Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382023662> ?p ?o ?g. }
- W4382023662 endingPage "513" @default.
- W4382023662 startingPage "493" @default.
- W4382023662 abstract "Physicians often label anatomical structure sets in Digital Imaging and Communications in Medicine (DICOM) images with nonstandard random names. Hence, the standardization of these names for the Organs at Risk (OARs), Planning Target Volumes (PTVs), and ‘Other’ organs is a vital problem. This paper presents novel deep learning methods on structure sets by integrating multimodal data compiled from the radiotherapy centers of the US Veterans Health Administration (VHA) and Virginia Commonwealth University (VCU). These de-identified data comprise 16,290 prostate structures. Our method integrates the multimodal textual and imaging data with Convolutional Neural Network (CNN)-based deep learning approaches such as CNN, Visual Geometry Group (VGG) network, and Residual Network (ResNet) and shows improved results in prostate radiotherapy structure name standardization. Evaluation with macro-averaged F1 score shows that our model with single-modal textual data usually performs better than previous studies. The models perform well on textual data alone, while the addition of imaging data shows that deep neural networks achieve better performance using information present in other modalities. Additionally, using masked images and masked doses along with text leads to an overall performance improvement with the CNN-based architectures than using all the modalities together. Undersampling the majority class leads to further performance enhancement. The VGG network on the masked image-dose data combined with CNNs on the text data performs the best and presents the state-of-the-art in this domain." @default.
- W4382023662 created "2023-06-27" @default.
- W4382023662 creator A5018203536 @default.
- W4382023662 creator A5021439006 @default.
- W4382023662 creator A5042412445 @default.
- W4382023662 creator A5047762320 @default.
- W4382023662 creator A5073284026 @default.
- W4382023662 creator A5080886331 @default.
- W4382023662 creator A5088682170 @default.
- W4382023662 date "2023-06-25" @default.
- W4382023662 modified "2023-09-30" @default.
- W4382023662 title "Multimodal Deep Learning Methods on Image and Textual Data to Predict Radiotherapy Structure Names" @default.
- W4382023662 cites W1832693441 @default.
- W4382023662 cites W2061459389 @default.
- W4382023662 cites W2064675550 @default.
- W4382023662 cites W2097117768 @default.
- W4382023662 cites W2112796928 @default.
- W4382023662 cites W2161673710 @default.
- W4382023662 cites W2194775991 @default.
- W4382023662 cites W2413354483 @default.
- W4382023662 cites W2482204222 @default.
- W4382023662 cites W2574038793 @default.
- W4382023662 cites W2735580341 @default.
- W4382023662 cites W2751796963 @default.
- W4382023662 cites W2774576524 @default.
- W4382023662 cites W2777460464 @default.
- W4382023662 cites W2794284562 @default.
- W4382023662 cites W2806482827 @default.
- W4382023662 cites W2901072570 @default.
- W4382023662 cites W2903870823 @default.
- W4382023662 cites W2907269905 @default.
- W4382023662 cites W2911489562 @default.
- W4382023662 cites W2919115771 @default.
- W4382023662 cites W2944008497 @default.
- W4382023662 cites W2984722729 @default.
- W4382023662 cites W3002921634 @default.
- W4382023662 cites W3020971732 @default.
- W4382023662 cites W3048137319 @default.
- W4382023662 cites W3048631361 @default.
- W4382023662 cites W3090140268 @default.
- W4382023662 cites W3094253649 @default.
- W4382023662 cites W3107237003 @default.
- W4382023662 cites W3135847490 @default.
- W4382023662 cites W3155178406 @default.
- W4382023662 cites W3165373734 @default.
- W4382023662 cites W3187760235 @default.
- W4382023662 cites W3188053439 @default.
- W4382023662 cites W3198980621 @default.
- W4382023662 cites W3202927817 @default.
- W4382023662 cites W4206706211 @default.
- W4382023662 cites W4238732474 @default.
- W4382023662 cites W4306315581 @default.
- W4382023662 cites W4376598142 @default.
- W4382023662 doi "https://doi.org/10.3390/biomedinformatics3030034" @default.
- W4382023662 hasPublicationYear "2023" @default.
- W4382023662 type Work @default.
- W4382023662 citedByCount "0" @default.
- W4382023662 crossrefType "journal-article" @default.
- W4382023662 hasAuthorship W4382023662A5018203536 @default.
- W4382023662 hasAuthorship W4382023662A5021439006 @default.
- W4382023662 hasAuthorship W4382023662A5042412445 @default.
- W4382023662 hasAuthorship W4382023662A5047762320 @default.
- W4382023662 hasAuthorship W4382023662A5073284026 @default.
- W4382023662 hasAuthorship W4382023662A5080886331 @default.
- W4382023662 hasAuthorship W4382023662A5088682170 @default.
- W4382023662 hasBestOaLocation W43820236621 @default.
- W4382023662 hasConcept C108583219 @default.
- W4382023662 hasConcept C111919701 @default.
- W4382023662 hasConcept C119857082 @default.
- W4382023662 hasConcept C136536468 @default.
- W4382023662 hasConcept C144024400 @default.
- W4382023662 hasConcept C153180895 @default.
- W4382023662 hasConcept C154945302 @default.
- W4382023662 hasConcept C188087704 @default.
- W4382023662 hasConcept C204321447 @default.
- W4382023662 hasConcept C2779903281 @default.
- W4382023662 hasConcept C36289849 @default.
- W4382023662 hasConcept C41008148 @default.
- W4382023662 hasConcept C50644808 @default.
- W4382023662 hasConcept C77331912 @default.
- W4382023662 hasConcept C81363708 @default.
- W4382023662 hasConceptScore W4382023662C108583219 @default.
- W4382023662 hasConceptScore W4382023662C111919701 @default.
- W4382023662 hasConceptScore W4382023662C119857082 @default.
- W4382023662 hasConceptScore W4382023662C136536468 @default.
- W4382023662 hasConceptScore W4382023662C144024400 @default.
- W4382023662 hasConceptScore W4382023662C153180895 @default.
- W4382023662 hasConceptScore W4382023662C154945302 @default.
- W4382023662 hasConceptScore W4382023662C188087704 @default.
- W4382023662 hasConceptScore W4382023662C204321447 @default.
- W4382023662 hasConceptScore W4382023662C2779903281 @default.
- W4382023662 hasConceptScore W4382023662C36289849 @default.
- W4382023662 hasConceptScore W4382023662C41008148 @default.
- W4382023662 hasConceptScore W4382023662C50644808 @default.
- W4382023662 hasConceptScore W4382023662C77331912 @default.
- W4382023662 hasConceptScore W4382023662C81363708 @default.
- W4382023662 hasIssue "3" @default.
- W4382023662 hasLocation W43820236621 @default.