Matches in SemOpenAlex for { <https://semopenalex.org/work/W3116761024> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3116761024 endingPage "54" @default.
- W3116761024 startingPage "44" @default.
- W3116761024 abstract "Unsupervised learning can discover various diseases, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a single medical image to detect outliers either in the learned feature space or from high reconstruction loss. However, without considering continuity between multiple adjacent slices, they cannot directly discriminate diseases composed of the accumulation of subtle anatomical anomalies, such as Alzheimer’s Disease (AD). Moreover, no study has shown how unsupervised anomaly detection is associated with disease stages. Therefore, we propose a two-step method using Generative Adversarial Network-based multiple adjacent brain MRI slice reconstruction to detect AD at various stages: (Reconstruction) Wasserstein loss with Gradient Penalty $$+$$ $$ell _1$$ loss—trained on 3 healthy slices to reconstruct the next 3 ones—reconstructs unseen healthy/AD cases; (Diagnosis) Average/Maximum loss (e.g., $$ell _2$$ loss) per scan discriminates them, comparing the reconstructed/ground truth images. The results show that we can reliably detect AD at a very early stage with Receiver Operating Characteristics-Area Under the Curve (ROC-AUC) 0.780 while also detecting AD at a late stage much more accurately with ROC-AUC 0.917; since our method is fully unsupervised, it should also discover and alert any anomalies including rare disease." @default.
- W3116761024 created "2021-01-05" @default.
- W3116761024 creator A5006166354 @default.
- W3116761024 creator A5018297843 @default.
- W3116761024 creator A5028460960 @default.
- W3116761024 creator A5050229964 @default.
- W3116761024 creator A5062787398 @default.
- W3116761024 creator A5070342938 @default.
- W3116761024 creator A5081459146 @default.
- W3116761024 creator A5086118610 @default.
- W3116761024 date "2020-01-01" @default.
- W3116761024 modified "2023-10-16" @default.
- W3116761024 title "GAN-Based Multiple Adjacent Brain MRI Slice Reconstruction for Unsupervised Alzheimer’s Disease Diagnosis" @default.
- W3116761024 cites W1901129140 @default.
- W3116761024 cites W1901624583 @default.
- W3116761024 cites W1991952617 @default.
- W3116761024 cites W2057536936 @default.
- W3116761024 cites W2353776455 @default.
- W3116761024 cites W2582180708 @default.
- W3116761024 cites W2596339904 @default.
- W3116761024 cites W2740481439 @default.
- W3116761024 cites W2794022343 @default.
- W3116761024 cites W2806118840 @default.
- W3116761024 cites W2806489700 @default.
- W3116761024 cites W2884156795 @default.
- W3116761024 cites W2897079521 @default.
- W3116761024 cites W2905215565 @default.
- W3116761024 cites W2914570111 @default.
- W3116761024 cites W2944950225 @default.
- W3116761024 cites W2950680182 @default.
- W3116761024 cites W2964334073 @default.
- W3116761024 cites W2981036610 @default.
- W3116761024 cites W2982587597 @default.
- W3116761024 cites W3037287540 @default.
- W3116761024 cites W4288086194 @default.
- W3116761024 cites W66427752 @default.
- W3116761024 doi "https://doi.org/10.1007/978-3-030-63061-4_5" @default.
- W3116761024 hasPublicationYear "2020" @default.
- W3116761024 type Work @default.
- W3116761024 sameAs 3116761024 @default.
- W3116761024 citedByCount "8" @default.
- W3116761024 countsByYear W31167610242020 @default.
- W3116761024 countsByYear W31167610242021 @default.
- W3116761024 countsByYear W31167610242022 @default.
- W3116761024 countsByYear W31167610242023 @default.
- W3116761024 crossrefType "book-chapter" @default.
- W3116761024 hasAuthorship W3116761024A5006166354 @default.
- W3116761024 hasAuthorship W3116761024A5018297843 @default.
- W3116761024 hasAuthorship W3116761024A5028460960 @default.
- W3116761024 hasAuthorship W3116761024A5050229964 @default.
- W3116761024 hasAuthorship W3116761024A5062787398 @default.
- W3116761024 hasAuthorship W3116761024A5070342938 @default.
- W3116761024 hasAuthorship W3116761024A5081459146 @default.
- W3116761024 hasAuthorship W3116761024A5086118610 @default.
- W3116761024 hasBestOaLocation W31167610242 @default.
- W3116761024 hasConcept C119857082 @default.
- W3116761024 hasConcept C138885662 @default.
- W3116761024 hasConcept C146849305 @default.
- W3116761024 hasConcept C153180895 @default.
- W3116761024 hasConcept C154945302 @default.
- W3116761024 hasConcept C2776401178 @default.
- W3116761024 hasConcept C41008148 @default.
- W3116761024 hasConcept C41895202 @default.
- W3116761024 hasConcept C58471807 @default.
- W3116761024 hasConcept C739882 @default.
- W3116761024 hasConcept C79337645 @default.
- W3116761024 hasConcept C8038995 @default.
- W3116761024 hasConceptScore W3116761024C119857082 @default.
- W3116761024 hasConceptScore W3116761024C138885662 @default.
- W3116761024 hasConceptScore W3116761024C146849305 @default.
- W3116761024 hasConceptScore W3116761024C153180895 @default.
- W3116761024 hasConceptScore W3116761024C154945302 @default.
- W3116761024 hasConceptScore W3116761024C2776401178 @default.
- W3116761024 hasConceptScore W3116761024C41008148 @default.
- W3116761024 hasConceptScore W3116761024C41895202 @default.
- W3116761024 hasConceptScore W3116761024C58471807 @default.
- W3116761024 hasConceptScore W3116761024C739882 @default.
- W3116761024 hasConceptScore W3116761024C79337645 @default.
- W3116761024 hasConceptScore W3116761024C8038995 @default.
- W3116761024 hasLocation W31167610241 @default.
- W3116761024 hasLocation W31167610242 @default.
- W3116761024 hasLocation W31167610243 @default.
- W3116761024 hasOpenAccess W3116761024 @default.
- W3116761024 hasPrimaryLocation W31167610241 @default.
- W3116761024 hasRelatedWork W2056643656 @default.
- W3116761024 hasRelatedWork W2076520961 @default.
- W3116761024 hasRelatedWork W2363496559 @default.
- W3116761024 hasRelatedWork W2546942002 @default.
- W3116761024 hasRelatedWork W2554403468 @default.
- W3116761024 hasRelatedWork W2567596697 @default.
- W3116761024 hasRelatedWork W2898472682 @default.
- W3116761024 hasRelatedWork W2899055016 @default.
- W3116761024 hasRelatedWork W2942455380 @default.
- W3116761024 hasRelatedWork W3136392033 @default.
- W3116761024 isParatext "false" @default.
- W3116761024 isRetracted "false" @default.
- W3116761024 magId "3116761024" @default.
- W3116761024 workType "book-chapter" @default.