Matches in SemOpenAlex for { <https://semopenalex.org/work/W4363650238> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4363650238 abstract "In this work, we propose MLP-Vnet, a token-based U-shaped multilayer linear perceptron-mixer (MLP-Mixer) network, incorporating a convolutional neural network for multi-structure segmentation on cardiac magnetic resonance imaging (MRI). The proposed MLP-Vnet is composed of an encoder and decoder. Taking an MRI scan as input, the semantic features are extracted by the encoder with one early convolutional block followed by four consecutive MLP-Mixer blocks. Then, the extracted features are passed to the decoder with mirrored architecture of the encoder to form a N-classes segmentation map. We evaluated our proposed network on the Automated Cardiac Diagnosis Challenge (ACDC) dataset. The performance of the network was assessed in terms of the volume- and surface-based similarities between the predicted contours and the manually delineated ground-truth contours, and computational efficiency. The volume-based similarities were measured by the Dice score coefficient (DSC), sensitivity, and precision. The surface-based similarities were measured by Hausdorff distance (HD), mean surface distance (MSD), and residual mean square distance (RMSD). The performance of the MLP-Vnet was compared with four state-of-the-art networks. The proposed network demonstrated statistically superior DSC and superior sensitivity or precision on all the three structures to the competing networks (p-value < 0.05): average DSC of 0.904, sensitivity of 0.908 and precision of 0.902 among all structures. The best surfaceased similarities were also demonstrated by the MLP-Vnet: average HD = 3.266 mm, MSD = 0.684 mm, and RMSD = 1.487 mm. Compared to the competing networks, the MLP-Vnet showed the shortest training time (7.32 hours) inference time per patient (3.12 seconds). The proposed MLP-Vnet is capable of using reasonable number of trainable parameters to solve the segmentation task on the cardiac MRI scans more quickly and accurately than the state-ofthe- art networks. This novel network could be a promising tool for accurate and efficient cardiac MRI segmentation to assist cardiac diagnosis and treatment decision making." @default.
- W4363650238 created "2023-04-11" @default.
- W4363650238 creator A5009731683 @default.
- W4363650238 creator A5029173262 @default.
- W4363650238 creator A5030054597 @default.
- W4363650238 creator A5055677011 @default.
- W4363650238 creator A5062115647 @default.
- W4363650238 creator A5078938291 @default.
- W4363650238 creator A5086751089 @default.
- W4363650238 date "2023-04-10" @default.
- W4363650238 modified "2023-10-01" @default.
- W4363650238 title "Multi-structure segmentation on cardiac MRI using multilayer perceptron mixer network" @default.
- W4363650238 doi "https://doi.org/10.1117/12.2653944" @default.
- W4363650238 hasPublicationYear "2023" @default.
- W4363650238 type Work @default.
- W4363650238 citedByCount "0" @default.
- W4363650238 crossrefType "proceedings-article" @default.
- W4363650238 hasAuthorship W4363650238A5009731683 @default.
- W4363650238 hasAuthorship W4363650238A5029173262 @default.
- W4363650238 hasAuthorship W4363650238A5030054597 @default.
- W4363650238 hasAuthorship W4363650238A5055677011 @default.
- W4363650238 hasAuthorship W4363650238A5062115647 @default.
- W4363650238 hasAuthorship W4363650238A5078938291 @default.
- W4363650238 hasAuthorship W4363650238A5086751089 @default.
- W4363650238 hasConcept C103278499 @default.
- W4363650238 hasConcept C111919701 @default.
- W4363650238 hasConcept C115961682 @default.
- W4363650238 hasConcept C118505674 @default.
- W4363650238 hasConcept C124504099 @default.
- W4363650238 hasConcept C127413603 @default.
- W4363650238 hasConcept C141898687 @default.
- W4363650238 hasConcept C146849305 @default.
- W4363650238 hasConcept C153180895 @default.
- W4363650238 hasConcept C154945302 @default.
- W4363650238 hasConcept C179717631 @default.
- W4363650238 hasConcept C21200559 @default.
- W4363650238 hasConcept C24326235 @default.
- W4363650238 hasConcept C41008148 @default.
- W4363650238 hasConcept C50644808 @default.
- W4363650238 hasConcept C81363708 @default.
- W4363650238 hasConcept C89600930 @default.
- W4363650238 hasConceptScore W4363650238C103278499 @default.
- W4363650238 hasConceptScore W4363650238C111919701 @default.
- W4363650238 hasConceptScore W4363650238C115961682 @default.
- W4363650238 hasConceptScore W4363650238C118505674 @default.
- W4363650238 hasConceptScore W4363650238C124504099 @default.
- W4363650238 hasConceptScore W4363650238C127413603 @default.
- W4363650238 hasConceptScore W4363650238C141898687 @default.
- W4363650238 hasConceptScore W4363650238C146849305 @default.
- W4363650238 hasConceptScore W4363650238C153180895 @default.
- W4363650238 hasConceptScore W4363650238C154945302 @default.
- W4363650238 hasConceptScore W4363650238C179717631 @default.
- W4363650238 hasConceptScore W4363650238C21200559 @default.
- W4363650238 hasConceptScore W4363650238C24326235 @default.
- W4363650238 hasConceptScore W4363650238C41008148 @default.
- W4363650238 hasConceptScore W4363650238C50644808 @default.
- W4363650238 hasConceptScore W4363650238C81363708 @default.
- W4363650238 hasConceptScore W4363650238C89600930 @default.
- W4363650238 hasLocation W43636502381 @default.
- W4363650238 hasOpenAccess W4363650238 @default.
- W4363650238 hasPrimaryLocation W43636502381 @default.
- W4363650238 hasRelatedWork W158826679 @default.
- W4363650238 hasRelatedWork W2130151498 @default.
- W4363650238 hasRelatedWork W2769435486 @default.
- W4363650238 hasRelatedWork W2897195263 @default.
- W4363650238 hasRelatedWork W2914010220 @default.
- W4363650238 hasRelatedWork W2973133528 @default.
- W4363650238 hasRelatedWork W2979303128 @default.
- W4363650238 hasRelatedWork W3027204089 @default.
- W4363650238 hasRelatedWork W3193301557 @default.
- W4363650238 hasRelatedWork W3207810281 @default.
- W4363650238 isParatext "false" @default.
- W4363650238 isRetracted "false" @default.
- W4363650238 workType "article" @default.