Matches in SemOpenAlex for { <https://semopenalex.org/work/W3114032431> ?p ?o ?g. }
- W3114032431 abstract "The application of supervised deep learning methods in digital pathology is limited due to their sensitivity to domain shift. Digital Pathology is an area prone to high variability due to many sources, including the common practice of evaluating several consecutive tissue sections stained with different staining protocols. Obtaining labels for each stain is very expensive and time consuming as it requires a high level of domain knowledge. In this article, we propose an unsupervised augmentation approach based on adversarial image-to-image translation, which facilitates the training of stain invariant supervised convolutional neural networks. By training the network on one commonly used staining modality and applying it to images that include corresponding, but differently stained, tissue structures, the presented method demonstrates significant improvements over other approaches. These benefits are illustrated in the problem of glomeruli segmentation in seven different staining modalities (PAS, Jones H&E, CD68, Sirius Red, CD34, H&E and CD3) and analysis of the learned representations demonstrate their stain invariance." @default.
- W3114032431 created "2021-01-05" @default.
- W3114032431 creator A5016714459 @default.
- W3114032431 creator A5057185329 @default.
- W3114032431 creator A5060510601 @default.
- W3114032431 creator A5091361238 @default.
- W3114032431 date "2020-12-22" @default.
- W3114032431 modified "2023-09-27" @default.
- W3114032431 title "Towards Histopathological Stain Invariance by Unsupervised Domain Augmentation using Generative Adversarial Networks" @default.
- W3114032431 cites W1901129140 @default.
- W3114032431 cites W1987971958 @default.
- W3114032431 cites W2099471712 @default.
- W3114032431 cites W2129112648 @default.
- W3114032431 cites W2132162500 @default.
- W3114032431 cites W2234666690 @default.
- W3114032431 cites W2343160907 @default.
- W3114032431 cites W2537109170 @default.
- W3114032431 cites W2592929672 @default.
- W3114032431 cites W2756073160 @default.
- W3114032431 cites W2771464104 @default.
- W3114032431 cites W2772926238 @default.
- W3114032431 cites W2774208477 @default.
- W3114032431 cites W2789277655 @default.
- W3114032431 cites W2805134189 @default.
- W3114032431 cites W2890029252 @default.
- W3114032431 cites W2899906096 @default.
- W3114032431 cites W2902855764 @default.
- W3114032431 cites W2909488080 @default.
- W3114032431 cites W2914823990 @default.
- W3114032431 cites W2939898723 @default.
- W3114032431 cites W2948425579 @default.
- W3114032431 cites W2956362951 @default.
- W3114032431 cites W2960960151 @default.
- W3114032431 cites W2962793481 @default.
- W3114032431 cites W2962793691 @default.
- W3114032431 cites W2962858109 @default.
- W3114032431 cites W2962919088 @default.
- W3114032431 cites W2963404620 @default.
- W3114032431 cites W2963709863 @default.
- W3114032431 cites W2963767194 @default.
- W3114032431 cites W2963981733 @default.
- W3114032431 cites W2964358045 @default.
- W3114032431 cites W2965775801 @default.
- W3114032431 cites W2969278648 @default.
- W3114032431 cites W2971184828 @default.
- W3114032431 cites W2979583169 @default.
- W3114032431 cites W2981585480 @default.
- W3114032431 cites W3003384866 @default.
- W3114032431 cites W3014795415 @default.
- W3114032431 cites W3015803845 @default.
- W3114032431 cites W3026766084 @default.
- W3114032431 cites W3033819176 @default.
- W3114032431 cites W3034600949 @default.
- W3114032431 cites W3089090082 @default.
- W3114032431 cites W3099287508 @default.
- W3114032431 hasPublicationYear "2020" @default.
- W3114032431 type Work @default.
- W3114032431 sameAs 3114032431 @default.
- W3114032431 citedByCount "0" @default.
- W3114032431 crossrefType "posted-content" @default.
- W3114032431 hasAuthorship W3114032431A5016714459 @default.
- W3114032431 hasAuthorship W3114032431A5057185329 @default.
- W3114032431 hasAuthorship W3114032431A5060510601 @default.
- W3114032431 hasAuthorship W3114032431A5091361238 @default.
- W3114032431 hasConcept C108583219 @default.
- W3114032431 hasConcept C142724271 @default.
- W3114032431 hasConcept C153180895 @default.
- W3114032431 hasConcept C154945302 @default.
- W3114032431 hasConcept C2781294515 @default.
- W3114032431 hasConcept C31972630 @default.
- W3114032431 hasConcept C41008148 @default.
- W3114032431 hasConcept C71924100 @default.
- W3114032431 hasConcept C74864618 @default.
- W3114032431 hasConcept C81363708 @default.
- W3114032431 hasConcept C89600930 @default.
- W3114032431 hasConceptScore W3114032431C108583219 @default.
- W3114032431 hasConceptScore W3114032431C142724271 @default.
- W3114032431 hasConceptScore W3114032431C153180895 @default.
- W3114032431 hasConceptScore W3114032431C154945302 @default.
- W3114032431 hasConceptScore W3114032431C2781294515 @default.
- W3114032431 hasConceptScore W3114032431C31972630 @default.
- W3114032431 hasConceptScore W3114032431C41008148 @default.
- W3114032431 hasConceptScore W3114032431C71924100 @default.
- W3114032431 hasConceptScore W3114032431C74864618 @default.
- W3114032431 hasConceptScore W3114032431C81363708 @default.
- W3114032431 hasConceptScore W3114032431C89600930 @default.
- W3114032431 hasLocation W31140324311 @default.
- W3114032431 hasOpenAccess W3114032431 @default.
- W3114032431 hasPrimaryLocation W31140324311 @default.
- W3114032431 hasRelatedWork W2178072586 @default.
- W3114032431 hasRelatedWork W2806892763 @default.
- W3114032431 hasRelatedWork W2897705552 @default.
- W3114032431 hasRelatedWork W2899683012 @default.
- W3114032431 hasRelatedWork W2907719205 @default.
- W3114032431 hasRelatedWork W2962793691 @default.
- W3114032431 hasRelatedWork W2964152645 @default.
- W3114032431 hasRelatedWork W2969278648 @default.
- W3114032431 hasRelatedWork W2998954342 @default.
- W3114032431 hasRelatedWork W3010759804 @default.
- W3114032431 hasRelatedWork W3011386817 @default.