FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380480143> ?p ?o ?g. }

• W4380480143 abstract "Invasive coronary angiography (ICA) is a primary imaging modality that visualizes the lumen area of coronary arteries for diagnosis and interventional guidance. In the current practice of quantitative coronary analysis (QCA), semi-automatic segmentation tools require labor-intensive and time-consuming manual correction, limiting their application in the catheterization room.This study aims to propose rank-based selective ensemble methods that improve the segmentation performance and reduce morphological errors that limit fully automated quantification of coronary artery using deep-learning segmentation of ICA.Two selective ensemble methods proposed in this work integrated the weighted ensemble approach with per-image quality estimation. The segmentation outcomes from five base models with different loss functions were ranked either by mask morphology or estimated dice similarity coefficient (DSC). The final output was determined by imposing different weights according to the ranks. The ranking criteria based on mask morphology were formulated from empirical insight to avoid frequent types of segmentation errors (MSEN), while the estimation of DSCs was performed by comparing the pseudo-ground truth generated from a meta-learner (ESEN). Five-fold cross-validation was performed with the internal dataset of 7426 coronary angiograms from 2924 patients, and prediction model was externally validated with 556 images of 226 patients.The selective ensemble methods improved the segmentation performance with DSCs up to 93.07% and provided a better delineation of coronary lesion with local DSCs of up to 93.93%, outperforming all individual models. Proposed methods also minimized the chances of mask disconnection in the most narrowed regions to 2.10%. The robustness of the proposed methods was also evident in the external validation. Inference time for major vessel segmentation was approximately one-sixth of a second.Proposed methods successfully reduced morphological errors in the predicted masks and were able to enhance the robustness of the automatic segmentation. The results suggest better applicability of real-time QCA-based diagnostic methods in routine clinical settings." @default.
• W4380480143 created "2023-06-14" @default.
• W4380480143 creator A5001255691 @default.
• W4380480143 creator A5012996842 @default.
• W4380480143 creator A5014395983 @default.
• W4380480143 creator A5030663708 @default.
• W4380480143 creator A5030664619 @default.
• W4380480143 creator A5033342453 @default.
• W4380480143 creator A5037973689 @default.
• W4380480143 creator A5041347320 @default.
• W4380480143 creator A5042358560 @default.
• W4380480143 creator A5048764382 @default.
• W4380480143 creator A5049190496 @default.
• W4380480143 creator A5057858888 @default.
• W4380480143 creator A5065417122 @default.
• W4380480143 creator A5072895439 @default.
• W4380480143 creator A5074521617 @default.
• W4380480143 creator A5080229165 @default.
• W4380480143 date "2023-06-13" @default.
• W4380480143 modified "2023-10-18" @default.
• W4380480143 title "Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography" @default.
• W4380480143 cites W123601357 @default.
• W4380480143 cites W1534477342 @default.
• W4380480143 cites W1901129140 @default.
• W4380480143 cites W2019124656 @default.
• W4380480143 cites W2048733914 @default.
• W4380480143 cites W2088516723 @default.
• W4380480143 cites W2100128988 @default.
• W4380480143 cites W2147123922 @default.
• W4380480143 cites W2155255287 @default.
• W4380480143 cites W2156920951 @default.
• W4380480143 cites W2162140684 @default.
• W4380480143 cites W2167055186 @default.
• W4380480143 cites W2187771232 @default.
• W4380480143 cites W2551431664 @default.
• W4380480143 cites W2599354622 @default.
• W4380480143 cites W2605396475 @default.
• W4380480143 cites W2752573065 @default.
• W4380480143 cites W2759338223 @default.
• W4380480143 cites W2762517245 @default.
• W4380480143 cites W2895996421 @default.
• W4380480143 cites W2913386487 @default.
• W4380480143 cites W2913732334 @default.
• W4380480143 cites W2917989249 @default.
• W4380480143 cites W2923430339 @default.
• W4380480143 cites W2941582932 @default.
• W4380480143 cites W2947077408 @default.
• W4380480143 cites W2953977469 @default.
• W4380480143 cites W2962731543 @default.
• W4380480143 cites W2963446712 @default.
• W4380480143 cites W2963959402 @default.
• W4380480143 cites W2966434031 @default.
• W4380480143 cites W2970357772 @default.
• W4380480143 cites W2979598282 @default.
• W4380480143 cites W2988846102 @default.
• W4380480143 cites W2990887757 @default.
• W4380480143 cites W3010704162 @default.
• W4380480143 cites W3012126194 @default.
• W4380480143 cites W3024690634 @default.
• W4380480143 cites W3028341911 @default.
• W4380480143 cites W3034777994 @default.
• W4380480143 cites W3043701234 @default.
• W4380480143 cites W3079188960 @default.
• W4380480143 cites W3082577495 @default.
• W4380480143 cites W3088993362 @default.
• W4380480143 cites W3094021879 @default.
• W4380480143 cites W3096903564 @default.
• W4380480143 cites W3107399755 @default.
• W4380480143 cites W3138480930 @default.
• W4380480143 cites W3149839747 @default.
• W4380480143 cites W3158013249 @default.
• W4380480143 cites W3159747129 @default.
• W4380480143 cites W3162412448 @default.
• W4380480143 cites W3163580316 @default.
• W4380480143 cites W3166555319 @default.
• W4380480143 cites W3174708193 @default.
• W4380480143 cites W3177119609 @default.
• W4380480143 cites W3185820546 @default.
• W4380480143 cites W3186953906 @default.
• W4380480143 cites W3200595552 @default.
• W4380480143 doi "https://doi.org/10.1002/mp.16554" @default.
• W4380480143 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37310802" @default.
• W4380480143 hasPublicationYear "2023" @default.
• W4380480143 type Work @default.
• W4380480143 citedByCount "0" @default.
• W4380480143 crossrefType "journal-article" @default.
• W4380480143 hasAuthorship W4380480143A5001255691 @default.
• W4380480143 hasAuthorship W4380480143A5012996842 @default.
• W4380480143 hasAuthorship W4380480143A5014395983 @default.
• W4380480143 hasAuthorship W4380480143A5030663708 @default.
• W4380480143 hasAuthorship W4380480143A5030664619 @default.
• W4380480143 hasAuthorship W4380480143A5033342453 @default.
• W4380480143 hasAuthorship W4380480143A5037973689 @default.
• W4380480143 hasAuthorship W4380480143A5041347320 @default.
• W4380480143 hasAuthorship W4380480143A5042358560 @default.
• W4380480143 hasAuthorship W4380480143A5048764382 @default.
• W4380480143 hasAuthorship W4380480143A5049190496 @default.
• W4380480143 hasAuthorship W4380480143A5057858888 @default.
• W4380480143 hasAuthorship W4380480143A5065417122 @default.
• W4380480143 hasAuthorship W4380480143A5072895439 @default.

• next