New reconstruction methodology for chest tomosynthesis based on deep learning

dc.affiliation.dptoUC3M. Departamento de Bioingenieríaes
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Biomedical Imaging and Instrumentation Groupes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Arquitectura de Computadores, Comunicaciones y Sistemases
dc.contributor.authorFernández del Cerro, Carlos
dc.contributor.authorGalán González, Agustín
dc.contributor.authorGarcía Blas, Francisco Javier
dc.contributor.authorDesco Menéndez, Manuel
dc.contributor.authorAbella García, Mónica
dc.contributor.funderComunidad de Madrides
dc.contributor.funderAgencia Estatal de Investigación (España)es
dc.descriptionProceeding of: 7th International Conference on Image Formation in X-Ray Computed Tomography (ICIFXCT 2022), Baltimore, Maryland, 12-16 June 2022en
dc.description.abstractTomosynthesis offers an alternative to planar radiography providing pseudo-tomographic information at a much lower radiation dose than CT. The fact that it cannot convey information about the density poses a major limitation towards the use of tomosynthesis in chest imaging, due to the wide range of pathologies that present an increase in the density of the pulmonary parenchyma. Previous works have attempted to improve image quality through enhanced analytical, iterative algorithms, or including a deep learning-based step in the reconstruction, but the results shown are still far from the quantitative information of a CT. In this work, we propose a reconstruction methodology consisting of a filtered back-projection step followed by post-processing based on Deep Learning to obtain a tomographic image closer to CT. Preliminary results show the potential of the proposed methodology to obtain true tomographic information from tomosynthesis data, which could replace CT scans in applications where the radiation dose is critical.en
dc.description.sponsorshipThis work has been supported by Ministerio de Ciencia e Innovación, Agencia Estatal de Investigación: PID2019-110369RB-I00/AEI/10.13039/501100011033 (RADHOR); PDC2021-121656-I00 (MULTIRAD), funded by MCIN/AEI/10.13039/501100011033 and by the European Union 'NextGenerationEU'/PRTR. Also funded by Comunidad de Madrid: Multiannual Agreement with UC3M in the line of 'Fostering Young Doctors Research' (DEEPCT-CM-UC3M), and in the context of the V PRICIT (Regional Programme of Research and Technological Innovation S2017/BMD-3867 RENIM-CM, co-funded by European Structural and Investment Fund. And also partially funded by CRUE Universidades, CSIC and Banco Santander (Fondo Supera Covid19), project RADCOV19 and by Instituto de Salud Carlos III through the project "PT20/00044", cofunded by European Regional Development Fund "A way to make Europe";. The CNIC is supported by Instituto de Salud Carlos III, Ministerio de Ciencia e Innovacióm and the Pro CNIC Foundation. The imaging and associated clinical data downloaded from MIDRC (The Medical Imaging Data Resource Center) and used for research in this publication was made possible by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) of the National Institutes of Health under contracts 75N92020C00008 and 75N92020C00021.en
dc.identifier.bibliographicCitationCerro, Carlos F. del, et al. New reconstruction methodology for chest tomosynthesis based on deep learning. In: Proceedings of SPIE, vol. (7th International Conference on Image Formation in X-Ray Computed Tomography), 123042X. SPIE, June 2022, 8 p.en
dc.identifier.issn1996-756X (online)
dc.identifier.publicationtitleProceedings of SPIE (7th International Conference on Image Formation in X-Ray Computed Tomography)en
dc.publisherInternational Society for Optics and Photonicsen
dc.relation.eventplaceBaltimore, ESTADOS UNIDOS DE AMERICAen
dc.relation.eventtitle7th International Conference on Image Formation in X-Ray Computed Tomography (ICIFXCT 2022)en
dc.relation.projectIDGobierno de España. PID2019-110369RB-I00es
dc.relation.projectIDGobierno de España. PDC2021-121656-I00es
dc.relation.projectIDComunidad de Madrid. S2017/BMD-3867es
dc.rights© 2022 SPIE.en
dc.rights.accessRightsopen accessen
dc.subject.ecienciaBiología y Biomedicinaes
dc.subject.otherChest tomosynthesisen
dc.subject.otherComputed tomographyen
dc.subject.otherDeep learningen
dc.subject.otherFDK-based reconstructionen
dc.subject.otherTransfer learningen
dc.titleNew reconstruction methodology for chest tomosynthesis based on deep learningen
dc.typeconference paper*
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
1.82 MB
Adobe Portable Document Format