Matches in SemOpenAlex for { <https://semopenalex.org/work/W3127804597> ?p ?o ?g. }
- W3127804597 abstract "Abstract Machine learning has greatly facilitated the analysis of medical data, while the internal operations usually remain intransparent. To better comprehend these opaque procedures, a convolutional neural network for optical coherence tomography image segmentation was enhanced with a Traceable Relevance Explainability (T-REX) technique. The proposed application was based on three components: ground truth generation by multiple graders, calculation of Hamming distances among graders and the machine learning algorithm, as well as a smart data visualization (‘neural recording’). An overall average variability of 1.75% between the human graders and the algorithm was found, slightly minor to 2.02% among human graders. The ambiguity in ground truth had noteworthy impact on machine learning results, which could be visualized. The convolutional neural network balanced between graders and allowed for modifiable predictions dependent on the compartment. Using the proposed T-REX setup, machine learning processes could be rendered more transparent and understandable, possibly leading to optimized applications." @default.
- W3127804597 created "2021-02-15" @default.
- W3127804597 creator A5004084769 @default.
- W3127804597 creator A5015881286 @default.
- W3127804597 creator A5016588157 @default.
- W3127804597 creator A5029283104 @default.
- W3127804597 creator A5043739803 @default.
- W3127804597 creator A5059328359 @default.
- W3127804597 creator A5068290836 @default.
- W3127804597 creator A5070786820 @default.
- W3127804597 creator A5072951845 @default.
- W3127804597 creator A5073823745 @default.
- W3127804597 creator A5081163806 @default.
- W3127804597 creator A5082600485 @default.
- W3127804597 creator A5091171261 @default.
- W3127804597 creator A5091498803 @default.
- W3127804597 date "2021-02-05" @default.
- W3127804597 modified "2023-10-18" @default.
- W3127804597 title "Unraveling the deep learning gearbox in optical coherence tomography image segmentation towards explainable artificial intelligence" @default.
- W3127804597 cites W1787224781 @default.
- W3127804597 cites W1901129140 @default.
- W3127804597 cites W1968110820 @default.
- W3127804597 cites W1976041506 @default.
- W3127804597 cites W1980259053 @default.
- W3127804597 cites W1982672043 @default.
- W3127804597 cites W1998392635 @default.
- W3127804597 cites W2006217757 @default.
- W3127804597 cites W2048182953 @default.
- W3127804597 cites W2076063813 @default.
- W3127804597 cites W2083780116 @default.
- W3127804597 cites W2120017555 @default.
- W3127804597 cites W2120393396 @default.
- W3127804597 cites W2134161293 @default.
- W3127804597 cites W2195388612 @default.
- W3127804597 cites W2254050631 @default.
- W3127804597 cites W2257979135 @default.
- W3127804597 cites W2282821441 @default.
- W3127804597 cites W2410891012 @default.
- W3127804597 cites W2418802570 @default.
- W3127804597 cites W2528491735 @default.
- W3127804597 cites W2557738935 @default.
- W3127804597 cites W2558050786 @default.
- W3127804597 cites W2582336686 @default.
- W3127804597 cites W2589074029 @default.
- W3127804597 cites W2589435368 @default.
- W3127804597 cites W2592399093 @default.
- W3127804597 cites W2592929672 @default.
- W3127804597 cites W2612758615 @default.
- W3127804597 cites W2620887047 @default.
- W3127804597 cites W2657631929 @default.
- W3127804597 cites W2743353487 @default.
- W3127804597 cites W2766447205 @default.
- W3127804597 cites W2772059204 @default.
- W3127804597 cites W2782908833 @default.
- W3127804597 cites W2784339534 @default.
- W3127804597 cites W2793079232 @default.
- W3127804597 cites W2886281300 @default.
- W3127804597 cites W2887693514 @default.
- W3127804597 cites W2888056875 @default.
- W3127804597 cites W2890068671 @default.
- W3127804597 cites W2896202491 @default.
- W3127804597 cites W2897690051 @default.
- W3127804597 cites W2898192966 @default.
- W3127804597 cites W2908201961 @default.
- W3127804597 cites W2919115771 @default.
- W3127804597 cites W2921060574 @default.
- W3127804597 cites W2927351257 @default.
- W3127804597 cites W2937186836 @default.
- W3127804597 cites W2948282852 @default.
- W3127804597 cites W2952362839 @default.
- W3127804597 cites W2962772482 @default.
- W3127804597 cites W2964996949 @default.
- W3127804597 cites W2966710025 @default.
- W3127804597 cites W2967173855 @default.
- W3127804597 cites W2969181508 @default.
- W3127804597 cites W2969343193 @default.
- W3127804597 cites W2972246881 @default.
- W3127804597 cites W2973920946 @default.
- W3127804597 cites W2974231756 @default.
- W3127804597 cites W2974726644 @default.
- W3127804597 cites W2975512858 @default.
- W3127804597 cites W2976398475 @default.
- W3127804597 cites W2978022936 @default.
- W3127804597 cites W2981731882 @default.
- W3127804597 cites W2986257978 @default.
- W3127804597 cites W2997681568 @default.
- W3127804597 cites W3000965188 @default.
- W3127804597 cites W3037158619 @default.
- W3127804597 cites W3037975076 @default.
- W3127804597 cites W3045945451 @default.
- W3127804597 cites W3048123412 @default.
- W3127804597 cites W3099661382 @default.
- W3127804597 cites W3102564565 @default.
- W3127804597 cites W3138819813 @default.
- W3127804597 cites W3202966610 @default.
- W3127804597 cites W4205380271 @default.
- W3127804597 cites W4236805817 @default.
- W3127804597 cites W4251212826 @default.
- W3127804597 doi "https://doi.org/10.1038/s42003-021-01697-y" @default.
- W3127804597 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7864998" @default.