.
- W4319986059 title "Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation" @default.
- W4319986059 doi "https://doi.org/10.48550/arxiv.2108.03429" @default.
- W4319986059 hasPublicationYear "2021" @default.
- W4319986059 type Work @default.
- W4319986059 citedByCount "0" @default.
- W4319986059 crossrefType "posted-content" @default.
- W4319986059 hasAuthorship W4319986059A5006461848 @default.
- W4319986059 hasAuthorship W4319986059A5011487190 @default.
- W4319986059 hasAuthorship W4319986059A5028293439 @default.
- W4319986059 hasAuthorship W4319986059A5042974614 @default.
- W4319986059 hasAuthorship W4319986059A5051434566 @default.
- W4319986059 hasAuthorship W4319986059A5056261326 @default.
- W4319986059 hasAuthorship W4319986059A5059823739 @default.
- W4319986059 hasAuthorship W4319986059A5063253432 @default.
- W4319986059 hasAuthorship W4319986059A5074707604 @default.
- W4319986059 hasAuthorship W4319986059A5077334337 @default.
- W4319986059 hasBestOaLocation W43199860591 @default.
- W4319986059 hasConcept C105795698 @default.
- W4319986059 hasConcept C108583219 @default.
- W4319986059 hasConcept C119857082 @default.
- W4319986059 hasConcept C124101348 @default.
- W4319986059 hasConcept C124504099 @default.
- W4319986059 hasConcept C134306372 @default.
- W4319986059 hasConcept C153180895 @default.
- W4319986059 hasConcept C154945302 @default.
- W4319986059 hasConcept C162324750 @default.
- W4319986059 hasConcept C176217482 @default.
- W4319986059 hasConcept C177148314 @default.
- W4319986059 hasConcept C21547014 @default.
- W4319986059 hasConcept C27158222 @default.
- W4319986059 hasConcept C31601959 @default.
- W4319986059 hasConcept C33923547 @default.
- W4319986059 hasConcept C41008148 @default.
- W4319986059 hasConcept C50644808 @default.
- W4319986059 hasConcept C58489278 @default.
- W4319986059 hasConcept C89600930 @default.
- W4319986059 hasConceptScore W4319986059C105795698 @default.
- W4319986059 hasConceptScore W4319986059C108583219 @default.
- W4319986059 hasConceptScore W4319986059C119857082 @default.
- W4319986059 hasConceptScore W4319986059C124101348 @default.
- W4319986059 hasConceptScore W4319986059C124504099 @default.
- W4319986059 hasConceptScore W4319986059C134306372 @default.
- W4319986059 hasConceptScore W4319986059C153180895 @default.
- W4319986059 hasConceptScore W4319986059C154945302 @default.
- W4319986059 hasConceptScore W4319986059C162324750 @default.
- W4319986059 hasConceptScore W4319986059C176217482 @default.
- W4319986059 hasConceptScore W4319986059C177148314 @default.
- W4319986059 hasConceptScore W4319986059C21547014 @default.
- W4319986059 hasConceptScore W4319986059C27158222 @default.
- W4319986059 hasConceptScore W4319986059C31601959 @default.
- W4319986059 hasConceptScore W4319986059C33923547 @default.
- W4319986059 hasConceptScore W4319986059C41008148 @default.
- W4319986059 hasConceptScore W4319986059C50644808 @default.
- W4319986059 hasConceptScore W4319986059C58489278 @default.
- W4319986059 hasConceptScore W4319986059C89600930 @default.
- W4319986059 hasLocation W43199860591 @default.
- W4319986059 hasOpenAccess W4319986059 @default.
- W4319986059 hasPrimaryLocation W43199860591 @default.
- W4319986059 hasRelatedWork W1507687735 @default.
- W4319986059 hasRelatedWork W2897195263 @default.
- W4319986059 hasRelatedWork W2948658236 @default.
- W4319986059 hasRelatedWork W2960184797 @default.
- W4319986059 hasRelatedWork W2972093541 @default.
- W4319986059 hasRelatedWork W3115553566 @default.
- W4319986059 hasRelatedWork W3135174555 @default.
- W4319986059 hasRelatedWork W3164697193 @default.
- W4319986059 hasRelatedWork W3209779739 @default.
- W4319986059 hasRelatedWork W4285827401 @default.
- W4319986059 isParatext "false" @default.
- W4319986059 isRetracted "false" @default.
- W4319986059 workType "article" @default.