FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4233328035> ?p ?o ?g. }

• W4233328035 endingPage "3150" @default.
• W4233328035 startingPage "3138" @default.
• W4233328035 abstract "Ultrasonography-an imaging technique that can show the anatomical section of nerves and surrounding tissues-is one of the most effective imaging methods to diagnose nerve diseases. However, segmenting the median nerve in two-dimensional (2D) ultrasound images is challenging due to the tiny and inconspicuous size of the nerve, the low contrast of images, and imaging noise. This study aimed to apply deep learning approaches to improve the accuracy of automatic segmentation of the median nerve in ultrasound images.In this study, we proposed an improved network called VGG16-UNet, which incorporates a contracting path and an expanding path. The contracting path is the VGG16 model with the 3 fully connected layers removed. The architecture of the expanding path resembles the upsampling path of U-Net. Moreover, attention mechanisms or/and residual modules were added to the U-Net and VGG16-UNet, which sequentially obtained Attention-UNet (A-UNet), Summation-UNet (S-UNet), Attention-Summation-UNet (AS-UNet), Attention-VGG16-UNet (A-VGG16-UNet), Summation-VGG16-UNet (S-VGG16-UNet), and Attention-Summation-VGG16-UNet (AS-VGG16-UNet). Each model was trained on the dataset of 910 median nerve images from 19 participants and tested on 207 frames from a new image sequence. The performance of the models was evaluated by metrics including Dice similarity coefficient (Dice), Jaccard similarity coefficient (Jaccard), Precision, and Recall. Based on the best segmentation results, we reconstructed a 3D median nerve image using the volume rendering method in the Visualization Toolkit (VTK) to assist in clinical nerve diagnosis.The results of paired t-tests showed significant differences (P<0.01) in the metrics' values of different models. It showed that AS-UNet ranked first in U-Net models. The VGG16-UNet and its variants performed better than the corresponding U-Net models. Furthermore, the model's performance with the attention mechanism was superior to that with the residual module either based on U-Net or VGG16-UNet. The A-VGG16-UNet achieved the best performance (Dice =0.904±0.035, Jaccard =0.826±0.057, Precision =0.905±0.061, and Recall =0.909±0.061). Finally, we applied the trained A-VGG16-UNet to segment the median nerve in the image sequence, then reconstructed and visualized the 3D image of the median nerve.This study demonstrates that the attention mechanism and residual module improve deep learning models for segmenting ultrasound images. The proposed VGG16-UNet-based models performed better than U-Net-based models. With segmentation, a 3D median nerve image can be reconstructed and can provide a visual reference for nerve diagnosis." @default.
• W4233328035 created "2022-05-12" @default.
• W4233328035 creator A5021024679 @default.
• W4233328035 creator A5027020513 @default.
• W4233328035 creator A5029376980 @default.
• W4233328035 creator A5072315367 @default.
• W4233328035 date "2022-06-01" @default.
• W4233328035 modified "2023-10-10" @default.
• W4233328035 title "Attention-VGG16-UNet: a novel deep learning approach for automatic segmentation of the median nerve in ultrasound images" @default.
• W4233328035 cites W1897214101 @default.
• W4233328035 cites W1973608488 @default.
• W4233328035 cites W2072707527 @default.
• W4233328035 cites W2415113500 @default.
• W4233328035 cites W2527910800 @default.
• W4233328035 cites W2799457612 @default.
• W4233328035 cites W2888358068 @default.
• W4233328035 cites W2888915272 @default.
• W4233328035 cites W2901441108 @default.
• W4233328035 cites W2928133111 @default.
• W4233328035 cites W2968342525 @default.
• W4233328035 cites W2996290406 @default.
• W4233328035 cites W2999014040 @default.
• W4233328035 cites W3004966381 @default.
• W4233328035 cites W3012158104 @default.
• W4233328035 cites W3034396853 @default.
• W4233328035 cites W3116332149 @default.
• W4233328035 cites W3158043644 @default.
• W4233328035 cites W3164781147 @default.
• W4233328035 cites W3183511035 @default.
• W4233328035 cites W3207523440 @default.
• W4233328035 doi "https://doi.org/10.21037/qims-21-1074" @default.
• W4233328035 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35655843" @default.
• W4233328035 hasPublicationYear "2022" @default.
• W4233328035 type Work @default.
• W4233328035 citedByCount "5" @default.
• W4233328035 countsByYear W42333280352023 @default.
• W4233328035 crossrefType "journal-article" @default.
• W4233328035 hasAuthorship W4233328035A5021024679 @default.
• W4233328035 hasAuthorship W4233328035A5027020513 @default.
• W4233328035 hasAuthorship W4233328035A5029376980 @default.
• W4233328035 hasAuthorship W4233328035A5072315367 @default.
• W4233328035 hasBestOaLocation W42333280351 @default.
• W4233328035 hasConcept C124504099 @default.
• W4233328035 hasConcept C126838900 @default.
• W4233328035 hasConcept C143753070 @default.
• W4233328035 hasConcept C153180895 @default.
• W4233328035 hasConcept C154945302 @default.
• W4233328035 hasConcept C163892561 @default.
• W4233328035 hasConcept C203519979 @default.
• W4233328035 hasConcept C41008148 @default.
• W4233328035 hasConcept C71924100 @default.
• W4233328035 hasConcept C89600930 @default.
• W4233328035 hasConceptScore W4233328035C124504099 @default.
• W4233328035 hasConceptScore W4233328035C126838900 @default.
• W4233328035 hasConceptScore W4233328035C143753070 @default.
• W4233328035 hasConceptScore W4233328035C153180895 @default.
• W4233328035 hasConceptScore W4233328035C154945302 @default.
• W4233328035 hasConceptScore W4233328035C163892561 @default.
• W4233328035 hasConceptScore W4233328035C203519979 @default.
• W4233328035 hasConceptScore W4233328035C41008148 @default.
• W4233328035 hasConceptScore W4233328035C71924100 @default.
• W4233328035 hasConceptScore W4233328035C89600930 @default.
• W4233328035 hasIssue "6" @default.
• W4233328035 hasLocation W42333280351 @default.
• W4233328035 hasLocation W42333280352 @default.
• W4233328035 hasLocation W42333280353 @default.
• W4233328035 hasOpenAccess W4233328035 @default.
• W4233328035 hasPrimaryLocation W42333280351 @default.
• W4233328035 hasRelatedWork W2441762250 @default.
• W4233328035 hasRelatedWork W2936519215 @default.
• W4233328035 hasRelatedWork W3093926553 @default.
• W4233328035 hasRelatedWork W3116883888 @default.
• W4233328035 hasRelatedWork W3120092106 @default.
• W4233328035 hasRelatedWork W4287631720 @default.
• W4233328035 hasRelatedWork W4288366250 @default.
• W4233328035 hasRelatedWork W4308701475 @default.
• W4233328035 hasRelatedWork W4315491877 @default.
• W4233328035 hasRelatedWork W4317748866 @default.
• W4233328035 hasVolume "12" @default.
• W4233328035 isParatext "false" @default.
• W4233328035 isRetracted "false" @default.
• W4233328035 workType "article" @default.