Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385973495> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4385973495 endingPage "100084" @default.
- W4385973495 startingPage "100084" @default.
- W4385973495 abstract "The purpose of this study is to develop an accurate deep learning model capable of Inferior Vena Cava (IVC) filter segmentation from CT scans. The study does a comparative assessment of the impact of Residual Networks (ResNets) complemented with reduced convolutional layer depth and also analyzes the impact of using vision transformer architectures without performance degradation. This experimental retrospective study on 84 CT scans consisting of 54618 slices involves design, implementation, and evaluation of segmentation algorithm which can be used to generate a clinical report for the presence of IVC filters on abdominal CT scans performed for any reason. Several variants of patch-based 3D-Convolutional Neural Network (CNN) and the Swin UNet Transformer (Swin-UNETR) is used to retrieve the signature of IVC filters. The Dice Score is used as a metric to compare the performance of the segmentation models. Model trained on UNet variant using four ResNet layers showed a higher segmentation performance achieving median Dice = 0.92 [Interquartile range(IQR): 0.85, 0.93] compared to the plain UNet model with four layers having median Dice = 0.89 [IQR: 0.83, 0.92]. Segmentation results from ResNet with two layers achieved a median Dice = 0.93 [IQR: 0.87, 0.94] which was higher than the plain UNet model with two layers at median Dice = 0.87 [IQR: 0.77, 0.90]. Models trained using SWIN-based transformers performed significantly better in both training and validation datasets compared to the four CNN variants. The validation median Dice was highest in 4 layer Swin UNETR at 0.88 followed by 2 layer Swin UNETR at 0.85. Utilization of vision based transformer Swin-UNETR results in segmentation output with both low bias and variance thereby solving a real-world problem within healthcare for advanced Artificial Intelligence (AI) image processing and recognition. The Swin UNETR will reduce the time spent manually tracking IVC filters by centralizing within the electronic health record. Link to GitHub repository." @default.
- W4385973495 created "2023-08-19" @default.
- W4385973495 creator A5008171401 @default.
- W4385973495 creator A5009439842 @default.
- W4385973495 creator A5034845580 @default.
- W4385973495 creator A5079803395 @default.
- W4385973495 creator A5080811856 @default.
- W4385973495 date "2023-12-01" @default.
- W4385973495 modified "2023-10-14" @default.
- W4385973495 title "Analysis of Swin-UNet vision transformer for Inferior Vena Cava filter segmentation from CT scans" @default.
- W4385973495 cites W1994229246 @default.
- W4385973495 cites W2015159529 @default.
- W4385973495 cites W2024896860 @default.
- W4385973495 cites W2034913543 @default.
- W4385973495 cites W2097964911 @default.
- W4385973495 cites W2103549027 @default.
- W4385973495 cites W2144631830 @default.
- W4385973495 cites W2170578249 @default.
- W4385973495 cites W2551320863 @default.
- W4385973495 cites W2885667037 @default.
- W4385973495 cites W2902054227 @default.
- W4385973495 cites W2974091645 @default.
- W4385973495 cites W3033040748 @default.
- W4385973495 cites W3096947210 @default.
- W4385973495 cites W4206706211 @default.
- W4385973495 cites W4289109734 @default.
- W4385973495 cites W4306149630 @default.
- W4385973495 cites W4360853472 @default.
- W4385973495 doi "https://doi.org/10.1016/j.ailsci.2023.100084" @default.
- W4385973495 hasPublicationYear "2023" @default.
- W4385973495 type Work @default.
- W4385973495 citedByCount "0" @default.
- W4385973495 crossrefType "journal-article" @default.
- W4385973495 hasAuthorship W4385973495A5008171401 @default.
- W4385973495 hasAuthorship W4385973495A5009439842 @default.
- W4385973495 hasAuthorship W4385973495A5034845580 @default.
- W4385973495 hasAuthorship W4385973495A5079803395 @default.
- W4385973495 hasAuthorship W4385973495A5080811856 @default.
- W4385973495 hasBestOaLocation W43859734951 @default.
- W4385973495 hasConcept C105795698 @default.
- W4385973495 hasConcept C108583219 @default.
- W4385973495 hasConcept C11413529 @default.
- W4385973495 hasConcept C119060515 @default.
- W4385973495 hasConcept C126838900 @default.
- W4385973495 hasConcept C141071460 @default.
- W4385973495 hasConcept C153180895 @default.
- W4385973495 hasConcept C154945302 @default.
- W4385973495 hasConcept C155512373 @default.
- W4385973495 hasConcept C22029948 @default.
- W4385973495 hasConcept C2910216633 @default.
- W4385973495 hasConcept C2989005 @default.
- W4385973495 hasConcept C33923547 @default.
- W4385973495 hasConcept C41008148 @default.
- W4385973495 hasConcept C71924100 @default.
- W4385973495 hasConcept C81363708 @default.
- W4385973495 hasConcept C89600930 @default.
- W4385973495 hasConceptScore W4385973495C105795698 @default.
- W4385973495 hasConceptScore W4385973495C108583219 @default.
- W4385973495 hasConceptScore W4385973495C11413529 @default.
- W4385973495 hasConceptScore W4385973495C119060515 @default.
- W4385973495 hasConceptScore W4385973495C126838900 @default.
- W4385973495 hasConceptScore W4385973495C141071460 @default.
- W4385973495 hasConceptScore W4385973495C153180895 @default.
- W4385973495 hasConceptScore W4385973495C154945302 @default.
- W4385973495 hasConceptScore W4385973495C155512373 @default.
- W4385973495 hasConceptScore W4385973495C22029948 @default.
- W4385973495 hasConceptScore W4385973495C2910216633 @default.
- W4385973495 hasConceptScore W4385973495C2989005 @default.
- W4385973495 hasConceptScore W4385973495C33923547 @default.
- W4385973495 hasConceptScore W4385973495C41008148 @default.
- W4385973495 hasConceptScore W4385973495C71924100 @default.
- W4385973495 hasConceptScore W4385973495C81363708 @default.
- W4385973495 hasConceptScore W4385973495C89600930 @default.
- W4385973495 hasLocation W43859734951 @default.
- W4385973495 hasOpenAccess W4385973495 @default.
- W4385973495 hasPrimaryLocation W43859734951 @default.
- W4385973495 hasRelatedWork W2009559548 @default.
- W4385973495 hasRelatedWork W2016385589 @default.
- W4385973495 hasRelatedWork W2385445039 @default.
- W4385973495 hasRelatedWork W2390936256 @default.
- W4385973495 hasRelatedWork W2475857072 @default.
- W4385973495 hasRelatedWork W2483429559 @default.
- W4385973495 hasRelatedWork W2906397153 @default.
- W4385973495 hasRelatedWork W3021239166 @default.
- W4385973495 hasRelatedWork W3104750253 @default.
- W4385973495 hasRelatedWork W4366341510 @default.
- W4385973495 hasVolume "4" @default.
- W4385973495 isParatext "false" @default.
- W4385973495 isRetracted "false" @default.
- W4385973495 workType "article" @default.