FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890356255> ?p ?o ?g. }

• W2890356255 endingPage "423" @default.
• W2890356255 startingPage "412" @default.
• W2890356255 abstract "Rationale and Objectives We propose an automated segmentation pipeline based on deep learning for proton lung MRI segmentation and ventilation-based quantification which improves on our previously reported methodologies in terms of computational efficiency while demonstrating accuracy and robustness. The large data requirement for the proposed framework is made possible by a novel template-based data augmentation strategy. Supporting this work is the open-source ANTsRNet—a growing repository of well-known deep learning architectures first introduced here. Materials and Methods Deep convolutional neural network (CNN) models were constructed and trained using a custom multilabel Dice metric loss function and a novel template-based data augmentation strategy. Training (including template generation and data augmentation) employed 205 proton MR images and 73 functional lung MRI. Evaluation was performed using data sets of size 63 and 40 images, respectively. Results Accuracy for CNN-based proton lung MRI segmentation (in terms of Dice overlap) was left lung: 0.93 ± 0.03, right lung: 0.94 ± 0.02, and whole lung: 0.94 ± 0.02. Although slightly less accurate than our previously reported joint label fusion approach (left lung: 0.95 ± 0.02, right lung: 0.96 ± 0.01, and whole lung: 0.96 ± 0.01), processing time is <1 second per subject for the proposed approach versus ∼30 minutes per subject using joint label fusion. Accuracy for quantifying ventilation defects was determined based on a consensus labeling where average accuracy (Dice multilabel overlap of ventilation defect regions plus normal region) was 0.94 for the CNN method; 0.92 for our previously reported method; and 0.90, 0.92, and 0.94 for expert readers. Conclusion The proposed framework yields accurate automated quantification in near real time. CNNs drastically reduce processing time after offline model construction and demonstrate significant future potential for facilitating quantitative analysis of functional lung MRI. We propose an automated segmentation pipeline based on deep learning for proton lung MRI segmentation and ventilation-based quantification which improves on our previously reported methodologies in terms of computational efficiency while demonstrating accuracy and robustness. The large data requirement for the proposed framework is made possible by a novel template-based data augmentation strategy. Supporting this work is the open-source ANTsRNet—a growing repository of well-known deep learning architectures first introduced here. Deep convolutional neural network (CNN) models were constructed and trained using a custom multilabel Dice metric loss function and a novel template-based data augmentation strategy. Training (including template generation and data augmentation) employed 205 proton MR images and 73 functional lung MRI. Evaluation was performed using data sets of size 63 and 40 images, respectively. Accuracy for CNN-based proton lung MRI segmentation (in terms of Dice overlap) was left lung: 0.93 ± 0.03, right lung: 0.94 ± 0.02, and whole lung: 0.94 ± 0.02. Although slightly less accurate than our previously reported joint label fusion approach (left lung: 0.95 ± 0.02, right lung: 0.96 ± 0.01, and whole lung: 0.96 ± 0.01), processing time is <1 second per subject for the proposed approach versus ∼30 minutes per subject using joint label fusion. Accuracy for quantifying ventilation defects was determined based on a consensus labeling where average accuracy (Dice multilabel overlap of ventilation defect regions plus normal region) was 0.94 for the CNN method; 0.92 for our previously reported method; and 0.90, 0.92, and 0.94 for expert readers. The proposed framework yields accurate automated quantification in near real time. CNNs drastically reduce processing time after offline model construction and demonstrate significant future potential for facilitating quantitative analysis of functional lung MRI." @default.
• W2890356255 created "2018-09-27" @default.
• W2890356255 creator A5005451810 @default.
• W2890356255 creator A5008424493 @default.
• W2890356255 creator A5015008578 @default.
• W2890356255 creator A5016551394 @default.
• W2890356255 creator A5017234848 @default.
• W2890356255 creator A5019251773 @default.
• W2890356255 creator A5026508249 @default.
• W2890356255 creator A5046912865 @default.
• W2890356255 creator A5056393696 @default.
• W2890356255 creator A5073296164 @default.
• W2890356255 creator A5083316571 @default.
• W2890356255 date "2019-03-01" @default.
• W2890356255 modified "2023-10-14" @default.
• W2890356255 title "Convolutional Neural Networks with Template-Based Data Augmentation for Functional Lung Image Quantification" @default.
• W2890356255 cites W1751414848 @default.
• W2890356255 cites W1885185971 @default.
• W2890356255 cites W1890180745 @default.
• W2890356255 cites W1899329334 @default.
• W2890356255 cites W1962021597 @default.
• W2890356255 cites W1967251218 @default.
• W2890356255 cites W1980863423 @default.
• W2890356255 cites W1992768366 @default.
• W2890356255 cites W2035093859 @default.
• W2890356255 cites W2058486397 @default.
• W2890356255 cites W2059587208 @default.
• W2890356255 cites W2076760127 @default.
• W2890356255 cites W2097659543 @default.
• W2890356255 cites W2101926813 @default.
• W2890356255 cites W2112796928 @default.
• W2890356255 cites W2116360511 @default.
• W2890356255 cites W2117340355 @default.
• W2890356255 cites W2117539524 @default.
• W2890356255 cites W2125517732 @default.
• W2890356255 cites W2136145485 @default.
• W2890356255 cites W2148157540 @default.
• W2890356255 cites W2148347694 @default.
• W2890356255 cites W2171058572 @default.
• W2890356255 cites W2395611524 @default.
• W2890356255 cites W2410080553 @default.
• W2890356255 cites W2570488788 @default.
• W2890356255 cites W2581569339 @default.
• W2890356255 cites W2592929672 @default.
• W2890356255 cites W2604517836 @default.
• W2890356255 cites W2604920239 @default.
• W2890356255 cites W2731903911 @default.
• W2890356255 cites W2792259308 @default.
• W2890356255 cites W2919115771 @default.
• W2890356255 doi "https://doi.org/10.1016/j.acra.2018.08.003" @default.
• W2890356255 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6397788" @default.
• W2890356255 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30195415" @default.
• W2890356255 hasPublicationYear "2019" @default.
• W2890356255 type Work @default.
• W2890356255 sameAs 2890356255 @default.
• W2890356255 citedByCount "41" @default.
• W2890356255 countsByYear W28903562552019 @default.
• W2890356255 countsByYear W28903562552020 @default.
• W2890356255 countsByYear W28903562552021 @default.
• W2890356255 countsByYear W28903562552022 @default.
• W2890356255 countsByYear W28903562552023 @default.
• W2890356255 crossrefType "journal-article" @default.
• W2890356255 hasAuthorship W2890356255A5005451810 @default.
• W2890356255 hasAuthorship W2890356255A5008424493 @default.
• W2890356255 hasAuthorship W2890356255A5015008578 @default.
• W2890356255 hasAuthorship W2890356255A5016551394 @default.
• W2890356255 hasAuthorship W2890356255A5017234848 @default.
• W2890356255 hasAuthorship W2890356255A5019251773 @default.
• W2890356255 hasAuthorship W2890356255A5026508249 @default.
• W2890356255 hasAuthorship W2890356255A5046912865 @default.
• W2890356255 hasAuthorship W2890356255A5056393696 @default.
• W2890356255 hasAuthorship W2890356255A5073296164 @default.
• W2890356255 hasAuthorship W2890356255A5083316571 @default.
• W2890356255 hasBestOaLocation W28903562552 @default.
• W2890356255 hasConcept C104317684 @default.
• W2890356255 hasConcept C108583219 @default.
• W2890356255 hasConcept C153180895 @default.
• W2890356255 hasConcept C154945302 @default.
• W2890356255 hasConcept C185592680 @default.
• W2890356255 hasConcept C22029948 @default.
• W2890356255 hasConcept C2524010 @default.
• W2890356255 hasConcept C33923547 @default.
• W2890356255 hasConcept C41008148 @default.
• W2890356255 hasConcept C50644808 @default.
• W2890356255 hasConcept C55493867 @default.
• W2890356255 hasConcept C63479239 @default.
• W2890356255 hasConcept C81363708 @default.
• W2890356255 hasConcept C89600930 @default.
• W2890356255 hasConceptScore W2890356255C104317684 @default.
• W2890356255 hasConceptScore W2890356255C108583219 @default.
• W2890356255 hasConceptScore W2890356255C153180895 @default.
• W2890356255 hasConceptScore W2890356255C154945302 @default.
• W2890356255 hasConceptScore W2890356255C185592680 @default.
• W2890356255 hasConceptScore W2890356255C22029948 @default.
• W2890356255 hasConceptScore W2890356255C2524010 @default.
• W2890356255 hasConceptScore W2890356255C33923547 @default.
• W2890356255 hasConceptScore W2890356255C41008148 @default.
• W2890356255 hasConceptScore W2890356255C50644808 @default.

• next