FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211592> ?p ?o ?g. }

• W4387211592 endingPage "436" @default.
• W4387211592 startingPage "427" @default.
• W4387211592 abstract "Skin lesion segmentation in dermoscopy images has seen recent success due to advancements in multi-scale boundary attention and feature-enhanced modules. However, existing methods that rely on end-to-end learning paradigms, which directly input images and output segmentation maps, often struggle with extremely hard boundaries, such as those found in lesions of particularly small or large sizes. This limitation arises because the receptive field and local context extraction capabilities of any finite model are inevitably limited, and the acquisition of additional expert-labeled data required for larger models is costly. Motivated by the impressive advances of diffusion models that regard image synthesis as a parameterized chain process, we introduce a novel approach that formulates skin lesion segmentation as a boundary evolution process to thoroughly investigate the boundary knowledge. Specifically, we propose the Medical Boundary Diffusion Model (MB-Diff), which starts with a randomly sampled Gaussian noise, and the boundary evolves within finite times to obtain a clear segmentation map. First, we propose an efficient multi-scale image guidance module to constrain the boundary evolution, which makes the evolution direction suit our desired lesions. Second, we propose an evolution uncertainty-based fusion strategy to refine the evolution results and yield more precise lesion boundaries. We evaluate the performance of our model on two popular skin lesion segmentation datasets and compare our model to the latest CNN and transformer models. Our results demonstrate that our model outperforms existing methods in all metrics and achieves superior performance on extremely challenging skin lesions. The proposed approach has the potential to significantly enhance the accuracy and reliability of skin lesion segmentation, providing critical information for diagnosis and treatment. All resources will be publicly available at https://github.com/jcwang123/MBDiff ." @default.
• W4387211592 created "2023-10-01" @default.
• W4387211592 creator A5006938103 @default.
• W4387211592 creator A5018181104 @default.
• W4387211592 creator A5088144059 @default.
• W4387211592 creator A5089732639 @default.
• W4387211592 date "2023-01-01" @default.
• W4387211592 modified "2023-10-01" @default.
• W4387211592 title "Medical Boundary Diffusion Model for Skin Lesion Segmentation" @default.
• W4387211592 cites W1901129140 @default.
• W4387211592 cites W2061253660 @default.
• W4387211592 cites W2565639579 @default.
• W4387211592 cites W2884436604 @default.
• W4387211592 cites W2884588972 @default.
• W4387211592 cites W3090920939 @default.
• W4387211592 cites W3096812112 @default.
• W4387211592 cites W3098712157 @default.
• W4387211592 cites W3104610662 @default.
• W4387211592 cites W3131500599 @default.
• W4387211592 cites W3174508405 @default.
• W4387211592 cites W3204166336 @default.
• W4387211592 cites W3205816419 @default.
• W4387211592 cites W4206841660 @default.
• W4387211592 cites W4220797664 @default.
• W4387211592 cites W4312933868 @default.
• W4387211592 cites W4316021925 @default.
• W4387211592 doi "https://doi.org/10.1007/978-3-031-43901-8_41" @default.
• W4387211592 hasPublicationYear "2023" @default.
• W4387211592 type Work @default.
• W4387211592 citedByCount "0" @default.
• W4387211592 crossrefType "book-chapter" @default.
• W4387211592 hasAuthorship W4387211592A5006938103 @default.
• W4387211592 hasAuthorship W4387211592A5018181104 @default.
• W4387211592 hasAuthorship W4387211592A5088144059 @default.
• W4387211592 hasAuthorship W4387211592A5089732639 @default.
• W4387211592 hasConcept C124504099 @default.
• W4387211592 hasConcept C134306372 @default.
• W4387211592 hasConcept C153180895 @default.
• W4387211592 hasConcept C154945302 @default.
• W4387211592 hasConcept C31972630 @default.
• W4387211592 hasConcept C33923547 @default.
• W4387211592 hasConcept C41008148 @default.
• W4387211592 hasConcept C62354387 @default.
• W4387211592 hasConcept C89600930 @default.
• W4387211592 hasConceptScore W4387211592C124504099 @default.
• W4387211592 hasConceptScore W4387211592C134306372 @default.
• W4387211592 hasConceptScore W4387211592C153180895 @default.
• W4387211592 hasConceptScore W4387211592C154945302 @default.
• W4387211592 hasConceptScore W4387211592C31972630 @default.
• W4387211592 hasConceptScore W4387211592C33923547 @default.
• W4387211592 hasConceptScore W4387211592C41008148 @default.
• W4387211592 hasConceptScore W4387211592C62354387 @default.
• W4387211592 hasConceptScore W4387211592C89600930 @default.
• W4387211592 hasLocation W43872115921 @default.
• W4387211592 hasOpenAccess W4387211592 @default.
• W4387211592 hasPrimaryLocation W43872115921 @default.
• W4387211592 hasRelatedWork W1669643531 @default.
• W4387211592 hasRelatedWork W1982826852 @default.
• W4387211592 hasRelatedWork W2005437358 @default.
• W4387211592 hasRelatedWork W2008656436 @default.
• W4387211592 hasRelatedWork W2023558673 @default.
• W4387211592 hasRelatedWork W2110230079 @default.
• W4387211592 hasRelatedWork W2134924024 @default.
• W4387211592 hasRelatedWork W2517104666 @default.
• W4387211592 hasRelatedWork W2613186388 @default.
• W4387211592 hasRelatedWork W1967061043 @default.
• W4387211592 isParatext "false" @default.
• W4387211592 isRetracted "false" @default.
• W4387211592 workType "book-chapter" @default.