Centre de documentation
scientifique

A stacked dense denoising–segmentation network for undersampled tomograms and knowledge transfer using synthetic tomograms / Dimitrios Bellos in Machine Vision and Applications, vol 32 n° 3 (May 2021)  

Public [article]  inMachine Vision and Applications > vol 32 n° 3 (May 2021) . - n° 75 Titre : A stacked dense denoising–segmentation network for undersampled tomograms and knowledge transfer using synthetic tomograms Type de document : Article/Communication Auteurs : Dimitrios Bellos, Auteur ; Mark Basham, Auteur ; Tony Pridmore, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 75 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] acquisition de connaissances [Termes IGN] apprentissage profond [Termes IGN] échantillonnage [Termes IGN] filtrage du bruit [Termes IGN] rapport signal sur bruit [Termes IGN] rayon X [Termes IGN] reconstruction d'image [Termes IGN] segmentation sémantique [Termes IGN] série temporelle [Termes IGN] tomographie Résumé : (auteur) Over recent years, many approaches have been proposed for the denoising or semantic segmentation of X-ray computed tomography (CT) scans. In most cases, high-quality CT reconstructions are used; however, such reconstructions are not always available. When the X-ray exposure time has to be limited, undersampled tomograms (in terms of their component projections) are attained. This low number of projections offers low-quality reconstructions that are difficult to segment. Here, we consider CT time-series (i.e. 4D data), where the limited time for capturing fast-occurring temporal events results in the time-series tomograms being necessarily undersampled. Fortunately, in these collections, it is common practice to obtain representative highly sampled tomograms before or after the time-critical portion of the experiment. In this paper, we propose an end-to-end network that can learn to denoise and segment the time-series’ undersampled CTs, by training with the earlier highly sampled representative CTs. Our single network can offer two desired outputs while only training once, with the denoised output improving the accuracy of the final segmentation. Our method is able to outperform state-of-the-art methods in the task of semantic segmentation and offer comparable results in regard to denoising. Additionally, we propose a knowledge transfer scheme using synthetic tomograms. This not only allows accurate segmentation and denoising using less real-world data, but also increases segmentation accuracy. Finally, we make our datasets, as well as the code, publicly available. Numéro de notice : A2021-456 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00138-021-01196-4 Date de publication en ligne : 27/04/2021 En ligne : https://doi.org/10.1007/s00138-021-01196-4 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97902 [article]