OPTical Imaging of Molecular and signalling Activity in Real-time: application to flatfish metamorphosis

Funder

Organizational Unit

Publications

Model-based deep learning framework for accelerated optical projection tomography

Publication . Obando, Marcos; Bassi, Andrea; Ducros, Nicolas; Mato, Germán; Correia, Teresa

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.

2023Journal article

Open access

Accelerated dynamic light sheet microscopy: unifying time-varying patterned illumination and low-rank and sparsity constrained reconstruction

Publication . Vitali, Marco Tobia; Candeo, Alessia; Farina, Andrea; Pozzi, Paolo; Brix, Alessia; Bassi, Andrea; Correia, Teresa

Light Sheet Fluorescence Microscopy (LSFM) enables rapid and gentle 3D fluorescence imaging of dynamic processes over extended periods in translucent samples at the mesoscopic scale. However, its temporal resolution is constrained by the sequential acquisition of individual two-dimensional planes at varying depths, making it challenging to capture rapid dynamics such as the beating of a zebrafish heart. To address this limitation, we recently developed spatially modulated Selective Volume Illumination Microscopy, which utilizes a compressed sensing approach to reconstruct the entire imaging volume from measurements where multiple planes are illuminated simultaneously using spatially modulated light. Building on this advancement, we now introduce a novel spatio-temporal patterned illumination strategy and volume reconstruction method that incorporates low-rank and sparsity constraints, effectively leveraging the temporal and spatial redundancy present in sequential volumetric acquisitions. This method was applied to the volumetric imaging of embryonic zebrafish hearts, achieving an improvement in imaging speed of 4-fold compared to standard LSFM and a 2-fold improvement compared to traditional compressed sensing approaches, while preserving reconstruction accuracy and enabling the visualization of fast dynamic events with a resolution of a few tens of milliseconds. Our approach represents a step forward in enhancing the temporal resolution of LSFM for studying fast biological dynamics.

2025-02-10Journal article

Open access