Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804976> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4385804976 abstract "Identifying the type of kidney stones can allow urologists to determine their cause of formation, improving the prescription of appropriate treatments to diminish future relapses. Currently, the associated ex-vivo diagnosis (known as Morpho-constitutional Analysis, MCA) is time-consuming, expensive and requires a great deal of experience, as it requires a visual analysis component that is highly operator dependant. Recently, machine learning methods have been developed for in-vivo endoscopic stone recognition. Deep Learning (DL) based methods outperform non-DL methods in terms of accuracy but lack explainability. Despite this trade-off, when it comes to making high-stakes decisions, it’s important to prioritize understandable Computer-Aided Diagnosis (CADx) that suggests a course of action based on reasonable evidence, rather than a model prescribing a course of action. In this proposal, we learn Prototypical Parts (PPs) per kidney stone subtype, which are used by the DL model to generate an output classification. Using PPs in the classification task enables case-based reasoning explanations for such output, thus making the model interpretable. In addition, we modify global visual characteristics to describe their relevance to the PPs and the sensitivity of our model’s performance. With this, we provide explanations with additional information at the sample, class and model levels in contrast to previous works. Although our implementation’s average accuracy is lower than state-of-the-art (SOTA) non-interpretable DL models by 1.5%, our models perform 2.8% better on perturbed images with a lower standard deviation, without adversarial training. Thus, Learning PPs has the potential to create more robust DL models. Code at: https://github.com/DanielF29/Prototipical-Parts" @default.
- W4385804976 created "2023-08-15" @default.
- W4385804976 creator A5033024566 @default.
- W4385804976 creator A5044516813 @default.
- W4385804976 creator A5058366337 @default.
- W4385804976 creator A5066403560 @default.
- W4385804976 creator A5072985093 @default.
- W4385804976 creator A5081235802 @default.
- W4385804976 creator A5089017788 @default.
- W4385804976 date "2023-06-01" @default.
- W4385804976 modified "2023-10-09" @default.
- W4385804976 title "Deep Prototypical-Parts Ease Morphological Kidney Stone Identification and are Competitively Robust to Photometric Perturbations" @default.
- W4385804976 cites W1998096232 @default.
- W4385804976 cites W2026484804 @default.
- W4385804976 cites W2419510799 @default.
- W4385804976 cites W2773003563 @default.
- W4385804976 cites W2786890437 @default.
- W4385804976 cites W2797090668 @default.
- W4385804976 cites W2913223168 @default.
- W4385804976 cites W3006594177 @default.
- W4385804976 cites W3082816544 @default.
- W4385804976 cites W3111630737 @default.
- W4385804976 cites W3134171531 @default.
- W4385804976 cites W4200254023 @default.
- W4385804976 cites W4206812748 @default.
- W4385804976 cites W4236047693 @default.
- W4385804976 cites W4245069552 @default.
- W4385804976 doi "https://doi.org/10.1109/cvprw59228.2023.00035" @default.
- W4385804976 hasPublicationYear "2023" @default.
- W4385804976 type Work @default.
- W4385804976 citedByCount "0" @default.
- W4385804976 crossrefType "proceedings-article" @default.
- W4385804976 hasAuthorship W4385804976A5033024566 @default.
- W4385804976 hasAuthorship W4385804976A5044516813 @default.
- W4385804976 hasAuthorship W4385804976A5058366337 @default.
- W4385804976 hasAuthorship W4385804976A5066403560 @default.
- W4385804976 hasAuthorship W4385804976A5072985093 @default.
- W4385804976 hasAuthorship W4385804976A5081235802 @default.
- W4385804976 hasAuthorship W4385804976A5089017788 @default.
- W4385804976 hasBestOaLocation W43858049762 @default.
- W4385804976 hasConcept C108583219 @default.
- W4385804976 hasConcept C119857082 @default.
- W4385804976 hasConcept C127413603 @default.
- W4385804976 hasConcept C153180895 @default.
- W4385804976 hasConcept C154945302 @default.
- W4385804976 hasConcept C158154518 @default.
- W4385804976 hasConcept C17744445 @default.
- W4385804976 hasConcept C199539241 @default.
- W4385804976 hasConcept C201995342 @default.
- W4385804976 hasConcept C2776502983 @default.
- W4385804976 hasConcept C2780451532 @default.
- W4385804976 hasConcept C37736160 @default.
- W4385804976 hasConcept C41008148 @default.
- W4385804976 hasConceptScore W4385804976C108583219 @default.
- W4385804976 hasConceptScore W4385804976C119857082 @default.
- W4385804976 hasConceptScore W4385804976C127413603 @default.
- W4385804976 hasConceptScore W4385804976C153180895 @default.
- W4385804976 hasConceptScore W4385804976C154945302 @default.
- W4385804976 hasConceptScore W4385804976C158154518 @default.
- W4385804976 hasConceptScore W4385804976C17744445 @default.
- W4385804976 hasConceptScore W4385804976C199539241 @default.
- W4385804976 hasConceptScore W4385804976C201995342 @default.
- W4385804976 hasConceptScore W4385804976C2776502983 @default.
- W4385804976 hasConceptScore W4385804976C2780451532 @default.
- W4385804976 hasConceptScore W4385804976C37736160 @default.
- W4385804976 hasConceptScore W4385804976C41008148 @default.
- W4385804976 hasLocation W43858049761 @default.
- W4385804976 hasLocation W43858049762 @default.
- W4385804976 hasOpenAccess W4385804976 @default.
- W4385804976 hasPrimaryLocation W43858049761 @default.
- W4385804976 hasRelatedWork W3014300295 @default.
- W4385804976 hasRelatedWork W3164822677 @default.
- W4385804976 hasRelatedWork W4223943233 @default.
- W4385804976 hasRelatedWork W4225161397 @default.
- W4385804976 hasRelatedWork W4250304930 @default.
- W4385804976 hasRelatedWork W4312200629 @default.
- W4385804976 hasRelatedWork W4360585206 @default.
- W4385804976 hasRelatedWork W4364306694 @default.
- W4385804976 hasRelatedWork W4380075502 @default.
- W4385804976 hasRelatedWork W4380086463 @default.
- W4385804976 isParatext "false" @default.
- W4385804976 isRetracted "false" @default.
- W4385804976 workType "article" @default.