Model-based deep learning framework for accelerated optical projection tomography - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Scientific Reports Année : 2023

Model-based deep learning framework for accelerated optical projection tomography

Résumé

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.

Dates et versions

hal-04334283 , version 1 (10-12-2023)

Identifiants

Citer

Marcos Obando, Andrea Bassi, Nicolas Ducros, Germán Mato, Teresa Correia. Model-based deep learning framework for accelerated optical projection tomography. Scientific Reports, 2023, 13 (1), pp.21735. ⟨10.1038/s41598-023-47650-3⟩. ⟨hal-04334283⟩
23 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More