Search

Background Manual microscopy remains a widely-used tool for malaria diagnosis and clinical studies, but it has inconsistent quality in the field due to variability in training and field practices. Automated diagnostic systems based on machine learning hold promise to improve quality and reproducibility of field microscopy. The World Health Organization (WHO) has designed a 55-slide set (WHO 55) for their External Competence Assessment of Malaria Microscopists (ECAMM) programme, which can also serve as a valuable benchmark for automated systems. The performance of a fully-automated malaria diagnostic system, EasyScan GO, on a WHO 55 slide set was evaluated. Methods The WHO 55 slide set is designed to evaluate microscopist competence in three areas of malaria diagnosis using Giemsa-stained blood films, focused on crucial field needs: malaria parasite detection, malaria parasite species identification (ID), and malaria parasite quantitation. The EasyScan GO is a fully-automated system that combines scanning of Giemsa-stained blood films with assessment algorithms to deliver malaria diagnoses. This system was tested on a WHO 55 slide set. Results The EasyScan GO achieved 94.3 % detection accuracy, 82.9 % species ID accuracy, and 50 % quantitation accuracy, corresponding to WHO microscopy competence Levels 1, 2, and 1, respectively. This is, to our knowledge, the best performance of a fully-automated system on a WHO 55 set. Conclusions EasyScan GO’s expert ratings in detection and quantitation on the WHO 55 slide set point towards its potential value in drug efficacy use-cases, as well as in some case management situations with less stringent species ID needs. Improved runtime may enable use in general case management settings.

BackgroundLight microscopy remains a standard method for the detection of malaria parasites in clinical cases but training of staff to a WHO level 2 or higher requires considerable time. Moreover, excessive workflow can rapidly lead to fatigue and impact performance, even for a highly skilled technician. An automated microscopy tool that can perform consistent, accurate diagnoses could be an effective aid in clinics with limited access to highly skilled microscopists, where the daily number of cases are excessively high for the number of available technicians or in multi-site studies where consistency between sites is essential. The EasyScan GO is an automated scanning microscope combined with machine learning software designed to detect malaria parasites in field-prepared Giemsa-stained blood films. This study evaluates the performance of the EasyScan GO to determine its ability to detect, quantify and identify the species of parasite present in Giemsa-stained blood films compared with expert light microscopy.MethodsTravelers returning to the UK and testing positive for malaria parasite infection were screened for eligibility and enrolled into the study. Surplus blood samples from enrolled patients were subsequently used to make Giemsa-stained thick and thin slide smears that were assessed by expert light microscopy and the EasyScan GO to determine parasite density and species. Blood samples were also assessed by real time PCR and nested PCR (Snounou) to confirm parasite density and species present and to resolve any discrepancy between manual microscopy and the EasyScan GO.ResultsWhen compared to light microscopy, the EasyScan GO exhibited a sensitivity of 90% (95% CI: 82–95%) and a specificity of 89% (95% CI: 86–90%). Of the 95 samples labelled positive by both light microscopy and the EasyScan GO, manual microscopy identified 83 as Plasmodium falciparum (P. falciparum) and 12 as non-P. falciparum. The EasyScan GO correctly reported P. falciparum for 82 out of the 83 P. falciparum samples and non-P. falciparum for 11 out of 12 non-P. falciparum samples. However, it failed to distinguish between non-P. falciparum species, reporting all non-P. falciparum samples as P. vivax. EasyScan GO calculated parasite densities were within +/-25% of the light microscopy densities for 33% of samples between 200 and 2000 p/µL, falling short of WHO level 1 (expert) manual microscopy competency (50% of samples should be within +/-25% of the true parasitaemia).ConclusionsThis study shows that the EasyScan GO can be proficient in detecting malaria parasites in Giemsa-stained blood films relative to expert manual light microscopy and can accurately distinguish between P. falciparum and non-P. falciparum species. Performance of the device at low parasite densities, distinguishing between non-P. falciparum species and accurate quantitation of parasitaemias require further development and evaluation. Nonetheless, the data shown here suggests that the EasyScan GO could provide assistance as a tool for malaria diagnosis in settings where work load is frequently higher than manageable or where access to expert microscopy is difficult.

Additional file 2:An example Field of View from the unreadable thin film, compared to an acceptable FoV.

Post-harvest losses to grain crops are conservatively estimated at 10-20% (ranging up to 40%) in many countries. In particular, grains must be properly dried to avoid spoilage, harmful mycotoxins from mold, and financial loss. Smallholder farmers can thus greatly benefit from a means to assess Moisture Content (MC) in their grain. We describe a two-step algorithm, with very low computational cost, that calculates MC with high accuracy, using Relative Humidity (RH) and Temperature (T) time-series. The time-series do not need to reach equilibrium state, enabling fast (12-minute) time-to-result. The algorithm first curve-fits the RH time-series to estimate asymptotic RH, in order to leverage the physics of the RH-T-MC equilibrium relationship. It then uses regression to estimate MC to within ±1% on ≥95% of samples over a wide range of ambient RH-T conditions, on both Lab and Field samples of 10 different grains.

Additional file 1.

Malaria is a life-threatening disease affecting millions. Microscopy-based assessment of thin blood films is a standard method to (i) determine malaria species and (ii) quantitate high-parasitemia infections. Full automation of malaria microscopy by machine learning (ML) is a challenging task because field-prepared slides vary widely in quality and presentation, and artifacts often heavily outnumber relatively rare parasites. In this work, we describe a complete, fully-automated framework for thin film malaria analysis that applies ML methods, including convolutional neural nets (CNNs), trained on a large and diverse dataset of field-prepared thin blood films. Quantitation and species identification results are close to sufficiently accurate for the concrete needs of drug resistance monitoring and clinical use-cases on field-prepared samples. We focus our methods and our performance metrics on the field use-case requirements. We discuss key issues and important metrics for the application of ML methods to malaria microscopy.

Additional file 2. Autoscope diagnostic performance vs. PCR for slides withâ >â 600 WBC (i.e., at Autoscopeâ s design specifications), separated by clinic.

The optical microscope remains a widely-used tool for diagnosis and quantitation of malaria. An automated system that can match the performance of well-trained technicians is motivated by a shortage of trained microscopists. We have developed a computer vision system that leverages deep learning to identify malaria parasites in micrographs of standard, field-prepared thick blood films. The prototype application diagnoses P. falciparum with sufficient accuracy to achieve competency level 1 in the World Health Organization external competency assessment, and quantitates with sufficient accuracy for use in drug resistance studies. A suite of new computer vision techniques-global white balance, adaptive nonlinear grayscale, and a novel augmentation scheme-underpin the system's state-of-the-art performance. We outline a rich, global training set; describe the algorithm in detail; argue for patient-level performance metrics for the evaluation of automated diagnosis methods; and provide results for P. falciparum.

Pneumonia is a common disease with both high morbidity and mortality. The diagnosis of pneumonia remains a clinical challenge, especially in low resource settings where prevalence is high, diagnostic devices are limited, and doctors are scarce. Lung ultrasound has been identified as a useful and low-cost tool for pneumonia diagnosis in many studies. In the present work, we first developed a convolutional neural network (CNN)-based deep learning algorithm to automatically identify four key features linked to lung conditions: pleural line, B-line, consolidation, and pleural effusion. The algorithm was trained using ultrasound data collected from over 150 pediatric and adult patients, with features annotated by expert sonographers. A single shot detection (SSD) framework was developed to detect those features in each video frame image. We then explored the accuracy of diagnosing pneumonia based on one or more lung ultrasound features, using CT as a gold standard. Our results indicate that deep learning algorithms can successfully detect abnormal lung features in ultrasound imagery, and those features can be used to diagnose pneumonia at a high sensitivity level. Computer-assisted ultrasound interpretation has the potential to place point of care, expert-level diagnostic accuracy in the hands of low-resource health care providers for pneumonia diagnosis.

The optical microscope is one of the most widely used tools for diagnosing infectious diseases in the developing world. Due to its reliance on trained microscopists, field microscopy often suffers from poor sensitivity, specificity, and reproducibility. The goal of this work, called the Autoscope, is a low-cost automated digital microscope coupled with a set of computer vision and classification algorithms, which can accurately diagnose of a variety of infectious diseases, targeting use-cases in the developing world. Our initial target is malaria, because of the high difficulty of the task and because manual microscopy is currently a central but highly imperfect tool for malaria work in the field. In addition to diagnosis, the algorithm performs species identification and quantitation of parasite load, parameters which are critical in many field applications but which are not effectively determined by rapid diagnostic tests (RDTs). We have built a hardware prototype which can scan approximately 0.1 μL of blood volume in a standard Giemsa-stained thick smear blood slide in approximately 20 minutes. We have also developed a comprehensive machine learning framework, leveraging computer vision and machine learning techniques including support vector machines (SVMs) and convolutional neural networks (CNNs). The Autoscope has undergone successful initial field testing for malaria diagnosis in Thailand.

L'harmonie essentielle entre la science et la religion, un enseignement de base de la foi baha'ie, est de grande importance pour l'evolution de la societe et l'emergence d'une civilisation mondiale. Toutefois, la science et la religion ont souvent ete mises en opposition, en particulier en ce qui a trait a l'evolution et a l'origine de l'homme. 'Abdu'l-Baha a formule des commentaires detailles sur l'evolution et l'origine de l'homme, fournissant l'exploration la plus approfondie de l'harmonie entre la science et la religion que l'on puisse trouver dans les enseignements baha'is. L'auteur passe en revue tous les enseignements d''Abdu'l-Baha concernant l'evolution, et il montre comment celui-ci reconcilie ces deux points de vue-l'evolution et la creation divine-que d'autres penseurs estimaient a tout jamais inconciliables.

We describe a framework for automatically identifying and visualizing the most differentiating attributes of each cluster in a clustered data set. A dissimilarity function measures the cluster-conditional distinguishing saliency of each attribute with respect to a reference realization of the same attribute. For each cluster, the N attributes that are most dissimilar are presented first to the human expert, along with the overall dissimilarity of the cluster. We discuss the computational benefits of the proposed framework, how it can be implemented with map-reduce, its application to the behavioral analysis of mobile phone users, and it broad applicability to diverse problem domains.

A new optoelectronic technology for the implementation of neural network architectures is being developed at Lincoln Laboratory. The new technology is based on a multiple-quantum- well (MQW) device called the monolithic optoelectronic transistor (MOET). MOET is a true optical transistor; it enables the switching of one optical signal with a much weaker one. The terminal characteristics are ideal for implementing a neuron: abrupt or sigmoidal thresholds, saturated ON and OFF states, and high fan-out. The device will be initially demonstrated for implementation of early visual processing networks. The baseline network is the CORT-X model, a multiple spatial-scale, feedforward network for boundary segmentation of noisy binary images. MOET implementation is possible with slight modifications to the CORT-X architecture. Simulations of the hardware implemented network are carried out and compared with the performance of the original model. As a function of input image carrier-to-noise ratio (CNR), performance is evaluated with respect to deviations from ideal response along two dimensions: (1) contrast-ratio and (2) nonuniformity. Assuming ideal hardware response, the modified CORT-X architecture performs better than the original model. Moderate contrast does not significantly degrade network performance, while nonuniformities as small as 10 degrade performance even for high CNR.© (1991) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

The representation of visual information in human striate cortex is of significance to machine vision. Invariance to certain geometrical transformations in the field-of-view may be provided by the computational anatomy of the visual cortex. For example, there is evidence that the retino-cortical mapping is closely approximated by a log-polar transform. When combined with the foveation response, log-polar mapping can provide a basis for translation, rotation, and scale-invariant perception. There is also evidence that the visual system is sensitive to the spatial frequency content of its input. Although a Fourier transform is physiologically implausible, some authors have suggested its use for invariant object recognition because the magnitude of the Fourier transform is shift invariant. The Fourier transform magnitude operation followed by log-polar mapping can also provide a basis for translation, rotation, and scale-invariant perception. Both of these image-transform (feature mapping) algorithms give mathematical invariance to translation, rotation, and dilation. For an automatic recognition system, however, the feature mapping module has to be robust to discretization error, noise, and possible obscuration. Robustness considerations led to the development of the bi- directional log-polar mapping (BPM) algorithm. The BPM algorithm overcomes the pixel- dropout problems associated with conventional approaches to log-polar mapping. The authors evaluate several feature mapping models, both biologically and mathematically inspired, for their effect on recognition performance when embedded in a neural-network-based, object- recognition system. The modular recognition system, consisting of image restoration, detection, segmentation, feature extraction, invariant mapping, and classification, is being developed to classify objects in laser radar range imagery. Synthetic laser radar range images of four vehicles rotated in the field-of-view, scaled to various ranges, and corrupted by increasing levels of sensor noise are used for this evaluation. This study indicates that feature mapping based on the bi-directional log-polar map provides translation, rotation, and scale- invariant recognition capabilities as well as robustness to noise and discretization.© (1991) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Simulations of the operation of a neural network architecture for boundary segmentation, an important stage of early visual processing, are presented. The network is based on the CORT-X model, a multiple spatial-scale, feedforward architecture for boundary segmentation of noisy binary images. The CORT-X architecture can be made to accommodate, with slight modifications, existing optoelectronic hardware capabilities. Network performance is evaluated with respect to deviations from ideal response along two dimensions: (1) contrast ratio and (2) nonuniformity. The effect of these parameters on network performance as a function of the input image signal-to-noise ratio (SNR) is evaluated. With ideal response (perfect uniformity and infinite contrast) the modified CORT-X architecture performs as well as the original model. Finite contrast does not significantly degrade network performance as long as there is some reasonable contrast. On the other hand, nonuniformities as small as 10% degrade performance even for high SNR.

A three-dimensional dynamic trap for confining a collisional neutral gas is described. The trap uses the interaction of the magnetic moments of the gas atoms with a time-dependent magnetic field. Collisions lead to the evaporative cooling of the trapped atoms and to the viscous heating of the gas, particularly at high densities. This magnetic trap may allow the attainment of Bose–Einstein condensation in spin-polarized atomic hydrogen gas.

A derivation from the weak‐gravity limit of general relativity is given of the basic equation for the flux function ψ(r,z) for general, steady, axisymmetric, relativistic, ideal magneto‐hydrodynamic flows aroud a black hole or a rotating magnetized star. One limit of this equation gives the Grad‐Shafranov equation, which describes the equilibrium of axisymmetric fusion plasmas. Another limit gives, except for an additional term, the ‘pulsar equation’ of Scharlemann, Wagoner, and Michel for relativistic plasma flows around an aligned, rotating, magnetized neutron star.

On propose une theorie generale pour les ecoulements magnetohydrodynamiques ideaux, a symetrie axiale, stationnaires, relativistes, autour d'un trou noir ou d'une etoile magnetisee en rotation

The tilt and shift stability of a spheromak plasma in the presence of a large orbit ion‐ring component is determined by evaluating the magnetic interaction of the plasma with the ion ring and the external coils. Neither the ion‐ring toroidal current nor the ring inverse aspect ratio is required to be small. The influence of conducting walls is considered to be negligible, as is appropriate for compression experiments. The plasma tilt and shift stability has been evaluated for a comprehensive set of numerically generated, self‐consistent, hybrid spheromak/ion‐ring equilibria. Stable equilibria are found over a considerable range of the parameters. The tilt stabilization of the plasma typically requires that more than about 25% of the total toroidal current be carried by the ion ring.