Matches in SemOpenAlex for { <https://semopenalex.org/work/W3179341750> ?p ?o ?g. }
- W3179341750 abstract "Radiation therapy requires clinical linear accelerators to be mechanically and dosimetrically calibrated to a high standard. One important quality assurance test is the Winston-Lutz test which localizes the radiation isocentre of the linac. In the current work we demonstrate a novel method of analysing EPID based Winston-Lutz QA images using a deep learning model trained only on synthetic image this http URL addition, we propose a novel method of generating the synthetic WL images and associated ground-truth masks using an optical ray-tracing engine to fake mega-voltage EPID images. The model called DeepWL was trained on 1500 synthetic WL images using data augmentation techniques for 180 epochs. The model was built using Keras with a TensorFlow backend on an Intel Core i5 6500T CPU and trained in approximately 15 hours. DeepWL was shown to produce ball bearing and multi-leaf collimator field segmentations with a mean dice coefficient of 0.964 and 0.994 respectively on previously unseen synthetic testing data. When DeepWL was applied to WL data measured on an EPID, the predicted mean displacements were shown to be statistically similar to the Canny Edge detection method. However, the DeepWL predictions for the ball bearing locations were shown to correlate better with manual annotations compared with the Canny edge detection algorithm. DeepWL was demonstrated to analyse Winston-Lutz images with accuracy suitable for routine linac quality assurance with some statistical evidence that it may outperform Canny Edge detection methods in terms of segmentation robustness and the resultant displacement predictions." @default.
- W3179341750 created "2021-07-19" @default.
- W3179341750 creator A5034306162 @default.
- W3179341750 creator A5072344157 @default.
- W3179341750 date "2021-07-05" @default.
- W3179341750 modified "2023-09-26" @default.
- W3179341750 title "DeepWL: Robust EPID based Winston-Lutz Analysis using Deep Learning and Synthetic Image Generation" @default.
- W3179341750 cites W1869960814 @default.
- W3179341750 cites W1901129140 @default.
- W3179341750 cites W2003533398 @default.
- W3179341750 cites W2026303854 @default.
- W3179341750 cites W2035109934 @default.
- W3179341750 cites W2133224356 @default.
- W3179341750 cites W2145023731 @default.
- W3179341750 cites W2282582865 @default.
- W3179341750 cites W2472443435 @default.
- W3179341750 cites W2476468818 @default.
- W3179341750 cites W2743627947 @default.
- W3179341750 cites W2749375587 @default.
- W3179341750 cites W2884588043 @default.
- W3179341750 cites W2886075188 @default.
- W3179341750 cites W2895619167 @default.
- W3179341750 cites W2900237898 @default.
- W3179341750 cites W2905098610 @default.
- W3179341750 cites W2911424749 @default.
- W3179341750 cites W2914285266 @default.
- W3179341750 cites W2920206089 @default.
- W3179341750 cites W2923131319 @default.
- W3179341750 cites W2924973940 @default.
- W3179341750 cites W2949153442 @default.
- W3179341750 cites W2949577196 @default.
- W3179341750 cites W2951241187 @default.
- W3179341750 cites W2952224528 @default.
- W3179341750 cites W2953240077 @default.
- W3179341750 cites W2962914239 @default.
- W3179341750 cites W2966885779 @default.
- W3179341750 cites W2969809394 @default.
- W3179341750 cites W2972534068 @default.
- W3179341750 cites W2991286928 @default.
- W3179341750 cites W2991915699 @default.
- W3179341750 cites W2995095597 @default.
- W3179341750 cites W2998208444 @default.
- W3179341750 cites W2998280826 @default.
- W3179341750 cites W3006982732 @default.
- W3179341750 cites W3016181437 @default.
- W3179341750 cites W3025592469 @default.
- W3179341750 cites W3025626553 @default.
- W3179341750 cites W3033892175 @default.
- W3179341750 cites W3037430895 @default.
- W3179341750 cites W3040140780 @default.
- W3179341750 cites W3092001362 @default.
- W3179341750 cites W3103968743 @default.
- W3179341750 cites W3108126638 @default.
- W3179341750 cites W3133075814 @default.
- W3179341750 cites W3140378620 @default.
- W3179341750 cites W3155605993 @default.
- W3179341750 hasPublicationYear "2021" @default.
- W3179341750 type Work @default.
- W3179341750 sameAs 3179341750 @default.
- W3179341750 citedByCount "0" @default.
- W3179341750 crossrefType "posted-content" @default.
- W3179341750 hasAuthorship W3179341750A5034306162 @default.
- W3179341750 hasAuthorship W3179341750A5072344157 @default.
- W3179341750 hasConcept C104317684 @default.
- W3179341750 hasConcept C106436119 @default.
- W3179341750 hasConcept C108583219 @default.
- W3179341750 hasConcept C115961682 @default.
- W3179341750 hasConcept C127413603 @default.
- W3179341750 hasConcept C146849305 @default.
- W3179341750 hasConcept C14705441 @default.
- W3179341750 hasConcept C153180895 @default.
- W3179341750 hasConcept C154945302 @default.
- W3179341750 hasConcept C185592680 @default.
- W3179341750 hasConcept C193536780 @default.
- W3179341750 hasConcept C21547014 @default.
- W3179341750 hasConcept C2778618615 @default.
- W3179341750 hasConcept C31972630 @default.
- W3179341750 hasConcept C41008148 @default.
- W3179341750 hasConcept C55493867 @default.
- W3179341750 hasConcept C63479239 @default.
- W3179341750 hasConcept C89600930 @default.
- W3179341750 hasConcept C9417928 @default.
- W3179341750 hasConceptScore W3179341750C104317684 @default.
- W3179341750 hasConceptScore W3179341750C106436119 @default.
- W3179341750 hasConceptScore W3179341750C108583219 @default.
- W3179341750 hasConceptScore W3179341750C115961682 @default.
- W3179341750 hasConceptScore W3179341750C127413603 @default.
- W3179341750 hasConceptScore W3179341750C146849305 @default.
- W3179341750 hasConceptScore W3179341750C14705441 @default.
- W3179341750 hasConceptScore W3179341750C153180895 @default.
- W3179341750 hasConceptScore W3179341750C154945302 @default.
- W3179341750 hasConceptScore W3179341750C185592680 @default.
- W3179341750 hasConceptScore W3179341750C193536780 @default.
- W3179341750 hasConceptScore W3179341750C21547014 @default.
- W3179341750 hasConceptScore W3179341750C2778618615 @default.
- W3179341750 hasConceptScore W3179341750C31972630 @default.
- W3179341750 hasConceptScore W3179341750C41008148 @default.
- W3179341750 hasConceptScore W3179341750C55493867 @default.
- W3179341750 hasConceptScore W3179341750C63479239 @default.
- W3179341750 hasConceptScore W3179341750C89600930 @default.