Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205330793> ?p ?o ?g. }
- W4205330793 abstract "This paper presents an approach to enhanced endoscopic tool segmentation combining separate pathways utilizing input images in two different coordinate representations. The proposed method examines U-Net convolutional neural networks with input endoscopic images represented via (1) the original rectangular coordinate format alongside (2) a morphological polar coordinate transformation. To maximize information and the breadth of the endoscope frustrum, imaging sensors are oftentimes larger than the image circle. This results in unused border regions. Ideally, the region of interest is proximal to the image center. The above two observations formed the basis for the morphological polar transformation pathway as an augmentation to typical rectangular input image representations. Results indicate that neither of the two investigated coordinate representations consistently yielded better segmentation performance as compared to the other. Improved segmentation can be achieved with a hybrid approach that carefully selects which of the two pathways to be used for individual input images. Towards that end, two binary classifiers were trained to identify, given an input endoscopic image, which of the two coordinate representation segmentation pathways (rectangular or polar), would result in better segmentation performance. Results are promising and suggest marked improvements using a hybrid pathway selection approach compared to either alone. The experiment used to evaluate the proposed hybrid method utilized a dataset consisting of 8360 endoscopic images from real surgery and evaluated segmentation performance with Dice coefficient and Intersection over Union. The results suggest that on-the-fly polar transformation for tool segmentation is useful when paired with the proposed hybrid tool-segmentation approach." @default.
- W4205330793 created "2022-01-26" @default.
- W4205330793 creator A5030494145 @default.
- W4205330793 creator A5054787732 @default.
- W4205330793 creator A5062032121 @default.
- W4205330793 creator A5089381043 @default.
- W4205330793 date "2021-11-17" @default.
- W4205330793 modified "2023-09-24" @default.
- W4205330793 title "Enhanced U-Net Tool Segmentation using Hybrid Coordinate Representations of Endoscopic Images" @default.
- W4205330793 cites W1993828782 @default.
- W4205330793 cites W2100005771 @default.
- W4205330793 cites W2114224287 @default.
- W4205330793 cites W2117962795 @default.
- W4205330793 cites W2127102696 @default.
- W4205330793 cites W2179331991 @default.
- W4205330793 cites W2604690505 @default.
- W4205330793 cites W2753115354 @default.
- W4205330793 cites W2754241550 @default.
- W4205330793 cites W2792810896 @default.
- W4205330793 cites W2798221358 @default.
- W4205330793 cites W2884436604 @default.
- W4205330793 cites W2890456155 @default.
- W4205330793 cites W2910149883 @default.
- W4205330793 cites W2913567513 @default.
- W4205330793 cites W2962766617 @default.
- W4205330793 cites W2963139324 @default.
- W4205330793 cites W2964227007 @default.
- W4205330793 cites W2967185966 @default.
- W4205330793 cites W3003776740 @default.
- W4205330793 cites W3008810159 @default.
- W4205330793 cites W3016889634 @default.
- W4205330793 cites W3082513746 @default.
- W4205330793 cites W3120518626 @default.
- W4205330793 cites W3192675092 @default.
- W4205330793 cites W3193348384 @default.
- W4205330793 cites W2094645810 @default.
- W4205330793 cites W3122184490 @default.
- W4205330793 doi "https://doi.org/10.1109/ismr48346.2021.9661519" @default.
- W4205330793 hasPublicationYear "2021" @default.
- W4205330793 type Work @default.
- W4205330793 citedByCount "2" @default.
- W4205330793 countsByYear W42053307932023 @default.
- W4205330793 crossrefType "proceedings-article" @default.
- W4205330793 hasAuthorship W4205330793A5030494145 @default.
- W4205330793 hasAuthorship W4205330793A5054787732 @default.
- W4205330793 hasAuthorship W4205330793A5062032121 @default.
- W4205330793 hasAuthorship W4205330793A5089381043 @default.
- W4205330793 hasConcept C104317684 @default.
- W4205330793 hasConcept C124504099 @default.
- W4205330793 hasConcept C127413603 @default.
- W4205330793 hasConcept C146978453 @default.
- W4205330793 hasConcept C153180895 @default.
- W4205330793 hasConcept C154945302 @default.
- W4205330793 hasConcept C163892561 @default.
- W4205330793 hasConcept C185592680 @default.
- W4205330793 hasConcept C204241405 @default.
- W4205330793 hasConcept C2524010 @default.
- W4205330793 hasConcept C31972630 @default.
- W4205330793 hasConcept C33923547 @default.
- W4205330793 hasConcept C40069579 @default.
- W4205330793 hasConcept C41008148 @default.
- W4205330793 hasConcept C55493867 @default.
- W4205330793 hasConcept C64543145 @default.
- W4205330793 hasConcept C65885262 @default.
- W4205330793 hasConcept C80551277 @default.
- W4205330793 hasConcept C89600930 @default.
- W4205330793 hasConceptScore W4205330793C104317684 @default.
- W4205330793 hasConceptScore W4205330793C124504099 @default.
- W4205330793 hasConceptScore W4205330793C127413603 @default.
- W4205330793 hasConceptScore W4205330793C146978453 @default.
- W4205330793 hasConceptScore W4205330793C153180895 @default.
- W4205330793 hasConceptScore W4205330793C154945302 @default.
- W4205330793 hasConceptScore W4205330793C163892561 @default.
- W4205330793 hasConceptScore W4205330793C185592680 @default.
- W4205330793 hasConceptScore W4205330793C204241405 @default.
- W4205330793 hasConceptScore W4205330793C2524010 @default.
- W4205330793 hasConceptScore W4205330793C31972630 @default.
- W4205330793 hasConceptScore W4205330793C33923547 @default.
- W4205330793 hasConceptScore W4205330793C40069579 @default.
- W4205330793 hasConceptScore W4205330793C41008148 @default.
- W4205330793 hasConceptScore W4205330793C55493867 @default.
- W4205330793 hasConceptScore W4205330793C64543145 @default.
- W4205330793 hasConceptScore W4205330793C65885262 @default.
- W4205330793 hasConceptScore W4205330793C80551277 @default.
- W4205330793 hasConceptScore W4205330793C89600930 @default.
- W4205330793 hasFunder F4320306076 @default.
- W4205330793 hasLocation W42053307931 @default.
- W4205330793 hasOpenAccess W4205330793 @default.
- W4205330793 hasPrimaryLocation W42053307931 @default.
- W4205330793 hasRelatedWork W1507266234 @default.
- W4205330793 hasRelatedWork W1631910785 @default.
- W4205330793 hasRelatedWork W1669643531 @default.
- W4205330793 hasRelatedWork W1700740617 @default.
- W4205330793 hasRelatedWork W2069711651 @default.
- W4205330793 hasRelatedWork W2117664411 @default.
- W4205330793 hasRelatedWork W2117933325 @default.
- W4205330793 hasRelatedWork W2739874619 @default.
- W4205330793 hasRelatedWork W3197341992 @default.
- W4205330793 hasRelatedWork W1967061043 @default.
- W4205330793 isParatext "false" @default.