Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386395698> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4386395698 abstract "While the Segment Anything Model (SAM) excels in semantic segmentation for general-purpose images, its performance significantly deteriorates when applied to medical images, primarily attributable to insufficient representation of medical images in its training dataset. Nonetheless, gathering comprehensive datasets and training models that are universally applicable is particularly challenging due to the long-tail problem common in medical images. To address this gap, here we present a Self-Sampling Meta SAM (SSM-SAM) framework for few-shot medical image segmentation. Our innovation lies in the design of three key modules: 1) An online fast gradient descent optimizer, further optimized by a meta-learner, which ensures swift and robust adaptation to new tasks. 2) A Self-Sampling module designed to provide well-aligned visual prompts for improved attention allocation; and 3) A robust attention-based decoder specifically designed for medical few-shot learning to capture relationship between different slices. Extensive experiments on a popular abdominal CT dataset and an MRI dataset demonstrate that the proposed method achieves significant improvements over state-of-the-art methods in few-shot segmentation, with an average improvements of 10.21% and 1.80% in terms of DSC, respectively. In conclusion, we present a novel approach for rapid online adaptation in interactive image segmentation, adapting to a new organ in just 0.83 minutes. Code is publicly available on GitHub upon acceptance." @default.
- W4386395698 created "2023-09-03" @default.
- W4386395698 creator A5030243559 @default.
- W4386395698 creator A5046394605 @default.
- W4386395698 creator A5049666232 @default.
- W4386395698 creator A5084618257 @default.
- W4386395698 date "2023-08-31" @default.
- W4386395698 modified "2023-09-26" @default.
- W4386395698 title "Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-Learning" @default.
- W4386395698 doi "https://doi.org/10.48550/arxiv.2308.16466" @default.
- W4386395698 hasPublicationYear "2023" @default.
- W4386395698 type Work @default.
- W4386395698 citedByCount "0" @default.
- W4386395698 crossrefType "posted-content" @default.
- W4386395698 hasAuthorship W4386395698A5030243559 @default.
- W4386395698 hasAuthorship W4386395698A5046394605 @default.
- W4386395698 hasAuthorship W4386395698A5049666232 @default.
- W4386395698 hasAuthorship W4386395698A5084618257 @default.
- W4386395698 hasBestOaLocation W43863956981 @default.
- W4386395698 hasConcept C106131492 @default.
- W4386395698 hasConcept C115961682 @default.
- W4386395698 hasConcept C119857082 @default.
- W4386395698 hasConcept C120665830 @default.
- W4386395698 hasConcept C121332964 @default.
- W4386395698 hasConcept C124504099 @default.
- W4386395698 hasConcept C139807058 @default.
- W4386395698 hasConcept C140779682 @default.
- W4386395698 hasConcept C153180895 @default.
- W4386395698 hasConcept C154945302 @default.
- W4386395698 hasConcept C177264268 @default.
- W4386395698 hasConcept C17744445 @default.
- W4386395698 hasConcept C178790620 @default.
- W4386395698 hasConcept C185592680 @default.
- W4386395698 hasConcept C199360897 @default.
- W4386395698 hasConcept C199539241 @default.
- W4386395698 hasConcept C26517878 @default.
- W4386395698 hasConcept C2776359362 @default.
- W4386395698 hasConcept C2776760102 @default.
- W4386395698 hasConcept C2778344882 @default.
- W4386395698 hasConcept C31972630 @default.
- W4386395698 hasConcept C38652104 @default.
- W4386395698 hasConcept C41008148 @default.
- W4386395698 hasConcept C89600930 @default.
- W4386395698 hasConcept C94625758 @default.
- W4386395698 hasConceptScore W4386395698C106131492 @default.
- W4386395698 hasConceptScore W4386395698C115961682 @default.
- W4386395698 hasConceptScore W4386395698C119857082 @default.
- W4386395698 hasConceptScore W4386395698C120665830 @default.
- W4386395698 hasConceptScore W4386395698C121332964 @default.
- W4386395698 hasConceptScore W4386395698C124504099 @default.
- W4386395698 hasConceptScore W4386395698C139807058 @default.
- W4386395698 hasConceptScore W4386395698C140779682 @default.
- W4386395698 hasConceptScore W4386395698C153180895 @default.
- W4386395698 hasConceptScore W4386395698C154945302 @default.
- W4386395698 hasConceptScore W4386395698C177264268 @default.
- W4386395698 hasConceptScore W4386395698C17744445 @default.
- W4386395698 hasConceptScore W4386395698C178790620 @default.
- W4386395698 hasConceptScore W4386395698C185592680 @default.
- W4386395698 hasConceptScore W4386395698C199360897 @default.
- W4386395698 hasConceptScore W4386395698C199539241 @default.
- W4386395698 hasConceptScore W4386395698C26517878 @default.
- W4386395698 hasConceptScore W4386395698C2776359362 @default.
- W4386395698 hasConceptScore W4386395698C2776760102 @default.
- W4386395698 hasConceptScore W4386395698C2778344882 @default.
- W4386395698 hasConceptScore W4386395698C31972630 @default.
- W4386395698 hasConceptScore W4386395698C38652104 @default.
- W4386395698 hasConceptScore W4386395698C41008148 @default.
- W4386395698 hasConceptScore W4386395698C89600930 @default.
- W4386395698 hasConceptScore W4386395698C94625758 @default.
- W4386395698 hasLocation W43863956981 @default.
- W4386395698 hasOpenAccess W4386395698 @default.
- W4386395698 hasPrimaryLocation W43863956981 @default.
- W4386395698 hasRelatedWork W1669643531 @default.
- W4386395698 hasRelatedWork W1982826852 @default.
- W4386395698 hasRelatedWork W2005437358 @default.
- W4386395698 hasRelatedWork W2008656436 @default.
- W4386395698 hasRelatedWork W2023558673 @default.
- W4386395698 hasRelatedWork W2110230079 @default.
- W4386395698 hasRelatedWork W2134924024 @default.
- W4386395698 hasRelatedWork W2517104666 @default.
- W4386395698 hasRelatedWork W2613186388 @default.
- W4386395698 hasRelatedWork W1967061043 @default.
- W4386395698 isParatext "false" @default.
- W4386395698 isRetracted "false" @default.
- W4386395698 workType "article" @default.