Matches in SemOpenAlex for { <https://semopenalex.org/work/W2914570111> ?p ?o ?g. }
- W2914570111 endingPage "44" @default.
- W2914570111 startingPage "30" @default.
- W2914570111 abstract "Obtaining expert labels in clinical imaging is difficult since exhaustive annotation is time-consuming. Furthermore, not all possibly relevant markers may be known and sufficiently well described a priori to even guide annotation. While supervised learning yields good results if expert labeled training data is available, the visual variability, and thus the vocabulary of findings, we can detect and exploit, is limited to the annotated lesions. Here, we present fast AnoGAN (f-AnoGAN), a generative adversarial network (GAN) based unsupervised learning approach capable of identifying anomalous images and image segments, that can serve as imaging biomarker candidates. We build a generative model of healthy training data, and propose and evaluate a fast mapping technique of new data to the GAN’s latent space. The mapping is based on a trained encoder, and anomalies are detected via a combined anomaly score based on the building blocks of the trained model – comprising a discriminator feature residual error and an image reconstruction error. In the experiments on optical coherence tomography data, we compare the proposed method with alternative approaches, and provide comprehensive empirical evidence that f-AnoGAN outperforms alternative approaches and yields high anomaly detection accuracy. In addition, a visual Turing test with two retina experts showed that the generated images are indistinguishable from real normal retinal OCT images. The f-AnoGAN code is available at https://github.com/tSchlegl/f-AnoGAN." @default.
- W2914570111 created "2019-02-21" @default.
- W2914570111 creator A5003511566 @default.
- W2914570111 creator A5003998290 @default.
- W2914570111 creator A5013612641 @default.
- W2914570111 creator A5053563726 @default.
- W2914570111 creator A5060814361 @default.
- W2914570111 date "2019-05-01" @default.
- W2914570111 modified "2023-10-17" @default.
- W2914570111 title "f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks" @default.
- W2914570111 cites W1019830208 @default.
- W2914570111 cites W1999327911 @default.
- W2914570111 cites W2014761989 @default.
- W2914570111 cites W2089554624 @default.
- W2914570111 cites W2109928907 @default.
- W2914570111 cites W2115627867 @default.
- W2914570111 cites W2127318120 @default.
- W2914570111 cites W2130686832 @default.
- W2914570111 cites W2161326860 @default.
- W2914570111 cites W2164583551 @default.
- W2914570111 cites W2340896621 @default.
- W2914570111 cites W2404901863 @default.
- W2914570111 cites W2493683088 @default.
- W2914570111 cites W2548063209 @default.
- W2914570111 cites W2581082771 @default.
- W2914570111 cites W2615412239 @default.
- W2914570111 cites W2621101817 @default.
- W2914570111 cites W2763099889 @default.
- W2914570111 cites W2775674471 @default.
- W2914570111 cites W2793232926 @default.
- W2914570111 cites W2963061824 @default.
- W2914570111 cites W2963798233 @default.
- W2914570111 cites W2964191491 @default.
- W2914570111 doi "https://doi.org/10.1016/j.media.2019.01.010" @default.
- W2914570111 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30831356" @default.
- W2914570111 hasPublicationYear "2019" @default.
- W2914570111 type Work @default.
- W2914570111 sameAs 2914570111 @default.
- W2914570111 citedByCount "654" @default.
- W2914570111 countsByYear W29145701112019 @default.
- W2914570111 countsByYear W29145701112020 @default.
- W2914570111 countsByYear W29145701112021 @default.
- W2914570111 countsByYear W29145701112022 @default.
- W2914570111 countsByYear W29145701112023 @default.
- W2914570111 crossrefType "journal-article" @default.
- W2914570111 hasAuthorship W2914570111A5003511566 @default.
- W2914570111 hasAuthorship W2914570111A5003998290 @default.
- W2914570111 hasAuthorship W2914570111A5013612641 @default.
- W2914570111 hasAuthorship W2914570111A5053563726 @default.
- W2914570111 hasAuthorship W2914570111A5060814361 @default.
- W2914570111 hasConcept C111919701 @default.
- W2914570111 hasConcept C11413529 @default.
- W2914570111 hasConcept C119857082 @default.
- W2914570111 hasConcept C138885662 @default.
- W2914570111 hasConcept C153180895 @default.
- W2914570111 hasConcept C154945302 @default.
- W2914570111 hasConcept C155512373 @default.
- W2914570111 hasConcept C177264268 @default.
- W2914570111 hasConcept C199360897 @default.
- W2914570111 hasConcept C2776321320 @default.
- W2914570111 hasConcept C2776401178 @default.
- W2914570111 hasConcept C2776760102 @default.
- W2914570111 hasConcept C2779803651 @default.
- W2914570111 hasConcept C41008148 @default.
- W2914570111 hasConcept C41895202 @default.
- W2914570111 hasConcept C43126263 @default.
- W2914570111 hasConcept C739882 @default.
- W2914570111 hasConcept C76155785 @default.
- W2914570111 hasConcept C94915269 @default.
- W2914570111 hasConceptScore W2914570111C111919701 @default.
- W2914570111 hasConceptScore W2914570111C11413529 @default.
- W2914570111 hasConceptScore W2914570111C119857082 @default.
- W2914570111 hasConceptScore W2914570111C138885662 @default.
- W2914570111 hasConceptScore W2914570111C153180895 @default.
- W2914570111 hasConceptScore W2914570111C154945302 @default.
- W2914570111 hasConceptScore W2914570111C155512373 @default.
- W2914570111 hasConceptScore W2914570111C177264268 @default.
- W2914570111 hasConceptScore W2914570111C199360897 @default.
- W2914570111 hasConceptScore W2914570111C2776321320 @default.
- W2914570111 hasConceptScore W2914570111C2776401178 @default.
- W2914570111 hasConceptScore W2914570111C2776760102 @default.
- W2914570111 hasConceptScore W2914570111C2779803651 @default.
- W2914570111 hasConceptScore W2914570111C41008148 @default.
- W2914570111 hasConceptScore W2914570111C41895202 @default.
- W2914570111 hasConceptScore W2914570111C43126263 @default.
- W2914570111 hasConceptScore W2914570111C739882 @default.
- W2914570111 hasConceptScore W2914570111C76155785 @default.
- W2914570111 hasConceptScore W2914570111C94915269 @default.
- W2914570111 hasFunder F4320321181 @default.
- W2914570111 hasFunder F4320322325 @default.
- W2914570111 hasLocation W29145701111 @default.
- W2914570111 hasOpenAccess W2914570111 @default.
- W2914570111 hasPrimaryLocation W29145701111 @default.
- W2914570111 hasRelatedWork W1489300767 @default.
- W2914570111 hasRelatedWork W1980965563 @default.
- W2914570111 hasRelatedWork W2057775761 @default.
- W2914570111 hasRelatedWork W2387995142 @default.
- W2914570111 hasRelatedWork W2896600774 @default.