Publication: New method for correcting beam-hardening artifacts in CT images via deep learning
dc.affiliation.dpto | UC3M. Departamento de Bioingeniería | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Biomedical Imaging and Instrumentation Group | es |
dc.contributor.author | Martínez Sánchez, Cristóbal | |
dc.contributor.author | Fernandez Del Cerro, Carlos | |
dc.contributor.author | Desco Menéndez, Manuel | |
dc.contributor.author | Abella García, Mónica | |
dc.contributor.funder | Comunidad de Madrid | es |
dc.contributor.funder | Ministerio de Ciencia e Innovación (España) | es |
dc.date.accessioned | 2023-05-24T15:23:41Z | |
dc.date.available | 2023-05-24T15:23:41Z | |
dc.date.issued | 2021-07-19 | |
dc.description | Proceedings of the 16th Virtual International Meeting on Fully 3D Image Reconstruction in Radiology and Nuclear Medicine, 19-23 July 2021, Leuven, Belgium. | en |
dc.description.abstract | Beam-hardening is the increase of the mean energy of an X-ray beam as it traverses a material. This effect produces two artifacts in the reconstructed image: cupping in homogeneous regions and dark bands among dense areas in heterogeneous regions. The correction methods proposed in the literature can be divided into post-processing and iterative methods. The former methods usually need a bone segmentation, which can fail in low-dose acquisitions, while the latter methods need several projections and reconstructions, increasing the computation time. In this work, we propose a new method for correcting the beamhardening artifacts in CT based on deep learning. A U-Net network was trained with rodent data for two scenarios: standard and low-dose. Results in an independent rodent study showed an optimum correction for both scenarios, similar to that of iterative approaches, but with a reduction of computational time of two orders of magnitude. | en |
dc.description.sponsorship | This work has been supported by project "DEEPCT-CMUC3M", funded by the call "Programa de apoyo a la realización de proyectos interdisciplinares de I+D para jóvenes investigadores de la UC3M 2019-2020, Convenio Plurianual CAM - UC3M" and project "RADCOV19", funded by CRUE Universidades, CSIC and Banco Santander (Fondo Supera). The CNIC is supported by the Ministerio de Ciencia, Innovación y Universidades and the Pro CNIC Foundation, and is a Severo Ochoa Center of Excellence (SEV-2015-0505). | en |
dc.format.extent | 5 | |
dc.identifier.bibliographicCitation | C. Martínez, C. F. Del Cerro, M. Desco & M. Abella (19-23 July 2021). New method for correcting beam-hardening artifacts in CT images via deep learning [poster]. Proceedings of the 16th Virtual International Meeting on Fully 3D Image Reconstruction in Radiology and Nuclear Medicine, Leuven, Belgium, pp. 188-192. | en |
dc.identifier.doi | https://doi.org/10.48550/arXiv.2110.04143 | |
dc.identifier.publicationfirstpage | 188 | |
dc.identifier.publicationlastpage | 192 | |
dc.identifier.publicationtitle | Proceedings of the 16th Virtual International Meeting on Fully 3D Image Reconstruction in Radiology and Nuclear Medicine | en |
dc.identifier.uri | https://hdl.handle.net/10016/37354 | |
dc.identifier.uxxi | CC/0000034354 | |
dc.language.iso | eng | |
dc.publisher | Cornell University | en |
dc.relation.eventdate | 2021-07-19 | |
dc.relation.eventplace | BÉLGICA | es |
dc.relation.eventtitle | 16th Virtual International Meeting on Fully 3D Image Reconstruction in Radiology and Nuclear Medicine (Fully3D 2021) | en |
dc.relation.projectID | Comunidad de Madrid. DEEPCT-CM-UC3M | es |
dc.relation.projectID | Gobierno de España. SEV-2015-0505 | es |
dc.rights | Atribución-NoComercial-SinDerivadas 3.0 España | * |
dc.rights.accessRights | open access | en |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ | * |
dc.subject.eciencia | Biología y Biomedicina | es |
dc.subject.eciencia | Electrónica | es |
dc.subject.eciencia | Medicina | es |
dc.title | New method for correcting beam-hardening artifacts in CT images via deep learning | en |
dc.type | conference poster | * |
dc.type.hasVersion | VoR | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1