Deep Active Learning via Open-Set Recognition.

In many applications, data is easy to acquire but expensive and time-consuming to label, prominent examples include medical imaging and NLP. This disparity has only grown in recent years as our ability to collect data improves. Under these constraints, it makes sense to select only the most informative instances from the unlabeled pool and request an oracle (e.g., a human expert) to provide labels for those samples. The goal of active learning is to infer the informativeness of unlabeled samples so as to minimize the number of requests to the oracle. Here, we formulate active learning as an open-set recognition problem. In this paradigm, only some of the inputs belong to known classes; the classifier must identify the rest as unknown. More specifically, we leverage variational neural networks (VNNs), which produce high-confidence (i.e., low-entropy) predictions only for inputs that closely resemble the training data. We use the inverse of this confidence measure to select the samples that the oracle should label. Intuitively, unlabeled samples that the VNN is uncertain about contain features that the network has not been exposed to; thus they are more informative for future training. We carried out an extensive evaluation of our novel, probabilistic formulation of active learning, achieving state-of-the-art results on MNIST, CIFAR-10, CIFAR-100, and FashionMNIST. Additionally, unlike current active learning methods, our algorithm can learn even in the presence of out-of-distribution outliers. As our experiments show, when the unlabeled pool consists of a mixture of samples from multiple datasets, our approach can automatically distinguish between samples from seen vs. unseen datasets. Overall, our results show that high-quality uncertainty measures are key for pool-based active learning.

Methicillin-resistant Staphylococcus aureus in Nepal: A systematic review and meta-analysis.

BACKGROUND: Methicillin-resistant Staphylococcus aureus (MRSA) is a significant health threat and public burden worldwide, particularly in developing countries, including Nepal, due to its low healthcare standards and irrational use of antibiotics. It is evident that MRSA strains are frequently detected in Nepalese hospitals; however, they remain underreported. Therefore, to provide a comprehensive and clear understanding of MRSA infection at the national level, this systematic review and meta-analysis evaluated the prevalence and antimicrobial susceptibility patterns of MRSA in Nepal. METHODS: PubMed, EMBASE, Cochrane CENTRAL, Google scholar, and Nepalese databases were searched for studies published between 1st January 2008 and 31st August 2020. A total of 26 original articles were selected for quantitative analysis. Data extraction was accomplished by three authors independently and meta-analysis was performed using MedCalc Version 19.5.1 and Comprehensive Meta-Analysis (CMA) software v.3.0. RESULT: The pooled prevalence of MRSA infections among 5951 confirmed S. aureus isolates was 38.2% (95% CI, 31.4%-45.2%). We found a significant heterogeneity (I2 = 96.7% for resistance proportion), and no evidence of publication bias (p = 0.256) among studies. MRSA strains showed a high level of resistance to beta-lactam antibiotics and the highest susceptibility profile was noted in vancomycin 98.0% followed by chloramphenicol 91.0%. CONCLUSION: The analysis revealed that the overall MRSA burden in Nepal is considerably high and the prevalence of MRSA infections is in the increasing trend. Sound legislation, definite antibiotic policy, and implementations of control interventions are indispensable for tackling MRSA infection and antimicrobial resistance as a whole.

Self-Net: Lifelong Learning via Continual Self-Modeling.

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence. While recent approaches achieve some degree of CL in deep neural networks, they either (1) store a new network (or an equivalent number of parameters) for each new task, (2) store training data from previous tasks, or (3) restrict the network's ability to learn new tasks. To address these issues, we propose a novel framework, Self-Net, that uses an autoencoder to learn a set of low-dimensional representations of the weights learned for different tasks. We demonstrate that these low-dimensional vectors can then be used to generate high-fidelity recollections of the original weights. Self-Net can incorporate new tasks over time with little retraining, minimal loss in performance for older tasks, and without storing prior training data. We show that our technique achieves over 10X storage compression in a continual fashion, and that it outperforms state-of-the-art approaches on numerous datasets, including continual versions of MNIST, CIFAR10, CIFAR100, Atari, and task-incremental CORe50. To the best of our knowledge, we are the first to use autoencoders to sequentially encode sets of network weights to enable continual learning.

Short Duration Repetitive Transcranial Electrical Stimulation During Sleep Enhances Declarative Memory of Facts.

Transcranial electrical stimulation (tES) during sleep has been shown to successfully modulate memory consolidation. Here, we tested the effect of short duration repetitive tES (SDR-tES) during a daytime nap on the consolidation of declarative memory of facts in healthy individuals. We use a previously described approach to deliver the stimulation at regular intervals during non-rapid eye movement (NREM) sleep, specifically stage NREM2 and NREM3. Similar to previous studies using tES, we find enhanced memory performance compared to sham both after sleep and 48 h later. We also observed an increase in the proportion of time spent in NREM3 sleep and SDR-tES boosted the overall rate of slow oscillations (SOs) during NREM2/NREM3 sleep. Retrospective investigation of brain activity immediately preceding stimulation suggests that increases in the SO rate are more likely when stimulation is delivered during quiescent and asynchronous periods of activity in contrast to other closed-loop approaches which target phasic stimulation during ongoing SOs.

Single neurons may encode simultaneous stimuli by switching between activity patterns.

How the brain preserves information about multiple simultaneous items is poorly understood. We report that single neurons can represent multiple stimuli by interleaving signals across time. We record single units in an auditory region, the inferior colliculus, while monkeys localize 1 or 2 simultaneous sounds. During dual-sound trials, we find that some neurons fluctuate between firing rates observed for each single sound, either on a whole-trial or on a sub-trial timescale. These fluctuations are correlated in pairs of neurons, can be predicted by the state of local field potentials prior to sound onset, and, in one monkey, can predict which sound will be reported first. We find corroborating evidence of fluctuating activity patterns in a separate dataset involving responses of inferotemporal cortex neurons to multiple visual stimuli. Alternation between activity patterns corresponding to each of multiple items may therefore be a general strategy to enhance the brain processing capacity, potentially linking such disparate phenomena as variable neural firing, neural oscillations, and limits in attentional/memory capacity.

Closed-Loop Targeted Memory Reactivation during Sleep Improves Spatial Navigation.

Sounds associated with newly learned information that are replayed during non-rapid eye movement (NREM) sleep can improve recall in simple tasks. The mechanism for this improvement is presumed to be reactivation of the newly learned memory during sleep when consolidation takes place. We have developed an EEG-based closed-loop system to precisely deliver sensory stimulation at the time of down-state to up-state transitions during NREM sleep. Here, we demonstrate that applying this technology to participants performing a realistic navigation task in virtual reality results in a significant improvement in navigation efficiency after sleep that is accompanied by increases in the spectral power especially in the fast (12-15 Hz) sleep spindle band. Our results show promise for the application of sleep-based interventions to drive improvement in real-world tasks.

Using an Image Fusion Methodology to Improve Efficiency and Traceability of Posterior Pole Vessel Analysis by ROPtool.

BACKGROUND: The diagnosis of plus disease in retinopathy of prematurity (ROP) largely determines the need for treatment; however, this diagnosis is subjective. To make the diagnosis of plus disease more objective, semi-automated computer programs (e.g. ROPtool) have been created to quantify vascular dilation and tortuosity. ROPtool can accurately analyze blood vessels only in images with very good quality, but many still images captured by indirect ophthalmoscopy have insufficient image quality for ROPtool analysis. PURPOSE: To evaluate the ability of an image fusion methodology (robust mosaicing) to increase the efficiency and traceability of posterior pole vessel analysis by ROPtool. MATERIALS AND METHODOLOGY: We retrospectively reviewed video indirect ophthalmoscopy images acquired during routine ROP examinations and selected the best unenhanced still image from the video for each infant. Robust mosaicing was used to create an enhanced mosaic image from the same video for each eye. We evaluated the time required for ROPtool analysis as well as ROPtool's ability to analyze vessels in enhanced vs. unenhanced images. RESULTS: We included 39 eyes of 39 infants. ROPtool analysis was faster (125 vs. 152 seconds; p=0.02) in enhanced vs. unenhanced images, respectively. ROPtool was able to trace retinal vessels in more quadrants (143/156, 92% vs 115/156, 74%; p=0.16) in enhanced mosaic vs. unenhanced still images, respectively and in more overall (38/39, 97% vs. 34/39, 87%; p=0.07) enhanced mosaic vs. unenhanced still images, respectively. CONCLUSION: Retinal image enhancement using robust mosaicing advances efforts to automate grading of posterior pole disease in ROP.

Tree Topology Estimation.

Tree-like structures are fundamental in nature, and it is often useful to reconstruct the topology of a tree - what connects to what - from a two-dimensional image of it. However, the projected branches often cross in the image: the tree projects to a planar graph, and the inverse problem of reconstructing the topology of the tree from that of the graph is ill-posed. We regularize this problem with a generative, parametric tree-growth model. Under this model, reconstruction is possible in linear time if one knows the direction of each edge in the graph - which edge endpoint is closer to the root of the tree - but becomes NP-hard if the directions are not known. For the latter case, we present a heuristic search algorithm to estimate the most likely topology of a rooted, three-dimensional tree from a single two-dimensional image. Experimental results on retinal vessel, plant root, and synthetic tree data sets show that our methodology is both accurate and efficient.

Retinal Artery-Vein Classification via Topology Estimation.

We propose a novel, graph-theoretic framework for distinguishing arteries from veins in a fundus image. We make use of the underlying vessel topology to better classify small and midsized vessels. We extend our previously proposed tree topology estimation framework by incorporating expert, domain-specific features to construct a simple, yet powerful global likelihood model. We efficiently maximize this model by iteratively exploring the space of possible solutions consistent with the projected vessels. We tested our method on four retinal datasets and achieved classification accuracies of 91.0%, 93.5%, 91.7%, and 90.9%, outperforming existing methods. Our results show the effectiveness of our approach, which is capable of analyzing the entire vasculature, including peripheral vessels, in wide field-of-view fundus photographs. This topology-based method is a potentially important tool for diagnosing diseases with retinal vascular manifestation.

Automated non-rigid registration and mosaicing for robust imaging of distinct retinal capillary beds using speckle variance optical coherence tomography.

Variance processing methods in Fourier domain optical coherence tomography (FD-OCT) have enabled depth-resolved visualization of the capillary beds in the retina due to the development of imaging systems capable of acquiring A-scan data in the 100 kHz regime. However, acquisition of volumetric variance data sets still requires several seconds of acquisition time, even with high speed systems. Movement of the subject during this time span is sufficient to corrupt visualization of the vasculature. We demonstrate a method to eliminate motion artifacts in speckle variance FD-OCT images of the retinal vasculature by creating a composite image from multiple volumes of data acquired sequentially. Slight changes in the orientation of the subject's eye relative to the optical system between acquired volumes may result in non-rigid warping of the image. Thus, we use a B-spline based free form deformation method to automatically register variance images from multiple volumes to obtain a motion-free composite image of the retinal vessels. We extend this technique to automatically mosaic individual vascular images into a widefield image of the retinal vasculature.

Exploratory Dijkstra forest based automatic vessel segmentation: applications in video indirect ophthalmoscopy (VIO).

We present a methodology for extracting the vascular network in the human retina using Dijkstra's shortest-path algorithm. Our method preserves vessel thickness, requires no manual intervention, and follows vessel branching naturally and efficiently. To test our method, we constructed a retinal video indirect ophthalmoscopy (VIO) image database from pediatric patients and compared the segmentations achieved by our method and state-of-the-art approaches to a human-drawn gold standard. Our experimental results show that our algorithm outperforms prior state-of-the-art methods, for both single VIO frames and automatically generated, large field-of-view enhanced mosaics. We have made the corresponding dataset and source code freely available online.

Enhanced video indirect ophthalmoscopy (VIO) via robust mosaicing.

Indirect ophthalmoscopy (IO) is the standard of care for evaluation of the neonatal retina. When recorded on video from a head-mounted camera, IO images have low quality and narrow Field of View (FOV). We present an image fusion methodology for converting a video IO recording into a single, high quality, wide-FOV mosaic that seamlessly blends the best frames in the video. To this end, we have developed fast and robust algorithms for automatic evaluation of video quality, artifact detection and removal, vessel mapping, registration, and multi-frame image fusion. Our experiments show the effectiveness of the proposed methods.

Real-time PCR Quantification and Mycotoxin Production of Fusarium graminearum in Wheat Inoculated with Isolates Collected from Potato, Sugar Beet, and Wheat.

ABSTRACT Fusarium graminearum causes Fusarium head blight (FHB) in small grains worldwide. Although primarily a pathogen of cereals, it also can infect noncereal crops such as potato and sugar beet in the United States. We used a real-time polymerase chain reaction (PCR) method based on intergenic sequences specific to the trichodiene synthase gene (Tri5) from F. graminearum. TaqMan probe and primers were designed and used to estimate DNA content of the pathogen (FgDNA) in the susceptible wheat cv. Grandin after inoculation with the 21 isolates of F. graminearum collected from potato, sugar beet, and wheat. The presence of nine mycotoxins was analyzed in the inoculated wheat heads by gas chromatography and mass spectrometry. All isolates contained the Tri5 gene and were virulent to cv. Grandin. Isolates of F. graminearum differed significantly in virulence (expressed as disease severity), FgDNA content, and mycotoxin accumulation. Potato isolates showed greater variability in producing different mycotoxins than sugar beet and wheat isolates. Correlation analysis showed a significant (P < 0.001) positive relationship between FgDNA content and FHB severity or deoxynivalenol (DON) production. Moreover, a significant (P < 0.001) positive correlation between FHB severity and DON content was observed. Our findings revealed that F. graminearum causing potato dry rot and sugar beet decay could be potential sources of inoculum for FHB epidemics in wheat. Real-time PCR assay provides sensitive and accurate quantification of F. graminearum in wheat and can be useful for monitoring the colonization of wheat grains by F. graminearum in controlled environments, and evaluating wheat germplasms for resistance to FHB.