1 February 2017 in Methods
Images in fluorescence microscopy are inherently blurred due to the limit of diffraction of light. The purpose of deconvolution microscopy is to compensate numerically for this degradation. Deconvolution is widely used to restore fine details of 3D biological samples. Unfortunately, dealing with deconvolution tools is not straightforward. Among others, end users have to select the appropriate algorithm, calibration and parametrization, while potentially facing demanding computational tasks. To make deconvolution more accessible, we have developed a practical platform for deconvolution microscopy called DeconvolutionLab. Freely distributed, DeconvolutionLab hosts standard algorithms for 3D microscopy deconvolution and drives them through a user-oriented interface. In this paper, we take advantage of the release of DeconvolutionLab2 to provide a complete description of the software package and its built-in deconvolution algorithms. We examine several standard algorithms used in deconvolution microscopy, notably: Regularized inverse filter, Tikhonov regularization, Landweber, Tikhonov-Miller, Richardson-Lucy, and fast iterative shrinkage-thresholding. We evaluate these methods over large 3D microscopy images using simulated datasets and real experimental images. We distinguish the algorithms in terms of image quality, performance, usability and computational requirements. Our presentation is completed with a discussion of recent trends in deconvolution, inspired by the results of the Grand Challenge on deconvolution microscopy that was recently organized.
13 July 2021 in IEEE Transactions on Computational Imaging
We present CryoGAN, a new paradigm for single-particle cryo-electron microscopy (cryo-EM) reconstruction based on unsupervised deep adversarial learning. In single-particle cryo-EM, the structure of a biomolecule needs to be reconstructed from a large set of noisy tomographic projections with unknown orientations. Current reconstruction techniques are based on a marginalized maximum-likelihood formulation that requires calculations over the set of all possible poses for each projection image, a computationally demanding procedure. Our approach is to seek a 3D structure that has simulated projections that match the real data in a distributional sense, thereby sidestepping pose estimation or marginalization. We prove that, in an idealized mathematical model of cryo-EM, this approach results in recovery of the correct structure. Motivated by distribution matching, we propose CryoGAN, a specialized GAN that consists of a 3D structure, a cryo-EM physics simulator, and a discriminator neural network. During reconstruction, the 3D structure is optimized so that its projections obtained through the simulator resemble real data (to the discriminator). Simultaneously, the discriminator is trained to distinguish real projections from simulated projections. CryoGAN takes as input only real projection images and the distribution of the cryo-EM imaging parameters. It involves neither prior training nor an initial estimation of the 3D structure. CryoGAN currently achieves a 10.8 Å resolution on a realistic synthetic dataset. Preliminary results on experimental β-galactosidase and 80S ribosome data demonstrate the ability of CryoGAN to exploit data statistics under standard experimental imaging conditions. We believe that this paradigm opens the door to a family of novel likelihood-free algorithms for cryo-EM reconstruction.
1 August 2017 in Ultramicroscopy
A central challenge in scanning transmission electron microscopy (STEM) is to reduce the electron radiation dosage required for accurate imaging of 3D biological nano-structures. Methods that permit tomographic reconstruction from a reduced number of STEM acquisitions without introducing significant degradation in the final volume are thus of particular importance. In random-beam STEM (RB-STEM), the projection measurements are acquired by randomly scanning a subset of pixels at every tilt view. In this work, we present a tailored RB-STEM acquisition-reconstruction framework that fully exploits the compressed sensing principles. We first demonstrate that RB-STEM acquisition fulfills the "incoherence" condition when the image is expressed in terms of wavelets. We then propose a regularized tomographic reconstruction framework to recover volumes from RB-STEM measurements. We demonstrate through simulations on synthetic and real projection measurements that the proposed framework reconstructs high-quality volumes from strongly downsampled RB-STEM data and outperforms existing techniques at doing so. This application of compressed sensing principles to STEM paves the way for a practical implementation of RB-STEM and opens new perspectives for high-quality reconstructions in STEM tomography. (C) 2017 The Authors. Published by Elsevier B.V.
16 October 2019 in bioRxiv
DeepImageJ is a user-friendly solution that enables the generic use of pre-trained deep learn ing (DL) models for biomedical image analysis in ImageJ. The deepImageJ environment gives access to the largest bioimage repository of pre-trained DL models (BioImage Model Zoo). Hence, non-experts can easily perform common image processing tasks in life-science research with DL-based tools including pixel and object classification, instance segmentation, denoising or virtual staining. DeepImageJ is compatible with existing state-of-the-art solutions and it is equipped with utility tools for developers to include new models. Very recently, several train ing frameworks have adopted the deepImageJ format to deploy their work in one of the most used software in the field (ImageJ). Beyond its direct use, we expect deepImageJ to contribute to the broader dissemination and reuse of DL models in life-sciences applications and bioimage informatics.
1 December 2018 in Journal of Structural Biology
We present a multiscale reconstruction framework for single-particle analysis (SPA). The representation of three-dimensional (3D) objects with scaled basis functions permits the reconstruction of volumes at any desired scale in the real-space. This multiscale approach generates interesting opportunities in SPA for the stabilization of the initial volume problem or the 3D iterative refinement procedure. In particular, we show that reconstructions performed at coarse scale are more robust to angular errors and permit gains in computational speed. A key component of the proposed iterative scheme is its fast implementation. The costly step of reconstruction, which was previously hindering the use of advanced iterative methods in SPA, is formulated as a discrete convolution with a cost that does not depend on the number of projection directions. The inclusion of the contrast transfer function inside the imaging matrix is also done at no extra computational cost. By permitting full 3D regularization, the framework is by itself a robust alternative to direct methods for performing reconstruction in adverse imaging conditions (e.g., heavy noise, large angular misassignments, low number of projections). We present reconstructions obtained at different scales from a dataset of the 2015/2016 EMDataBank Map Challenge. The algorithm has been implemented in the Scipion package.