The Experts below are selected from a list of 252 Experts worldwide ranked by ideXlab platform
Joachim Frank - One of the best experts on this subject based on the ideXlab platform.
-
reference free particle selection enhanced with semi supervised machine learning for cryo electron microscopy
Journal of Structural Biology, 2011Co-Authors: Robert Langlois, Jesper Pallesen, Joachim FrankAbstract:Abstract Reference-based methods have dominated the approaches to the particle selection problem, proving fast, and accurate on even the most challenging Micrographs. A reference volume, however, is not always available and compiling a set of reference projections from the Micrographs themselves requires significant effort to attain the same level of accuracy. We propose a reference-free method to quickly extract particles from the Micrograph. The method is augmented with a new semi-supervised machine-learning algorithm to accurately discriminate particles from contaminants and noise.
-
An assay for local quality in cryo-electron Micrographs of single particles.
Ultramicroscopy, 2002Co-Authors: Christian M.t. Spahn, Robert A. Grassucci, Joachim FrankAbstract:Abstract High quality of the cryo-electron Micrographs is of crucial importance for the success of single particle three-dimensional reconstruction methods. In analyzing some Micrographs from cryo-electron microscopy specimens, we found an extraordinary variability, within the same Micrograph, in the appearance of particles. We developed a method for analyzing the variability of local image quality, using correspondence analysis of local power spectra. With this technique, we discovered a strong systematic variation of the envelope modulating an otherwise unchanged contrast transfer function. The underlying causes may be uncontrollable effects, such as variations in the thickness of ice, instability of the holey carbon, and charging. The method of assaying, resulting in “local quality maps”, may be useful as a general tool for screening Micrographs used as input for reconstructions.
Yoshinori Fujiyoshi - One of the best experts on this subject based on the ideXlab platform.
-
image resolution enhancement by combining information from electron diffraction pattern and Micrograph
Ultramicroscopy, 1991Co-Authors: Fan Haifu, Natsu Uyeda, Xiang Shibin, Li Fanghua, Pan Qing, Yoshinori FujiyoshiAbstract:Abstract An electron Micrograph of chlorinated copper phthalocyanine at 2 A resolution taken on the Kyoto 500 kV electron microscope has been enhanced to 1 A resolution by incorporating the information from the corresponding electron diffraction pattern. Structure-factor amplitudes up to 1 A resolution were obtained from the electron diffraction pattern. Phases of the structure factors within 2 A resolution were derived from the Fourier transform of the electron Micrograph. A phase-extension technique introduced from X-ray crystallography was then used to derive the phases between 2 and 1 A resolution. The final image was obtained by the inverse Fourier transform using the structure factor amplitudes from the electron diffraction pattern and the phases from the electron Micrograph and from the phase-extension procedure.
-
image deconvolution of a single high resolution electron Micrograph
Acta Crystallographica Section A, 1990Co-Authors: S B Xiang, D Tang, F H Li, Natsu Uyeda, Yoshinori FujiyoshiAbstract:An X-ray crystallographic method has been introduced into the image processing of high-resolution electron microscopy. This enables the deconvolution of single electron Micrographs of a crystalline sample. For this purpose the chemical composition of the sample should be known approximately, the image should be taken near the optimum defocus condition, but no preliminary knowledge of the crystal structure is needed. The method has been proved to be efficient with a high-resolution electron Micrograph of chlorinated copper phthalocyanine taken on the Kyoto 500 kV electron microscope.
Jose M Carazo - One of the best experts on this subject based on the ideXlab platform.
-
Micrographcleaner a python package for cryo em Micrograph cleaning using deep learning
Journal of Structural Biology, 2020Co-Authors: Ruben Sanchezgarcia, Joan Segura, David Maluenda, C O S Sorzano, Jose M CarazoAbstract:Abstract Cryo-EM Single Particle Analysis workflows require tens of thousands of high-quality particle projections to unveil the three-dimensional structure of macromolecules. Conventional methods for automatic particle picking tend to suffer from high false-positive rates, hampering the reconstruction process. One common cause of this problem is the presence of carbon and different types of high-contrast contaminations. In order to overcome this limitation, we have developed MicrographCleaner, a deep learning package designed to discriminate, in an automated fashion, between regions of Micrographs which are suitable for particle picking, and those which are not. MicrographCleaner implements a U-net-like deep learning model trained on a manually curated dataset compiled from over five hundred Micrographs. The benchmarking, carried out on approximately one hundred independent Micrographs, shows that MicrographCleaner is a very efficient approach for Micrograph preprocessing. MicrographCleaner (Micrograph_cleaner_em) package is available at PyPI and Anaconda Cloud and also as a Scipion/Xmipp protocol. Source code is available at https://github.com/rsanchezgarc/Micrograph_cleaner_em .
-
Micrographcleaner a python package for cryo em Micrograph cleaning using deep learning
bioRxiv, 2019Co-Authors: Ruben Sanchezgarcia, Joan Segura, David Maluenda, C O S Sorzano, Jose M CarazoAbstract:Cryo-EM workflows require from tens of thousands of high-quality particle projections to unveil the three-dimensional structure of macromolecules. Current methods for automatic particle picking tend to suffer from high false-positive rates, hurdling the reconstruction process. One common cause of this problem is the presence of carbon and different types of high-contrast contaminations that, in many cases, affect large areas of Micrographs. In order to overcome this limitation, we have developed MicrographCleaner, a deep learning approach designed to discriminate which regions of Micrographs are suitable for particle picking and which are not, that we will refer to as "contaminated". MicrographCleaner implements a U-net-like model trained on a manually curated dataset compiled from over five hundred Micrographs. The benchmarking, carried out on about one hundred independent Micrographs, shows that MicrographCleaner is a very efficient approach for Micrograph preprocessing.
Ruben Sanchezgarcia - One of the best experts on this subject based on the ideXlab platform.
-
Micrographcleaner a python package for cryo em Micrograph cleaning using deep learning
Journal of Structural Biology, 2020Co-Authors: Ruben Sanchezgarcia, Joan Segura, David Maluenda, C O S Sorzano, Jose M CarazoAbstract:Abstract Cryo-EM Single Particle Analysis workflows require tens of thousands of high-quality particle projections to unveil the three-dimensional structure of macromolecules. Conventional methods for automatic particle picking tend to suffer from high false-positive rates, hampering the reconstruction process. One common cause of this problem is the presence of carbon and different types of high-contrast contaminations. In order to overcome this limitation, we have developed MicrographCleaner, a deep learning package designed to discriminate, in an automated fashion, between regions of Micrographs which are suitable for particle picking, and those which are not. MicrographCleaner implements a U-net-like deep learning model trained on a manually curated dataset compiled from over five hundred Micrographs. The benchmarking, carried out on approximately one hundred independent Micrographs, shows that MicrographCleaner is a very efficient approach for Micrograph preprocessing. MicrographCleaner (Micrograph_cleaner_em) package is available at PyPI and Anaconda Cloud and also as a Scipion/Xmipp protocol. Source code is available at https://github.com/rsanchezgarc/Micrograph_cleaner_em .
-
Micrographcleaner a python package for cryo em Micrograph cleaning using deep learning
bioRxiv, 2019Co-Authors: Ruben Sanchezgarcia, Joan Segura, David Maluenda, C O S Sorzano, Jose M CarazoAbstract:Cryo-EM workflows require from tens of thousands of high-quality particle projections to unveil the three-dimensional structure of macromolecules. Current methods for automatic particle picking tend to suffer from high false-positive rates, hurdling the reconstruction process. One common cause of this problem is the presence of carbon and different types of high-contrast contaminations that, in many cases, affect large areas of Micrographs. In order to overcome this limitation, we have developed MicrographCleaner, a deep learning approach designed to discriminate which regions of Micrographs are suitable for particle picking and which are not, that we will refer to as "contaminated". MicrographCleaner implements a U-net-like model trained on a manually curated dataset compiled from over five hundred Micrographs. The benchmarking, carried out on about one hundred independent Micrographs, shows that MicrographCleaner is a very efficient approach for Micrograph preprocessing.
Daniel Lewis - One of the best experts on this subject based on the ideXlab platform.
-
Image driven machine learning methods for microstructure recognition
Computational Materials Science, 2016Co-Authors: Aritra Chowdhury, Elizabeth Kautz, Bülent Yener, Daniel LewisAbstract:Computer vision and machine learning methods were applied to the challenge of automatic microstructure recognition. Here, a case study on dendritic morphologies was performed. Two classification tasks were completed, and involved distinguishing between Micrographs that depict dendritic morphologies from those that do not contain this particular microstructural feature (Task 1), and from those Micrographs identified as depicting dendrites, different cross-sectional views (longitudinal or transverse) were identified (Task 2). Data sets were comprised of images taken over a range of magnifications, from materials with different compositions and varying orientations of microstructural features. Feature extraction and dimensionality reduction were performed prior to training machine learning algorithms to classify microstructural image data. Visual bag of words, texture and shape statistics, and pre-trained convolutional neural networks (deep learning algorithms) were used for feature extraction. Classification was then performed using support vector machine, voting, nearest neighbors, and random forest models. For each model, classification was completed using full (original size) and reduced feature vectors for each feature extraction method tested. Performance comparisons were done to evaluate all possible combinations of feature extraction, selection, and classifiers for the task of Micrograph classification. Results demonstrate that pre-trained neural networks represent microstructure image data well, and when used for feature extraction yield the highest classification accuracies for the majority of classifier and feature selection methods tested. Thus, deep learning algorithms can successfully be applied to Micrograph recognition tasks. Maximum classification accuracies of 91.85 ± 4.25% and 97.37 ± 3.33% for Tasks 1 and 2 respectively, were achieved. This work is a broad investigation of computer vision and machine learning methods that acts as a step towards applying these established methods to more sophisticated materials recognition or characterization tasks. The approach presented here could offer improvements over established stereological measurements by removing the requirement of expert knowledge (bias) for interpretation of image data prior to characterization.