EM algorithm
Dotaz
Zobrazit nápovědu
To stimulate progress in automating the reconstruction of neural circuits, we organized the first international challenge on 2D segmentation of electron microscopic (EM) images of the brain. Participants submitted boundary maps predicted for a test set of images, and were scored based on their agreement with a consensus of human expert annotations. The winning team had no prior experience with EM images, and employed a convolutional network. This "deep learning" approach has since become accepted as a standard for segmentation of EM images. The challenge has continued to accept submissions, and the best so far has resulted from cooperation between two teams. The challenge has probably saturated, as algorithms cannot progress beyond limits set by ambiguities inherent in 2D scoring and the size of the test dataset. Retrospective evaluation of the challenge scoring system reveals that it was not sufficiently robust to variations in the widths of neurite borders. We propose a solution to this problem, which should be useful for a future 3D segmentation challenge.
- Publikační typ
- časopisecké články MeSH
In cryo-electron microscopy, accurate particle localization and classification are imperative. Recent deep learning solutions, though successful, require extensive training datasets. The protracted generation time of physics-based models, often employed to produce these datasets, limits their broad applicability. We introduce FakET, a method based on neural style transfer, capable of simulating the forward operator of any cryo transmission electron microscope. It can be used to adapt a synthetic training dataset according to reference data producing high-quality simulated micrographs or tilt-series. To assess the quality of our generated data, we used it to train a state-of-the-art localization and classification architecture and compared its performance with a counterpart trained on benchmark data. Remarkably, our technique matches the performance, boosts data generation speed 750×, uses 33× less memory, and scales well to typical transmission electron microscope detector sizes. It leverages GPU acceleration and parallel processing. The source code is available at https://github.com/paloha/faket/.
BACKGROUND: Face transplantation (FT) has emerged as a viable option for treating devastating facial injuries. Most reported outcomes have demonstrated satisfactory motor and sensory restoration despite differences in technique. The authors have developed an algorithm of facial nerve management in these challenging patients. Our principles of management are illustrated by 2 specific patients. METHODS: A retrospective analysis of prospectively collected data on 2 full face transplants was performed. Both patients required nerve grafting during full FT. Patient 1 due to short donor facial nerve stumps and patient 2 due to intraoperative soft tissue swelling. Patient 2 required a nerve transfer 11 months after full FT due to impaired motor recovery opposite the side of nerve grafting. Follow-up examinations consisting of manual muscle testing and Sunnybrook Facial Grading System 6 to 42 months after full FT with selected video examinations were critically reviewed. RESULTS: Patient 1 had symmetrical motor recovery with gradual improvements noted throughout. At 6 months, Patient 2 had asymmetrically improving motor function. After nerve transfer, the patient showed gradual improvement in motor recovery, symmetry, and tone. Videos for each patient demonstrate the evolution of the patients' ability to smile from 6 to 42 months. DISCUSSION: The authors describe their assessment of motor recovery and management of facial nerve reconstruction as it pertains to FT. Finally, the authors illustrate the principles of nerve transfer are applicable to FT recipients.
- Publikační typ
- časopisecké články MeSH
Image processing in cryogenic electron tomography (cryoET) is currently at a similar state as Single Particle Analysis (SPA) in cryogenic electron microscopy (cryoEM) was a few years ago. Its data processing workflows are far from being well defined and the user experience is still not smooth. Moreover, file formats of different software packages and their associated metadata are not standardized, mainly since different packages are developed by different groups, focusing on different steps of the data processing pipeline. The Scipion framework, originally developed for SPA (de la Rosa-Trevín et al., 2016), has a generic python workflow engine that gives it the versatility to be extended to other fields, as demonstrated for model building (Martínez et al., 2020). In this article, we provide an extension of Scipion based on a set of tomography plugins (referred to as ScipionTomo hereafter), with a similar purpose: to allow users to be focused on the data processing and analysis instead of having to deal with multiple software installation issues and the inconvenience of switching from one to another, converting metadata files, managing possible incompatibilities, scripting (writing a simple program in a language that the computer must convert to machine language each time the program is run), etcetera. Additionally, having all the software available in an integrated platform allows comparing the results of different algorithms trying to solve the same problem. In this way, the commonalities and differences between estimated parameters shed light on which results can be more trusted than others. ScipionTomo is developed by a collaborative multidisciplinary team composed of Scipion team engineers, structural biologists, and in some cases, the developers whose software packages have been integrated. It is open to anyone in the field willing to contribute to this project. The result is a framework extension that combines the acquired knowledge of Scipion developers in close collaboration with third-party developers, and the on-demand design of functionalities requested by beta testers applying this solution to actual biological problems.
... Uniform Simulation 36 r 2.1.2 The Inverse Transform 38 i 2.1.3 Alternatives 40 -- 2.1.4 Optimal Algorithms ... ... 5.3 Stochastic Approximation 174 -- 5.3.1 Missing Data Models and Demarginalization 174 -- 5.3.2 The EM ... ... Algorithm 176 -- 5.3.3 Monte Carlo EM 183 -- 5.3.4 EM Standard Errors 186 -- Contents XIX -- 5.4 Problems ... ... 313 -- 7.8.2 Geometric Convergence of Metropolis-Hastings -- Algorithms 315 -- 7.8.3 A Reinterpretation ... ... of Simulated Annealing 315 -- 7.8.4 Reference Acceptance Rates 316 -- 7.8.5 Langevin Algorithms 318 ...
Springer texts in statistics
2nd ed. xxx, 645 s., grafy
BACKGROUND AND PURPOSE: Characterization of iron deposition associated with demyelinating lesions of multiple sclerosis and neuromyelitis optica has not been well studied. Our aim was to investigate the potential of ultra-high-field MR imaging to distinguish MS from neuromyelitis optica and to characterize tissue injury associated with iron pathology within lesions. MATERIALS AND METHODS: Twenty-one patients with MS and 21 patients with neuromyelitis optica underwent 7T high-resolution 2D-gradient-echo-T2* and 3D-susceptibility-weighted imaging. An in-house-developed algorithm was used to reconstruct quantitative susceptibility mapping from SWI. Lesions were classified as "iron-laden" if they demonstrated hypointensity on gradient-echo-T2*-weighted images and/or SWI and hyperintensity on quantitative susceptibility mapping. Lesions were considered "non-iron-laden" if they were hyperintense on gradient-echo-T2* and isointense or hyperintense on quantitative susceptibility mapping. RESULTS: Of 21 patients with MS, 19 (90.5%) demonstrated at least 1 quantitative susceptibility mapping-hyperintense lesion, and 11/21 (52.4%) had iron-laden lesions. No quantitative susceptibility mapping-hyperintense or iron-laden lesions were observed in any patients with neuromyelitis optica. Iron-laden and non-iron-laden lesions could each be further characterized into 2 distinct patterns based on lesion signal and morphology on gradient-echo-T2*/SWI and quantitative susceptibility mapping. In MS, most lesions (n = 262, 75.9% of all lesions) were hyperintense on gradient-echo T2* and isointense on quantitative susceptibility mapping (pattern A), while a small minority (n = 26, 7.5% of all lesions) were hyperintense on both gradient-echo-T2* and quantitative susceptibility mapping (pattern B). Iron-laden lesions (n = 57, 16.5% of all lesions) were further classified as nodular (n = 22, 6.4%, pattern C) or ringlike (n = 35, 10.1%, pattern D). CONCLUSIONS: Ultra-high-field MR imaging may be useful in distinguishing MS from neuromyelitis optica. Different patterns related to iron and noniron pathology may provide in vivo insight into the pathophysiology of lesions in MS.
- MeSH
- algoritmy MeSH
- dítě MeSH
- dospělí MeSH
- elektromagnetická pole MeSH
- kojenec MeSH
- lidé středního věku MeSH
- lidé MeSH
- magnetická rezonanční tomografie MeSH
- mapování mozku MeSH
- mladiství MeSH
- mladý dospělý MeSH
- neuromyelitis optica diagnostické zobrazování metabolismus MeSH
- novorozenec MeSH
- počítačové zpracování obrazu MeSH
- předškolní dítě MeSH
- roztroušená skleróza diagnostické zobrazování metabolismus MeSH
- železo metabolismus MeSH
- zobrazování trojrozměrné MeSH
- Check Tag
- dítě MeSH
- dospělí MeSH
- kojenec MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladiství MeSH
- mladý dospělý MeSH
- mužské pohlaví MeSH
- novorozenec MeSH
- předškolní dítě MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
When considering the probabilistic approach to neural networks in the framework of statistical pattern recognition we assume approximation of class-conditional probability distributions by finite mixtures of product components. The mixture components can be interpreted as probabilistic neurons in neurophysiological terms and, in this respect, the fixed probabilistic description contradicts the well known short-term dynamic properties of biological neurons. By introducing iterative schemes of recognition we show that some parameters of probabilistic neural networks can be "released" for the sake of dynamic processes without disturbing the statistically correct decision making. In particular, we can iteratively adapt the mixture component weights or modify the input pattern in order to facilitate correct recognition. Both procedures are shown to converge monotonically as a special case of the well known EM algorithm for estimating mixtures.
OBJECTIVES: To determine the relationship between nasolabial symmetry and esthetics in subjects with orofacial clefts. MATERIAL AND METHODS: Eighty-four subjects (mean age 10 years, standard deviation 1.5) with various types of nonsyndromic clefts were included: 11 had unilateral cleft lip (UCL); 30 had unilateral cleft lip and alveolus (UCLA); and 43 had unilateral cleft lip, alveolus, and palate (UCLAP). A 3D stereophotogrammetric image of the face was taken for each subject. Symmetry and esthetics were evaluated on cropped 3D facial images. The degree of asymmetry of the nasolabial area was calculated based on all 3D data points using a surface registration algorithm. Esthetic ratings of various elements of nasal morphology were performed by eight lay raters on a 100 mm visual analog scale. Statistical analysis included ANOVA tests and regression models. RESULTS: Nasolabial asymmetry increased with growing severity of the cleft (p = 0.029). Overall, nasolabial appearance was affected by nasolabial asymmetry; subjects with more nasolabial asymmetry were judged as having a less esthetically pleasing nasolabial area (p < 0.001). However, the relationship between nasolabial symmetry and esthetics was relatively weak in subjects with UCLAP, in whom only vermilion border esthetics was associated with asymmetry. CONCLUSIONS: Nasolabial symmetry assessed with 3D facial imaging can be used as an objective measure of treatment outcome in subjects with less severe cleft deformity. In subjects with more severe cleft types, other factors may play a decisive role. CLINICAL SIGNIFICANCE: Assessment of nasolabial symmetry is a useful measure of treatment success in less severe cleft types.
- MeSH
- dítě MeSH
- lidé MeSH
- rozštěp patra patologie chirurgie MeSH
- rozštěp rtu patologie chirurgie MeSH
- zobrazování trojrozměrné * MeSH
- Check Tag
- dítě MeSH
- lidé MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
