Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293861757> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4293861757 abstract "Intravascular ultrasound (IVUS) imaging allows direct visualization of the coronary vessel wall and is suitable for the assessment of atherosclerosis and the degree of stenosis. Accurate segmentation and measurements of lumen and median-adventitia (MA) from IVUS are essential for such a successful clinical evaluation. However, current segmentation relies on manual operations, which is time-consuming and user-dependent. In this paper, we aim to develop a deep learning-based method using an encoder-decoder deep architecture to automatically extract both lumen and MA border. Our method named IVUS-U-Net++ is an extension of the well-known U-Net++ model. More specifically, a feature pyramid network was added to the U-Net++ model, enabling the utilization of feature maps at different scales. As a result, the accuracy of the probability map and subsequent segmentation have been improved We collected 1746 IVUS images from 18 patients in this study. The whole dataset was split into a training dataset (1572 images) for the 10-fold cross-validation and a test dataset (174 images) for evaluating the performance of models. Our IVUS-U-Net++ segmentation model achieved a Jaccard measure (JM) of 0.9412, a Hausdorff distance (HD) of 0.0639 mm for the lumen border, and a JM of 0.9509, an HD of 0.0867 mm for the MA border, respectively. Moreover, the Pearson correlation and Bland-Altman analyses were performed to evaluate the correlations of 12 clinical parameters measured from our segmentation results and the ground truth, and automatic measurements agreed well with those from the ground truth (all Ps<0.01). In conclusion, our preliminary results demonstrate that the proposed IVUS-U-Net++ model has great promise for clinical use." @default.
- W4293861757 created "2022-09-01" @default.
- W4293861757 creator A5011937138 @default.
- W4293861757 creator A5014638202 @default.
- W4293861757 creator A5017263150 @default.
- W4293861757 creator A5021555728 @default.
- W4293861757 creator A5059338233 @default.
- W4293861757 creator A5071278984 @default.
- W4293861757 creator A5075356494 @default.
- W4293861757 creator A5091114655 @default.
- W4293861757 date "2021-02-20" @default.
- W4293861757 modified "2023-09-27" @default.
- W4293861757 title "A Deep Learning-based Method to Extract Lumen and Media-Adventitia in Intravascular Ultrasound Images" @default.
- W4293861757 doi "https://doi.org/10.48550/arxiv.2102.10480" @default.
- W4293861757 hasPublicationYear "2021" @default.
- W4293861757 type Work @default.
- W4293861757 citedByCount "0" @default.
- W4293861757 crossrefType "posted-content" @default.
- W4293861757 hasAuthorship W4293861757A5011937138 @default.
- W4293861757 hasAuthorship W4293861757A5014638202 @default.
- W4293861757 hasAuthorship W4293861757A5017263150 @default.
- W4293861757 hasAuthorship W4293861757A5021555728 @default.
- W4293861757 hasAuthorship W4293861757A5059338233 @default.
- W4293861757 hasAuthorship W4293861757A5071278984 @default.
- W4293861757 hasAuthorship W4293861757A5075356494 @default.
- W4293861757 hasAuthorship W4293861757A5091114655 @default.
- W4293861757 hasBestOaLocation W42938617571 @default.
- W4293861757 hasConcept C108583219 @default.
- W4293861757 hasConcept C126838900 @default.
- W4293861757 hasConcept C131631996 @default.
- W4293861757 hasConcept C138885662 @default.
- W4293861757 hasConcept C141071460 @default.
- W4293861757 hasConcept C141898687 @default.
- W4293861757 hasConcept C142575187 @default.
- W4293861757 hasConcept C146849305 @default.
- W4293861757 hasConcept C153180895 @default.
- W4293861757 hasConcept C154945302 @default.
- W4293861757 hasConcept C203519979 @default.
- W4293861757 hasConcept C2524010 @default.
- W4293861757 hasConcept C2776401178 @default.
- W4293861757 hasConcept C2776931568 @default.
- W4293861757 hasConcept C31972630 @default.
- W4293861757 hasConcept C33923547 @default.
- W4293861757 hasConcept C41008148 @default.
- W4293861757 hasConcept C41895202 @default.
- W4293861757 hasConcept C71924100 @default.
- W4293861757 hasConcept C89600930 @default.
- W4293861757 hasConceptScore W4293861757C108583219 @default.
- W4293861757 hasConceptScore W4293861757C126838900 @default.
- W4293861757 hasConceptScore W4293861757C131631996 @default.
- W4293861757 hasConceptScore W4293861757C138885662 @default.
- W4293861757 hasConceptScore W4293861757C141071460 @default.
- W4293861757 hasConceptScore W4293861757C141898687 @default.
- W4293861757 hasConceptScore W4293861757C142575187 @default.
- W4293861757 hasConceptScore W4293861757C146849305 @default.
- W4293861757 hasConceptScore W4293861757C153180895 @default.
- W4293861757 hasConceptScore W4293861757C154945302 @default.
- W4293861757 hasConceptScore W4293861757C203519979 @default.
- W4293861757 hasConceptScore W4293861757C2524010 @default.
- W4293861757 hasConceptScore W4293861757C2776401178 @default.
- W4293861757 hasConceptScore W4293861757C2776931568 @default.
- W4293861757 hasConceptScore W4293861757C31972630 @default.
- W4293861757 hasConceptScore W4293861757C33923547 @default.
- W4293861757 hasConceptScore W4293861757C41008148 @default.
- W4293861757 hasConceptScore W4293861757C41895202 @default.
- W4293861757 hasConceptScore W4293861757C71924100 @default.
- W4293861757 hasConceptScore W4293861757C89600930 @default.
- W4293861757 hasLocation W42938617571 @default.
- W4293861757 hasOpenAccess W4293861757 @default.
- W4293861757 hasPrimaryLocation W42938617571 @default.
- W4293861757 hasRelatedWork W144883078 @default.
- W4293861757 hasRelatedWork W174452041 @default.
- W4293861757 hasRelatedWork W2624210927 @default.
- W4293861757 hasRelatedWork W2914416139 @default.
- W4293861757 hasRelatedWork W3010980797 @default.
- W4293861757 hasRelatedWork W3022807913 @default.
- W4293861757 hasRelatedWork W3130862144 @default.
- W4293861757 hasRelatedWork W4284693175 @default.
- W4293861757 hasRelatedWork W4293861757 @default.
- W4293861757 hasRelatedWork W4313566628 @default.
- W4293861757 isParatext "false" @default.
- W4293861757 isRetracted "false" @default.
- W4293861757 workType "article" @default.