Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292109050> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4292109050 abstract "Multi-instance learning (MIL) is widely used in the computer-aided interpretation of pathological Whole Slide Images (WSIs) to solve the lack of pixel-wise or patch-wise annotations. Often, this approach directly applies natural image driven MIL algorithms which overlook the multi-scale (i.e. pyramidal) nature of WSIs. Off-the-shelf MIL algorithms are typically deployed on a single-scale of WSIs (e.g., 20x magnification), while human pathologists usually aggregate the global and local patterns in a multi-scale manner (e.g., by zooming in and out between different magnifications). In this study, we propose a novel cross-scale attention mechanism to explicitly aggregate inter-scale interactions into a single MIL network for Crohn's Disease (CD), which is a form of inflammatory bowel disease. The contribution of this paper is two-fold: (1) a cross-scale attention mechanism is proposed to aggregate features from different resolutions with multi-scale interaction; and (2) differential multi-scale attention visualizations are generated to localize explainable lesion patterns. By training ~250,000 H&E-stained Ascending Colon (AC) patches from 20 CD patient and 30 healthy control samples at different scales, our approach achieved a superior Area under the Curve (AUC) score of 0.8924 compared with baseline models. The official implementation is publicly available at https://github.com/hrlblab/CS-MIL." @default.
- W4292109050 created "2022-08-17" @default.
- W4292109050 creator A5005241662 @default.
- W4292109050 creator A5011476670 @default.
- W4292109050 creator A5016604916 @default.
- W4292109050 creator A5020518724 @default.
- W4292109050 creator A5036231550 @default.
- W4292109050 creator A5037133367 @default.
- W4292109050 creator A5048972725 @default.
- W4292109050 creator A5055115466 @default.
- W4292109050 creator A5058681839 @default.
- W4292109050 creator A5067191302 @default.
- W4292109050 creator A5067212450 @default.
- W4292109050 creator A5073353188 @default.
- W4292109050 creator A5075735203 @default.
- W4292109050 creator A5085028455 @default.
- W4292109050 creator A5086819137 @default.
- W4292109050 date "2022-08-15" @default.
- W4292109050 modified "2023-09-26" @default.
- W4292109050 title "Cross-scale Attention Guided Multi-instance Learning for Crohn's Disease Diagnosis with Pathological Images" @default.
- W4292109050 doi "https://doi.org/10.48550/arxiv.2208.07322" @default.
- W4292109050 hasPublicationYear "2022" @default.
- W4292109050 type Work @default.
- W4292109050 citedByCount "0" @default.
- W4292109050 crossrefType "posted-content" @default.
- W4292109050 hasAuthorship W4292109050A5005241662 @default.
- W4292109050 hasAuthorship W4292109050A5011476670 @default.
- W4292109050 hasAuthorship W4292109050A5016604916 @default.
- W4292109050 hasAuthorship W4292109050A5020518724 @default.
- W4292109050 hasAuthorship W4292109050A5036231550 @default.
- W4292109050 hasAuthorship W4292109050A5037133367 @default.
- W4292109050 hasAuthorship W4292109050A5048972725 @default.
- W4292109050 hasAuthorship W4292109050A5055115466 @default.
- W4292109050 hasAuthorship W4292109050A5058681839 @default.
- W4292109050 hasAuthorship W4292109050A5067191302 @default.
- W4292109050 hasAuthorship W4292109050A5067212450 @default.
- W4292109050 hasAuthorship W4292109050A5073353188 @default.
- W4292109050 hasAuthorship W4292109050A5075735203 @default.
- W4292109050 hasAuthorship W4292109050A5085028455 @default.
- W4292109050 hasAuthorship W4292109050A5086819137 @default.
- W4292109050 hasBestOaLocation W42921090501 @default.
- W4292109050 hasConcept C119857082 @default.
- W4292109050 hasConcept C124913957 @default.
- W4292109050 hasConcept C151730666 @default.
- W4292109050 hasConcept C153180895 @default.
- W4292109050 hasConcept C15336307 @default.
- W4292109050 hasConcept C154945302 @default.
- W4292109050 hasConcept C159985019 @default.
- W4292109050 hasConcept C160633673 @default.
- W4292109050 hasConcept C192562407 @default.
- W4292109050 hasConcept C205649164 @default.
- W4292109050 hasConcept C2778755073 @default.
- W4292109050 hasConcept C41008148 @default.
- W4292109050 hasConcept C4144372 @default.
- W4292109050 hasConcept C4679612 @default.
- W4292109050 hasConcept C58640448 @default.
- W4292109050 hasConcept C86803240 @default.
- W4292109050 hasConceptScore W4292109050C119857082 @default.
- W4292109050 hasConceptScore W4292109050C124913957 @default.
- W4292109050 hasConceptScore W4292109050C151730666 @default.
- W4292109050 hasConceptScore W4292109050C153180895 @default.
- W4292109050 hasConceptScore W4292109050C15336307 @default.
- W4292109050 hasConceptScore W4292109050C154945302 @default.
- W4292109050 hasConceptScore W4292109050C159985019 @default.
- W4292109050 hasConceptScore W4292109050C160633673 @default.
- W4292109050 hasConceptScore W4292109050C192562407 @default.
- W4292109050 hasConceptScore W4292109050C205649164 @default.
- W4292109050 hasConceptScore W4292109050C2778755073 @default.
- W4292109050 hasConceptScore W4292109050C41008148 @default.
- W4292109050 hasConceptScore W4292109050C4144372 @default.
- W4292109050 hasConceptScore W4292109050C4679612 @default.
- W4292109050 hasConceptScore W4292109050C58640448 @default.
- W4292109050 hasConceptScore W4292109050C86803240 @default.
- W4292109050 hasLocation W42921090501 @default.
- W4292109050 hasOpenAccess W4292109050 @default.
- W4292109050 hasPrimaryLocation W42921090501 @default.
- W4292109050 hasRelatedWork W1964191339 @default.
- W4292109050 hasRelatedWork W1970243926 @default.
- W4292109050 hasRelatedWork W207516188 @default.
- W4292109050 hasRelatedWork W2124132578 @default.
- W4292109050 hasRelatedWork W2136485282 @default.
- W4292109050 hasRelatedWork W2546871836 @default.
- W4292109050 hasRelatedWork W2548791488 @default.
- W4292109050 hasRelatedWork W2565015337 @default.
- W4292109050 hasRelatedWork W2592141703 @default.
- W4292109050 hasRelatedWork W2902972690 @default.
- W4292109050 isParatext "false" @default.
- W4292109050 isRetracted "false" @default.
- W4292109050 workType "article" @default.