Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205422329> ?p ?o ?g. }
- W3205422329 endingPage "1951" @default.
- W3205422329 startingPage "1951" @default.
- W3205422329 abstract "In the automatic diagnosis of ocular toxoplasmosis (OT), Deep Learning (DL) has arisen as a powerful and promising approach for diagnosis. However, despite the good performance of the models, decision rules should be interpretable to elicit trust from the medical community. Therefore, the development of an evaluation methodology to assess DL models based on interpretability methods is a challenging task that is necessary to extend the use of AI among clinicians. In this work, we propose a novel methodology to quantify the similarity between the decision rules used by a DL model and an ophthalmologist, based on the assumption that doctors are more likely to trust a prediction that was based on decision rules they can understand. Given an eye fundus image with OT, the proposed methodology compares the segmentation mask of OT lesions labeled by an ophthalmologist with the attribution matrix produced by interpretability methods. Furthermore, an open dataset that includes the eye fundus images and the segmentation masks is shared with the community. The proposal was tested on three different DL architectures. The results suggest that complex models tend to perform worse in terms of likelihood to be trusted while achieving better results in sensitivity and specificity." @default.
- W3205422329 created "2021-10-25" @default.
- W3205422329 creator A5003348717 @default.
- W3205422329 creator A5017068244 @default.
- W3205422329 creator A5023990593 @default.
- W3205422329 creator A5028615417 @default.
- W3205422329 creator A5043334355 @default.
- W3205422329 creator A5052597406 @default.
- W3205422329 creator A5056006771 @default.
- W3205422329 creator A5056656076 @default.
- W3205422329 creator A5063513544 @default.
- W3205422329 creator A5069212138 @default.
- W3205422329 creator A5082861421 @default.
- W3205422329 date "2021-10-21" @default.
- W3205422329 modified "2023-10-17" @default.
- W3205422329 title "A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images" @default.
- W3205422329 cites W1787224781 @default.
- W3205422329 cites W2089122000 @default.
- W3205422329 cites W2097659338 @default.
- W3205422329 cites W2131421899 @default.
- W3205422329 cites W2794284562 @default.
- W3205422329 cites W2903896358 @default.
- W3205422329 cites W2912072952 @default.
- W3205422329 cites W2919115771 @default.
- W3205422329 cites W2964303497 @default.
- W3205422329 cites W3019643191 @default.
- W3205422329 cites W3035941285 @default.
- W3205422329 cites W3036458852 @default.
- W3205422329 cites W3102363003 @default.
- W3205422329 cites W3140854437 @default.
- W3205422329 cites W3175311671 @default.
- W3205422329 cites W3194668998 @default.
- W3205422329 doi "https://doi.org/10.3390/diagnostics11111951" @default.
- W3205422329 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8617957" @default.
- W3205422329 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34829299" @default.
- W3205422329 hasPublicationYear "2021" @default.
- W3205422329 type Work @default.
- W3205422329 sameAs 3205422329 @default.
- W3205422329 citedByCount "0" @default.
- W3205422329 crossrefType "journal-article" @default.
- W3205422329 hasAuthorship W3205422329A5003348717 @default.
- W3205422329 hasAuthorship W3205422329A5017068244 @default.
- W3205422329 hasAuthorship W3205422329A5023990593 @default.
- W3205422329 hasAuthorship W3205422329A5028615417 @default.
- W3205422329 hasAuthorship W3205422329A5043334355 @default.
- W3205422329 hasAuthorship W3205422329A5052597406 @default.
- W3205422329 hasAuthorship W3205422329A5056006771 @default.
- W3205422329 hasAuthorship W3205422329A5056656076 @default.
- W3205422329 hasAuthorship W3205422329A5063513544 @default.
- W3205422329 hasAuthorship W3205422329A5069212138 @default.
- W3205422329 hasAuthorship W3205422329A5082861421 @default.
- W3205422329 hasBestOaLocation W32054223291 @default.
- W3205422329 hasConcept C108583219 @default.
- W3205422329 hasConcept C118487528 @default.
- W3205422329 hasConcept C119857082 @default.
- W3205422329 hasConcept C143299363 @default.
- W3205422329 hasConcept C153180895 @default.
- W3205422329 hasConcept C154945302 @default.
- W3205422329 hasConcept C15744967 @default.
- W3205422329 hasConcept C2776391266 @default.
- W3205422329 hasConcept C2781067378 @default.
- W3205422329 hasConcept C41008148 @default.
- W3205422329 hasConcept C71924100 @default.
- W3205422329 hasConcept C77805123 @default.
- W3205422329 hasConcept C89600930 @default.
- W3205422329 hasConceptScore W3205422329C108583219 @default.
- W3205422329 hasConceptScore W3205422329C118487528 @default.
- W3205422329 hasConceptScore W3205422329C119857082 @default.
- W3205422329 hasConceptScore W3205422329C143299363 @default.
- W3205422329 hasConceptScore W3205422329C153180895 @default.
- W3205422329 hasConceptScore W3205422329C154945302 @default.
- W3205422329 hasConceptScore W3205422329C15744967 @default.
- W3205422329 hasConceptScore W3205422329C2776391266 @default.
- W3205422329 hasConceptScore W3205422329C2781067378 @default.
- W3205422329 hasConceptScore W3205422329C41008148 @default.
- W3205422329 hasConceptScore W3205422329C71924100 @default.
- W3205422329 hasConceptScore W3205422329C77805123 @default.
- W3205422329 hasConceptScore W3205422329C89600930 @default.
- W3205422329 hasFunder F4320328088 @default.
- W3205422329 hasIssue "11" @default.
- W3205422329 hasLocation W32054223291 @default.
- W3205422329 hasLocation W32054223292 @default.
- W3205422329 hasLocation W32054223293 @default.
- W3205422329 hasLocation W32054223294 @default.
- W3205422329 hasOpenAccess W3205422329 @default.
- W3205422329 hasPrimaryLocation W32054223291 @default.
- W3205422329 hasRelatedWork W2605281151 @default.
- W3205422329 hasRelatedWork W3006943036 @default.
- W3205422329 hasRelatedWork W3129898729 @default.
- W3205422329 hasRelatedWork W3191046242 @default.
- W3205422329 hasRelatedWork W4206534706 @default.
- W3205422329 hasRelatedWork W4213225422 @default.
- W3205422329 hasRelatedWork W4229079080 @default.
- W3205422329 hasRelatedWork W4294031299 @default.
- W3205422329 hasRelatedWork W4299487748 @default.
- W3205422329 hasRelatedWork W4310880831 @default.
- W3205422329 hasVolume "11" @default.
- W3205422329 isParatext "false" @default.