The use of high-resolution imaging methods in scanning transmission electron microscopy (STEM) is limited in many cases by the sensitivity of the sample to the beam and the onset of electron beam ...damage (for example, in the study of organic systems, in tomography and during in situ experiments). To demonstrate that alternative strategies for image acquisition can help alleviate this beam damage issue, here we apply compressive sensing via Bayesian dictionary learning to high-resolution STEM images. These computational algorithms have been applied to a set of images with a reduced number of sampled pixels in the image. For a reduction in the number of pixels down to 5% of the original image, the algorithms can recover the original image from the reduced data set. We show that this approach is valid for both atomic-resolution images and nanometer-resolution studies, such as those that might be used in tomography datasets, by applying the method to images of strontium titanate and zeolites. As STEM images are acquired pixel by pixel while the beam is scanned over the surface of the sample, these postacquisition manipulations of the images can, in principle, be directly implemented as a low-dose acquisition method with no change in the electron optics or the alignment of the microscope itself.
In domains where data are sensitive or private, there is great value in methods that can learn in a distributed manner without the data ever leaving the local devices. In light of this need, ...federated learning has emerged as a popular training paradigm. However, many federated learning approaches trade transmitting data for communicating updated weight parameters for each local device. Therefore, a successful breach that would have otherwise directly compromised the data instead grants whitebox access to the local model, which opens the door to a number of attacks, including exposing the very data federated learning seeks to protect. Additionally, in distributed scenarios, individual client devices commonly exhibit high statistical heterogeneity. Many common federated approaches learn a single global model; while this may do well on average, performance degrades when the i.i.d. assumption is violated, underfitting individuals further from the mean and raising questions of fairness. To address these issues, we propose Weight Anonymized Factorization for Federated Learning (WAFFLe), an approach that combines the Indian Buffet Process with a shared dictionary of weight factors for neural networks. Experiments on MNIST, FashionMNIST, and CIFAR-10 demonstrate WAFFLe's significant improvement to local test performance and fairness while simultaneously providing an extra layer of security.
Negative Binomial Process Count and Mixture Modeling Zhou, Mingyuan; Carin, Lawrence
IEEE transactions on pattern analysis and machine intelligence,
2015-Feb., 2015-Feb, 2015-2-00, 20150201, Volume:
37, Issue:
2
Journal Article
Peer reviewed
Open access
The seemingly disjoint problems of count and mixture modeling are united under the negative binomial (NB) process. A gamma process is employed to model the rate measure of a Poisson process, whose ...normalization provides a random probability measure for mixture modeling and whose marginalization leads to an NB process for count modeling. A draw from the NB process consists of a Poisson distributed finite number of distinct atoms, each of which is associated with a logarithmic distributed number of data samples. We reveal relationships between various count- and mixture-modeling distributions and construct a Poisson-logarithmic bivariate distribution that connects the NB and Chinese restaurant table distributions. Fundamental properties of the models are developed, and we derive efficient Bayesian inference. It is shown that with augmentation and normalization, the NB process and gamma-NB process can be reduced to the Dirichlet process and hierarchical Dirichlet process, respectively. These relationships highlight theoretical, structural, and computational advantages of the NB process. A variety of NB processes, including the beta-geometric, beta-NB, marked-beta-NB, marked-gamma-NB and zero-inflated-NB processes, with distinct sharing mechanisms, are also constructed. These models are applied to topic modeling, with connections made to existing algorithms under Poisson factor analysis. Example results show the importance of inferring both the NB dispersion and probability parameters.
Background
The growing interest in analysis of surgical video through machine learning has led to increased research efforts; however, common methods of annotating video data are lacking. There is a ...need to establish recommendations on the annotation of surgical video data to enable assessment of algorithms and multi-institutional collaboration.
Methods
Four working groups were formed from a pool of participants that included clinicians, engineers, and data scientists. The working groups were focused on four themes: (1) temporal models, (2) actions and tasks, (3) tissue characteristics and general anatomy, and (4) software and data structure. A modified Delphi process was utilized to create a consensus survey based on suggested recommendations from each of the working groups.
Results
After three Delphi rounds, consensus was reached on recommendations for annotation within each of these domains. A hierarchy for annotation of temporal events in surgery was established.
Conclusions
While additional work remains to achieve accepted standards for video annotation in surgery, the consensus recommendations on a general framework for annotation presented here lay the foundation for standardization. This type of framework is critical to enabling diverse datasets, performance benchmarks, and collaboration.
Circuits distributed across cortico-limbic brain regions compose the networks that mediate emotional behavior. The prefrontal cortex (PFC) regulates ultraslow (<1 Hz) dynamics across these networks, ...and PFC dysfunction is implicated in stress-related illnesses including major depressive disorder (MDD). To uncover the mechanism whereby stress-induced changes in PFC circuitry alter emotional networks to yield pathology, we used a multi-disciplinary approach including in vivo recordings in mice and chronic social defeat stress. Our network model, inferred using machine learning, linked stress-induced behavioral pathology to the capacity of PFC to synchronize amygdala and VTA activity. Direct stimulation of PFC-amygdala circuitry with DREADDs normalized PFC-dependent limbic synchrony in stress-susceptible animals and restored normal behavior. In addition to providing insights into MDD mechanisms, our findings demonstrate an interdisciplinary approach that can be used to identify the large-scale network changes that underlie complex emotional pathologies and the specific network nodes that can be used to develop targeted interventions.
•Prefrontal cortex (PFC) oscillations synchronize with ultraslow limbic dynamics•PFC unit firing signals the synchronization state of amygdala (AMY) and ventral tegmental area (VTA)•Chronic stress selectively disrupts PFC-dependent regulation of AMY-VTA synchrony•PFC to AMY circuit stimulation recovers normal network function and behavior
The complex mechanisms whereby multiple brain regions coordinate emotion remain tenebrous. Hultman et al. show that the prefrontal cortex (PFC) directly regulates beta oscillatory connectivity between multiple limbic brain regions. Stress-induced disruption of this PFC-dependent function yields pathological emotional behavior.
Acute respiratory infections caused by bacterial or viral pathogens are among the most common reasons for seeking medical care. Despite improvements in pathogen-based diagnostics, most patients ...receive inappropriate antibiotics. Host response biomarkers offer an alternative diagnostic approach to direct antimicrobial use. This observational cohort study determined whether host gene expression patterns discriminate noninfectious from infectious illness and bacterial from viral causes of acute respiratory infection in the acute care setting. Peripheral whole blood gene expression from 273 subjects with community-onset acute respiratory infection (ARI) or noninfectious illness, as well as 44 healthy controls, was measured using microarrays. Sparse logistic regression was used to develop classifiers for bacterial ARI (71 probes), viral ARI (33 probes), or a noninfectious cause of illness (26 probes). Overall accuracy was 87% (238 of 273 concordant with clinical adjudication), which was more accurate than procalcitonin (78%, P < 0.03) and three published classifiers of bacterial versus viral infection (78 to 83%). The classifiers developed here externally validated in five publicly available data sets (AUC, 0.90 to 0.99). A sixth publicly available data set included 25 patients with co-identification of bacterial and viral pathogens. Applying the ARI classifiers defined four distinct groups: a host response to bacterial ARI, viral ARI, coinfection, and neither a bacterial nor a viral response. These findings create an opportunity to develop and use host gene expression classifiers as diagnostic platforms to combat inappropriate antibiotic use and emerging antibiotic resistance.
Information-Theoretic Compressive Measurement Design Liming Wang; Minhua Chen; Rodrigues, Miguel ...
IEEE transactions on pattern analysis and machine intelligence,
2017-June-1, 2017-06-00, 2017-6-1, 20170601, Volume:
39, Issue:
6
Journal Article
Peer reviewed
Open access
An information-theoretic projection design framework is proposed, of interest for feature design and compressive measurements. Both Gaussian and Poisson measurement models are considered. The ...gradient of a proposed information-theoretic metric (ITM) is derived, and a gradient-descent algorithm is applied in design; connections are made to the information bottleneck. The fundamental solution structure of such design is revealed in the case of a Gaussian measurement model and arbitrary input statistics. This new theoretical result reveals how ITM parameter settings impact the number of needed projection measurements, with this verified experimentally. The ITM achieves promising results on real data, for both signal recovery and classification.
Abstract
We consider machine-learning-based lesion identification and malignancy prediction from clinical dermatological images, which can be indistinctly acquired via smartphone or dermoscopy ...capture. Additionally, we do not assume that images contain single lesions, thus the framework supports both focal or wide-field images. Specifically, we propose a two-stage approach in which we first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy that can be used for high-level screening processes. Further, we consider augmenting the proposed approach with clinical covariates (from electronic health records) and publicly available data (the ISIC dataset). Comprehensive experiments validated on an independent test dataset demonstrate that (1) the proposed approach outperforms alternative model architectures; (2) the model based on images outperforms a pure clinical model by a large margin, and the combination of images and clinical data does not significantly improves over the image-only model; and (3) the proposed framework offers comparable performance in terms of malignancy classification relative to three board certified dermatologists with different levels of experience.
We consider analysis of noisy and incomplete hyperspectral imagery, with the objective of removing the noise and inferring the missing data. The noise statistics may be wavelength dependent, and the ...fraction of data missing (at random) may be substantial, including potentially entire bands, offering the potential to significantly reduce the quantity of data that need be measured. To achieve this objective, the imagery is divided into contiguous three-dimensional (3D) spatio-spectral blocks of spatial dimension much less than the image dimension. It is assumed that each such 3D block may be represented as a linear combination of dictionary elements of the same dimension, plus noise, and the dictionary elements are learned in situ based on the observed data (no a priori training). The number of dictionary elements needed for representation of any particular block is typically small relative to the block dimensions, and all the image blocks are processed jointly ("collaboratively") to infer the underlying dictionary. We address dictionary learning from a Bayesian perspective, considering two distinct means of imposing sparse dictionary usage. These models allow inference of the number of dictionary elements needed as well as the underlying wavelength-dependent noise statistics. It is demonstrated that drawing the dictionary elements from a Gaussian process prior, imposing structure on the wavelength dependence of the dictionary elements, yields significant advantages, relative to the more conventional approach of using an independent and identically distributed Gaussian prior for the dictionary elements; this advantage is particularly evident in the presence of noise. The framework is demonstrated by processing hyperspectral imagery with a significant number of voxels missing uniformly at random, with imagery at specific wavelengths missing entirely, and in the presence of substantial additive noise.