Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286795909> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4286795909 abstract "Widely used traditional supervised deep learning methods require a large number of training samples but often fail to generalize on unseen datasets. Therefore, a more general application of any trained model is quite limited for medical imaging for clinical practice. Using separately trained models for each unique lesion category or a unique patient population will require sufficiently large curated datasets, which is not practical to use in a real-world clinical set-up. Few-shot learning approaches can not only minimize the need for an enormous number of reliable ground truth labels that are labour-intensive and expensive but can also be used to model on a dataset coming from a new population. To this end, we propose to exploit an optimization-based implicit model agnostic meta-learning (iMAML) algorithm under few-shot settings for medical image segmentation. Our approach can leverage the learned weights from diverse but small training samples to perform analysis on unseen datasets with high accuracy. We show that, unlike classical few-shot learning approaches, our method improves generalization capability. To our knowledge, this is the first work that exploits iMAML for medical image segmentation and explores the strength of the model on scenarios such as meta-training on unique and mixed instances of lesion datasets. Our quantitative results on publicly available skin and polyp datasets show that the proposed method outperforms the naive supervised baseline model and two recent few-shot segmentation approaches by large margins. In addition, our iMAML approach shows an improvement of 2%-4% in dice score compared to its counterpart MAML for most experiments." @default.
- W4286795909 created "2022-07-24" @default.
- W4286795909 creator A5022601521 @default.
- W4286795909 creator A5034317141 @default.
- W4286795909 creator A5041662804 @default.
- W4286795909 creator A5044673103 @default.
- W4286795909 creator A5071467487 @default.
- W4286795909 creator A5080765299 @default.
- W4286795909 creator A5088962741 @default.
- W4286795909 date "2021-06-06" @default.
- W4286795909 modified "2023-09-27" @default.
- W4286795909 title "Meta-learning with implicit gradients in a few-shot setting for medical image segmentation" @default.
- W4286795909 doi "https://doi.org/10.48550/arxiv.2106.03223" @default.
- W4286795909 hasPublicationYear "2021" @default.
- W4286795909 type Work @default.
- W4286795909 citedByCount "0" @default.
- W4286795909 crossrefType "posted-content" @default.
- W4286795909 hasAuthorship W4286795909A5022601521 @default.
- W4286795909 hasAuthorship W4286795909A5034317141 @default.
- W4286795909 hasAuthorship W4286795909A5041662804 @default.
- W4286795909 hasAuthorship W4286795909A5044673103 @default.
- W4286795909 hasAuthorship W4286795909A5071467487 @default.
- W4286795909 hasAuthorship W4286795909A5080765299 @default.
- W4286795909 hasAuthorship W4286795909A5088962741 @default.
- W4286795909 hasBestOaLocation W42867959091 @default.
- W4286795909 hasConcept C119857082 @default.
- W4286795909 hasConcept C124504099 @default.
- W4286795909 hasConcept C134306372 @default.
- W4286795909 hasConcept C136389625 @default.
- W4286795909 hasConcept C144024400 @default.
- W4286795909 hasConcept C146849305 @default.
- W4286795909 hasConcept C149923435 @default.
- W4286795909 hasConcept C153083717 @default.
- W4286795909 hasConcept C153180895 @default.
- W4286795909 hasConcept C154945302 @default.
- W4286795909 hasConcept C165696696 @default.
- W4286795909 hasConcept C177148314 @default.
- W4286795909 hasConcept C177264268 @default.
- W4286795909 hasConcept C199360897 @default.
- W4286795909 hasConcept C2908647359 @default.
- W4286795909 hasConcept C33923547 @default.
- W4286795909 hasConcept C38652104 @default.
- W4286795909 hasConcept C41008148 @default.
- W4286795909 hasConcept C50644808 @default.
- W4286795909 hasConcept C89600930 @default.
- W4286795909 hasConceptScore W4286795909C119857082 @default.
- W4286795909 hasConceptScore W4286795909C124504099 @default.
- W4286795909 hasConceptScore W4286795909C134306372 @default.
- W4286795909 hasConceptScore W4286795909C136389625 @default.
- W4286795909 hasConceptScore W4286795909C144024400 @default.
- W4286795909 hasConceptScore W4286795909C146849305 @default.
- W4286795909 hasConceptScore W4286795909C149923435 @default.
- W4286795909 hasConceptScore W4286795909C153083717 @default.
- W4286795909 hasConceptScore W4286795909C153180895 @default.
- W4286795909 hasConceptScore W4286795909C154945302 @default.
- W4286795909 hasConceptScore W4286795909C165696696 @default.
- W4286795909 hasConceptScore W4286795909C177148314 @default.
- W4286795909 hasConceptScore W4286795909C177264268 @default.
- W4286795909 hasConceptScore W4286795909C199360897 @default.
- W4286795909 hasConceptScore W4286795909C2908647359 @default.
- W4286795909 hasConceptScore W4286795909C33923547 @default.
- W4286795909 hasConceptScore W4286795909C38652104 @default.
- W4286795909 hasConceptScore W4286795909C41008148 @default.
- W4286795909 hasConceptScore W4286795909C50644808 @default.
- W4286795909 hasConceptScore W4286795909C89600930 @default.
- W4286795909 hasLocation W42867959091 @default.
- W4286795909 hasLocation W42867959092 @default.
- W4286795909 hasLocation W42867959093 @default.
- W4286795909 hasLocation W42867959094 @default.
- W4286795909 hasOpenAccess W4286795909 @default.
- W4286795909 hasPrimaryLocation W42867959091 @default.
- W4286795909 hasRelatedWork W158826679 @default.
- W4286795909 hasRelatedWork W2005476934 @default.
- W4286795909 hasRelatedWork W2130151498 @default.
- W4286795909 hasRelatedWork W2137493099 @default.
- W4286795909 hasRelatedWork W2897195263 @default.
- W4286795909 hasRelatedWork W3027204089 @default.
- W4286795909 hasRelatedWork W3207810281 @default.
- W4286795909 hasRelatedWork W3216776746 @default.
- W4286795909 hasRelatedWork W4292998323 @default.
- W4286795909 hasRelatedWork W4311496088 @default.
- W4286795909 isParatext "false" @default.
- W4286795909 isRetracted "false" @default.
- W4286795909 workType "article" @default.