Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197793506> ?p ?o ?g. }
- W3197793506 endingPage "336" @default.
- W3197793506 startingPage "311" @default.
- W3197793506 abstract "Recently, Artificial Intelligence (AI) and more particularly Deep Learning (DL) applications gained significant importance in several domains such as computer vision, robotics, medical imaging, etc. Despite the excellent results of AI models, in terms of precision and performance, their decisions are not always interpretable and explainable, which makes from them a black box. Since May 2018, the general data protection regulation (GDPR) requires a right of explanation for the output of an algorithm, which is necessary and justified for several examples such as autonomous cars and computer-aided diagnosis (CAD) systems. As a result, a high interest in terms of research has been given recently to the domain of Explainable Artificial Intelligence (XAI). In this book chapter, we propose an approach for explaining Deep Learning algorithms when applied to image classification and segmentation. The proposed approach allows to provide the most appropriate explanation method and the most accurate and explainable DL model. As a use case, we applied our approach for explaining DL models used Covid-19 image classification and segmentation with two modalities: X-ray and CT-scan images. Experimental results showed the interest of our explanation approach within three facts: (1) identification of the most interpretable DL model; (2) measurement of positive and negative contributions of input parameters (image pixels) in the decision of DL models; (3) detection of data (training and validation datasets) biases, where the deep neural networks are focusing on image regions that are not supposed to be important. The provided explanations were evaluated by doctors and physicians who confirmed the accuracy of our results." @default.
- W3197793506 created "2021-09-13" @default.
- W3197793506 creator A5006034468 @default.
- W3197793506 creator A5026980527 @default.
- W3197793506 creator A5027972689 @default.
- W3197793506 creator A5028300366 @default.
- W3197793506 creator A5086430193 @default.
- W3197793506 date "2021-03-12" @default.
- W3197793506 modified "2023-09-27" @default.
- W3197793506 title "Explainable Deep Learning for Covid-19 Detection Using Chest X-ray and CT-Scan Images" @default.
- W3197793506 cites W1504661965 @default.
- W3197793506 cites W1525827451 @default.
- W3197793506 cites W1787224781 @default.
- W3197793506 cites W2008152292 @default.
- W3197793506 cites W2059134484 @default.
- W3197793506 cites W2097117768 @default.
- W3197793506 cites W2194775991 @default.
- W3197793506 cites W2195388612 @default.
- W3197793506 cites W2240067561 @default.
- W3197793506 cites W2282821441 @default.
- W3197793506 cites W2295107390 @default.
- W3197793506 cites W2492248554 @default.
- W3197793506 cites W2755757081 @default.
- W3197793506 cites W2769746012 @default.
- W3197793506 cites W2890269507 @default.
- W3197793506 cites W2962858109 @default.
- W3197793506 cites W2963039693 @default.
- W3197793506 cites W2963446712 @default.
- W3197793506 cites W2973136764 @default.
- W3197793506 cites W3007510962 @default.
- W3197793506 cites W3013277995 @default.
- W3197793506 cites W3019531985 @default.
- W3197793506 cites W3021085078 @default.
- W3197793506 cites W3027682070 @default.
- W3197793506 cites W3036552116 @default.
- W3197793506 cites W3036638392 @default.
- W3197793506 cites W3039563973 @default.
- W3197793506 cites W3054666633 @default.
- W3197793506 cites W3126084544 @default.
- W3197793506 cites W3159001838 @default.
- W3197793506 cites W338347518 @default.
- W3197793506 doi "https://doi.org/10.1007/978-3-030-72752-9_16" @default.
- W3197793506 hasPublicationYear "2021" @default.
- W3197793506 type Work @default.
- W3197793506 sameAs 3197793506 @default.
- W3197793506 citedByCount "2" @default.
- W3197793506 countsByYear W31977935062022 @default.
- W3197793506 countsByYear W31977935062023 @default.
- W3197793506 crossrefType "book-chapter" @default.
- W3197793506 hasAuthorship W3197793506A5006034468 @default.
- W3197793506 hasAuthorship W3197793506A5026980527 @default.
- W3197793506 hasAuthorship W3197793506A5027972689 @default.
- W3197793506 hasAuthorship W3197793506A5028300366 @default.
- W3197793506 hasAuthorship W3197793506A5086430193 @default.
- W3197793506 hasConcept C108583219 @default.
- W3197793506 hasConcept C115961682 @default.
- W3197793506 hasConcept C116834253 @default.
- W3197793506 hasConcept C119857082 @default.
- W3197793506 hasConcept C134306372 @default.
- W3197793506 hasConcept C153180895 @default.
- W3197793506 hasConcept C154945302 @default.
- W3197793506 hasConcept C160633673 @default.
- W3197793506 hasConcept C33923547 @default.
- W3197793506 hasConcept C36503486 @default.
- W3197793506 hasConcept C41008148 @default.
- W3197793506 hasConcept C50644808 @default.
- W3197793506 hasConcept C59822182 @default.
- W3197793506 hasConcept C86803240 @default.
- W3197793506 hasConcept C89600930 @default.
- W3197793506 hasConceptScore W3197793506C108583219 @default.
- W3197793506 hasConceptScore W3197793506C115961682 @default.
- W3197793506 hasConceptScore W3197793506C116834253 @default.
- W3197793506 hasConceptScore W3197793506C119857082 @default.
- W3197793506 hasConceptScore W3197793506C134306372 @default.
- W3197793506 hasConceptScore W3197793506C153180895 @default.
- W3197793506 hasConceptScore W3197793506C154945302 @default.
- W3197793506 hasConceptScore W3197793506C160633673 @default.
- W3197793506 hasConceptScore W3197793506C33923547 @default.
- W3197793506 hasConceptScore W3197793506C36503486 @default.
- W3197793506 hasConceptScore W3197793506C41008148 @default.
- W3197793506 hasConceptScore W3197793506C50644808 @default.
- W3197793506 hasConceptScore W3197793506C59822182 @default.
- W3197793506 hasConceptScore W3197793506C86803240 @default.
- W3197793506 hasConceptScore W3197793506C89600930 @default.
- W3197793506 hasLocation W31977935061 @default.
- W3197793506 hasOpenAccess W3197793506 @default.
- W3197793506 hasPrimaryLocation W31977935061 @default.
- W3197793506 hasRelatedWork W2136485282 @default.
- W3197793506 hasRelatedWork W2546871836 @default.
- W3197793506 hasRelatedWork W2790662084 @default.
- W3197793506 hasRelatedWork W4223943233 @default.
- W3197793506 hasRelatedWork W4225161397 @default.
- W3197793506 hasRelatedWork W4312200629 @default.
- W3197793506 hasRelatedWork W4360585206 @default.
- W3197793506 hasRelatedWork W4364306694 @default.
- W3197793506 hasRelatedWork W4380075502 @default.
- W3197793506 hasRelatedWork W4380086463 @default.
- W3197793506 isParatext "false" @default.