Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225620582> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4225620582 abstract "Skin lesions can be an early indicator of a wide range of infectious and other diseases. The use of deep learning (DL) models to diagnose skin lesions has great potential in assisting clinicians with prescreening patients. However, these models often learn biases inherent in training data, which can lead to a performance gap in the diagnosis of people with light and/or dark skin tones. To the best of our knowledge, limited work has been done on identifying, let alone reducing, model bias in skin disease classification and segmentation. In this paper, we examine DL fairness and demonstrate the existence of bias in classification and segmentation models for subpopulations with darker skin tones compared to individuals with lighter skin tones, for specific diseases including Lyme, Tinea Corporis and Herpes Zoster. Then, we propose a novel preprocessing, data alteration method, called EdgeMixup, to improve model fairness with a linear combination of an input skin lesion image and a corresponding a predicted edge detection mask combined with color saturation alteration. For the task of skin disease classification, EdgeMixup outperforms much more complex competing methods such as adversarial approaches, achieving a 10.99% reduction in accuracy gap between light and dark skin tone samples, and resulting in 8.4% improved performance for an underrepresented subpopulation." @default.
- W4225620582 created "2022-05-05" @default.
- W4225620582 creator A5000880653 @default.
- W4225620582 creator A5017568333 @default.
- W4225620582 creator A5030280857 @default.
- W4225620582 creator A5050068749 @default.
- W4225620582 creator A5050207215 @default.
- W4225620582 creator A5070605476 @default.
- W4225620582 creator A5078445265 @default.
- W4225620582 creator A5082440285 @default.
- W4225620582 date "2022-02-28" @default.
- W4225620582 modified "2023-09-24" @default.
- W4225620582 title "EdgeMixup: Improving Fairness for Skin Disease Classification and Segmentation" @default.
- W4225620582 doi "https://doi.org/10.48550/arxiv.2202.13883" @default.
- W4225620582 hasPublicationYear "2022" @default.
- W4225620582 type Work @default.
- W4225620582 citedByCount "0" @default.
- W4225620582 crossrefType "posted-content" @default.
- W4225620582 hasAuthorship W4225620582A5000880653 @default.
- W4225620582 hasAuthorship W4225620582A5017568333 @default.
- W4225620582 hasAuthorship W4225620582A5030280857 @default.
- W4225620582 hasAuthorship W4225620582A5050068749 @default.
- W4225620582 hasAuthorship W4225620582A5050207215 @default.
- W4225620582 hasAuthorship W4225620582A5070605476 @default.
- W4225620582 hasAuthorship W4225620582A5078445265 @default.
- W4225620582 hasAuthorship W4225620582A5082440285 @default.
- W4225620582 hasBestOaLocation W42256205821 @default.
- W4225620582 hasConcept C108583219 @default.
- W4225620582 hasConcept C119857082 @default.
- W4225620582 hasConcept C153180895 @default.
- W4225620582 hasConcept C154945302 @default.
- W4225620582 hasConcept C16005928 @default.
- W4225620582 hasConcept C2775983603 @default.
- W4225620582 hasConcept C2779489039 @default.
- W4225620582 hasConcept C2988168687 @default.
- W4225620582 hasConcept C34736171 @default.
- W4225620582 hasConcept C41008148 @default.
- W4225620582 hasConcept C523546767 @default.
- W4225620582 hasConcept C54355233 @default.
- W4225620582 hasConcept C71924100 @default.
- W4225620582 hasConcept C86803240 @default.
- W4225620582 hasConcept C89600930 @default.
- W4225620582 hasConceptScore W4225620582C108583219 @default.
- W4225620582 hasConceptScore W4225620582C119857082 @default.
- W4225620582 hasConceptScore W4225620582C153180895 @default.
- W4225620582 hasConceptScore W4225620582C154945302 @default.
- W4225620582 hasConceptScore W4225620582C16005928 @default.
- W4225620582 hasConceptScore W4225620582C2775983603 @default.
- W4225620582 hasConceptScore W4225620582C2779489039 @default.
- W4225620582 hasConceptScore W4225620582C2988168687 @default.
- W4225620582 hasConceptScore W4225620582C34736171 @default.
- W4225620582 hasConceptScore W4225620582C41008148 @default.
- W4225620582 hasConceptScore W4225620582C523546767 @default.
- W4225620582 hasConceptScore W4225620582C54355233 @default.
- W4225620582 hasConceptScore W4225620582C71924100 @default.
- W4225620582 hasConceptScore W4225620582C86803240 @default.
- W4225620582 hasConceptScore W4225620582C89600930 @default.
- W4225620582 hasLocation W42256205821 @default.
- W4225620582 hasOpenAccess W4225620582 @default.
- W4225620582 hasPrimaryLocation W42256205821 @default.
- W4225620582 hasRelatedWork W2609625738 @default.
- W4225620582 hasRelatedWork W2790662084 @default.
- W4225620582 hasRelatedWork W2948658236 @default.
- W4225620582 hasRelatedWork W3014300295 @default.
- W4225620582 hasRelatedWork W4211209597 @default.
- W4225620582 hasRelatedWork W4220785415 @default.
- W4225620582 hasRelatedWork W4223943233 @default.
- W4225620582 hasRelatedWork W4225620582 @default.
- W4225620582 hasRelatedWork W4243168368 @default.
- W4225620582 hasRelatedWork W4281653405 @default.
- W4225620582 isParatext "false" @default.
- W4225620582 isRetracted "false" @default.
- W4225620582 workType "article" @default.