FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207875145> ?p ?o ?g. }

• W3207875145 endingPage "1186" @default.
• W3207875145 startingPage "1176" @default.
• W3207875145 abstract "Deep convolutional neural networks (CNN) provide high accuracy for automatic classification of dopamine transporter (DAT) SPECT images. However, CNN are inherently black-box in nature lacking any kind of explanation for their decisions. This limits their acceptance for clinical use. This study tested layer-wise relevance propagation (LRP) to explain CNN-based classification of DAT-SPECT in patients with clinically uncertain parkinsonian syndromes.The study retrospectively included 1296 clinical DAT-SPECT with visual binary interpretation as normal or reduced by two experienced readers as standard-of-truth. A custom-made CNN was trained with 1008 randomly selected DAT-SPECT. The remaining 288 DAT-SPECT were used to assess classification performance of the CNN and to test LRP for explanation of the CNN-based classification.Overall accuracy, sensitivity, and specificity of the CNN were 95.8%, 92.8%, and 98.7%, respectively. LRP provided relevance maps that were easy to interpret in each individual DAT-SPECT. In particular, the putamen in the hemisphere most affected by nigrostriatal degeneration was the most relevant brain region for CNN-based classification in all reduced DAT-SPECT. Some misclassified DAT-SPECT showed an inconsistent relevance map more typical for the true class label.LRP is useful to provide explanation of CNN-based decisions in individual DAT-SPECT and, therefore, can be recommended to support CNN-based classification of DAT-SPECT in clinical routine. Total computation time of 3 s is compatible with busy clinical workflow. The utility of inconsistent relevance maps to identify misclassified cases requires further investigation." @default.
• W3207875145 created "2021-10-25" @default.
• W3207875145 creator A5016411406 @default.
• W3207875145 creator A5017251514 @default.
• W3207875145 creator A5018037502 @default.
• W3207875145 creator A5022668044 @default.
• W3207875145 creator A5034288621 @default.
• W3207875145 creator A5056186864 @default.
• W3207875145 creator A5072841040 @default.
• W3207875145 date "2021-10-15" @default.
• W3207875145 modified "2023-10-09" @default.
• W3207875145 title "Explainable AI to improve acceptance of convolutional neural networks for automatic classification of dopamine transporter SPECT in the diagnosis of clinically uncertain parkinsonian syndromes" @default.
• W3207875145 cites W1787224781 @default.
• W3207875145 cites W1992707674 @default.
• W3207875145 cites W1994016278 @default.
• W3207875145 cites W200060780 @default.
• W3207875145 cites W2007227352 @default.
• W3207875145 cites W2016293149 @default.
• W3207875145 cites W2038223412 @default.
• W3207875145 cites W2045257928 @default.
• W3207875145 cites W2052580603 @default.
• W3207875145 cites W2079985430 @default.
• W3207875145 cites W2088610989 @default.
• W3207875145 cites W2094406550 @default.
• W3207875145 cites W2096574063 @default.
• W3207875145 cites W2195388612 @default.
• W3207875145 cites W2282821441 @default.
• W3207875145 cites W2319585903 @default.
• W3207875145 cites W2528491735 @default.
• W3207875145 cites W2531182291 @default.
• W3207875145 cites W2582331812 @default.
• W3207875145 cites W2592929672 @default.
• W3207875145 cites W2620832945 @default.
• W3207875145 cites W2754039296 @default.
• W3207875145 cites W2769664495 @default.
• W3207875145 cites W2770811760 @default.
• W3207875145 cites W2778473818 @default.
• W3207875145 cites W2883558452 @default.
• W3207875145 cites W2885096695 @default.
• W3207875145 cites W2887749301 @default.
• W3207875145 cites W2901663923 @default.
• W3207875145 cites W2902620820 @default.
• W3207875145 cites W2919115771 @default.
• W3207875145 cites W2920462083 @default.
• W3207875145 cites W2922167346 @default.
• W3207875145 cites W2937876673 @default.
• W3207875145 cites W2943448780 @default.
• W3207875145 cites W2952405831 @default.
• W3207875145 cites W2954129211 @default.
• W3207875145 cites W2954725578 @default.
• W3207875145 cites W2956993163 @default.
• W3207875145 cites W2963773574 @default.
• W3207875145 cites W2971256692 @default.
• W3207875145 cites W2971685841 @default.
• W3207875145 cites W2972441196 @default.
• W3207875145 cites W2973136764 @default.
• W3207875145 cites W2981597422 @default.
• W3207875145 cites W3025713257 @default.
• W3207875145 cites W3081043797 @default.
• W3207875145 cites W3091589898 @default.
• W3207875145 cites W3092273386 @default.
• W3207875145 cites W3109500069 @default.
• W3207875145 cites W3110093938 @default.
• W3207875145 cites W3117098709 @default.
• W3207875145 cites W3118826788 @default.
• W3207875145 cites W3121886582 @default.
• W3207875145 doi "https://doi.org/10.1007/s00259-021-05569-9" @default.
• W3207875145 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34651223" @default.
• W3207875145 hasPublicationYear "2021" @default.
• W3207875145 type Work @default.
• W3207875145 sameAs 3207875145 @default.
• W3207875145 citedByCount "16" @default.
• W3207875145 countsByYear W32078751452022 @default.
• W3207875145 countsByYear W32078751452023 @default.
• W3207875145 crossrefType "journal-article" @default.
• W3207875145 hasAuthorship W3207875145A5016411406 @default.
• W3207875145 hasAuthorship W3207875145A5017251514 @default.
• W3207875145 hasAuthorship W3207875145A5018037502 @default.
• W3207875145 hasAuthorship W3207875145A5022668044 @default.
• W3207875145 hasAuthorship W3207875145A5034288621 @default.
• W3207875145 hasAuthorship W3207875145A5056186864 @default.
• W3207875145 hasAuthorship W3207875145A5072841040 @default.
• W3207875145 hasBestOaLocation W32078751451 @default.
• W3207875145 hasConcept C126322002 @default.
• W3207875145 hasConcept C137183658 @default.
• W3207875145 hasConcept C153180895 @default.
• W3207875145 hasConcept C154945302 @default.
• W3207875145 hasConcept C2776755682 @default.
• W3207875145 hasConcept C2984398910 @default.
• W3207875145 hasConcept C2989005 @default.
• W3207875145 hasConcept C41008148 @default.
• W3207875145 hasConcept C513476851 @default.
• W3207875145 hasConcept C71924100 @default.
• W3207875145 hasConcept C81363708 @default.
• W3207875145 hasConceptScore W3207875145C126322002 @default.
• W3207875145 hasConceptScore W3207875145C137183658 @default.
• W3207875145 hasConceptScore W3207875145C153180895 @default.
• W3207875145 hasConceptScore W3207875145C154945302 @default.

• next