Model-based deep learning framework for accelerated optical projection tomography | ||
| dc.conicet.organizacion | Comisión Nacional de Energía Atómica. Gerencia del Área de Energía Nuclear. Instituto Balseiro | |
| dc.conicet.organizacion | Politecnico di Milano | |
| dc.conicet.organizacion | Centre National de la Recherche Scientifique | |
| dc.conicet.organizacion | Comisión Nacional de Energía Atómica. Gerencia del Área de Energía Nuclear. Instituto Balseiro. Archivo Histórico del Centro Atómico Bariloche e Instituto Balseiro | Universidad Nacional de Cuyo. Instituto Balseiro. Archivo Histórico del Centro Atómico Bariloche e Instituto Balseiro | |
| dc.conicet.organizacion | Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Patagonia Norte | |
| dc.conicet.organizacion | Kings College London (kcl) | |
| dc.contributor.author | Obando, Marcos | |
| dc.contributor.author | Bassi, Andrea | |
| dc.contributor.author | Ducros, Nicolas | |
| dc.contributor.author | Mato, German | |
| dc.contributor.author | Correia, Teresa M. | |
| dc.date.issued | 2023-12 | |
| dc.description.abstract | In this work, we propose a model-based deep learning reconstruction algorithm for optical projection tomography (ToMoDL), to greatly reduce acquisition and reconstruction times. The proposed method iterates over a data consistency step and an image domain artefact removal step achieved by a convolutional neural network. A preprocessing stage is also included to avoid potential misalignments between the sample center of rotation and the detector. The algorithm is trained using a database of wild-type zebrafish (Danio rerio) at different stages of development to minimise the mean square error for a fixed number of iterations. Using a cross-validation scheme, we compare the results to other reconstruction methods, such as filtered backprojection, compressed sensing and a direct deep learning method where the pseudo-inverse solution is corrected by a U-Net. The proposed method performs equally well or better than the alternatives. For a highly reduced number of projections, only the U-Net method provides images comparable to those obtained with ToMoDL. However, ToMoDL has a much better performance if the amount of data available for training is limited, given that the number of network trainable parameters is smaller. | es |
| dc.description.fil | Fil: Obando, Marcos. Comisión Nacional de Energía Atómica. Gerencia del Área de Energía Nuclear. Instituto Balseiro; Argentina | |
| dc.description.fil | Fil: Bassi, Andrea. Politecnico di Milano; Italia | |
| dc.description.fil | Fil: Ducros, Nicolas. Centre National de la Recherche Scientifique; Francia | |
| dc.description.fil | Fil: Mato, German. Comisión Nacional de Energía Atómica. Gerencia del Área de Energía Nuclear. Instituto Balseiro. Archivo Histórico del Centro Atómico Bariloche e Instituto Balseiro | Universidad Nacional de Cuyo. Instituto Balseiro. Archivo Histórico del Centro Atómico Bariloche e Instituto Balseiro; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Patagonia Norte; Argentina | |
| dc.description.fil | Fil: Correia, Teresa M.. Kings College London (kcl); | |
| dc.format | application/pdf | es |
| dc.identifier.citation | Obando, Marcos; Bassi, Andrea; Ducros, Nicolas; Mato, German; Correia, Teresa M.; Model-based deep learning framework for accelerated optical projection tomography; Nature; Scientific Reports; 13; 1; 12-2023; 1-9 | es |
| dc.identifier.institucional | CONICET | |
| dc.identifier.issn | 2045-2322 | es |
| dc.identifier.repo | CONICET Digital | |
| dc.identifier.uri | http://hdl.handle.net/11336/225457 | |
| dc.journal.number | 1 | es |
| dc.journal.pagination | 1-9 | es |
| dc.journal.pais | Reino Unido | es |
| dc.journal.title | Scientific Reports | es |
| dc.journal.volume | 13 | es |
| dc.language.iso | eng | es |
| dc.publisher | Nature | es |
| dc.relation.alternativeid | info:eu-repo/semantics/altIdentifier/url/https://www.nature.com/articles/s41598-023-47650-3 | |
| dc.relation.alternativeid | info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1038/s41598-023-47650-3 | |
| dc.rights | info:eu-repo/semantics/openAccess | * |
| dc.rights.uri | https://creativecommons.org/licenses/by/2.5/ar/ | * |
| dc.subject | optical projection tomography | es |
| dc.subject | deep learning | es |
| dc.subject | acceleration | es |
| dc.subject.classification | Otras Ciencias Naturales y Exactas | es |
| dc.subject.classification | Otras Ciencias Naturales y Exactas | es |
| dc.subject.classification | CIENCIAS NATURALES Y EXACTAS | es |
| dc.title | Model-based deep learning framework for accelerated optical projection tomography | es |
| dc.type | info:eu-repo/semantics/article | |
| dc.type | info:ar-repo/semantics/artículo | |
| dc.type | info:eu-repo/semantics/publishedVersion | |
Archivos
Bloque original
Cargando...
- Nombre:
- CONICET_Digital_Nro.58f54c6e-ee47-404e-bd17-d458de629a8b_B.pdf
- Tamaño:
- 2.08 MB
- Formato:
- Adobe Portable Document Format