Spatial Analysis Fortin, Marie-Josée; Dale, Mark R. T.
04/2005
eBook
The spatial and temporal dimensions of ecological phenomena have always been inherent in the conceptual framework of ecology, but only recently have they been incorporated explicitly into ecological ...theory, sampling design, experimental design and models. Statistical techniques for spatial analysis of ecological data are burgeoning and many ecologists are unfamiliar with what is available and how the techniques should be used correctly. This book gives an overview of the wide range of spatial statistics available to analyse ecological data, and provides advice and guidance for graduate students and practising researchers who are either about to embark on spatial analysis in ecological studies or who have started but are unsure how to proceed. Only a basic understanding of statistics is assumed and many schematic illustrations are given to complement or replace mathematical technicalities, making the book accessible to ecologists wishing to enter this important and fast-growing field for the first time.
This commentary briefly reviews the background for the development of the horseradish peroxidase–diaminobenzidine tetrahydrochloride histochemical method originally described by Graham and Karnovsky ...in their citation classic, reprinted in full in this issue of Journal of Histochemistry & Cytochemistry. Some of the method’s subsequent applications, including its use as a macromolecular tracer for kidney glomerular permeability and use in immunoelectron microscopy and other immunoassays, are also discussed.
Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to ...specify rules explicitly. Application of these methods to medical imaging requires further assessment and validation.
To apply deep learning to create an algorithm for automated detection of diabetic retinopathy and diabetic macular edema in retinal fundus photographs.
A specific type of neural network optimized for image classification called a deep convolutional neural network was trained using a retrospective development data set of 128 175 retinal images, which were graded 3 to 7 times for diabetic retinopathy, diabetic macular edema, and image gradability by a panel of 54 US licensed ophthalmologists and ophthalmology senior residents between May and December 2015. The resultant algorithm was validated in January and February 2016 using 2 separate data sets, both graded by at least 7 US board-certified ophthalmologists with high intragrader consistency.
Deep learning-trained algorithm.
The sensitivity and specificity of the algorithm for detecting referable diabetic retinopathy (RDR), defined as moderate and worse diabetic retinopathy, referable diabetic macular edema, or both, were generated based on the reference standard of the majority decision of the ophthalmologist panel. The algorithm was evaluated at 2 operating points selected from the development set, one selected for high specificity and another for high sensitivity.
The EyePACS-1 data set consisted of 9963 images from 4997 patients (mean age, 54.4 years; 62.2% women; prevalence of RDR, 683/8878 fully gradable images 7.8%); the Messidor-2 data set had 1748 images from 874 patients (mean age, 57.6 years; 42.6% women; prevalence of RDR, 254/1745 fully gradable images 14.6%). For detecting RDR, the algorithm had an area under the receiver operating curve of 0.991 (95% CI, 0.988-0.993) for EyePACS-1 and 0.990 (95% CI, 0.986-0.995) for Messidor-2. Using the first operating cut point with high specificity, for EyePACS-1, the sensitivity was 90.3% (95% CI, 87.5%-92.7%) and the specificity was 98.1% (95% CI, 97.8%-98.5%). For Messidor-2, the sensitivity was 87.0% (95% CI, 81.1%-91.0%) and the specificity was 98.5% (95% CI, 97.7%-99.1%). Using a second operating point with high sensitivity in the development set, for EyePACS-1 the sensitivity was 97.5% and specificity was 93.4% and for Messidor-2 the sensitivity was 96.1% and specificity was 93.9%.
In this evaluation of retinal fundus photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy. Further research is necessary to determine the feasibility of applying this algorithm in the clinical setting and to determine whether use of the algorithm could lead to improved care and outcomes compared with current ophthalmologic assessment.
A number of different types of induced resistance have been defined based on differences in signalling pathways and spectra of effectiveness, including systemic acquired resistance and induced ...systemic resistance. Such resistance can be induced in plants by application of a variety of biotic and abiotic agents. The resulting resistance tends to be broad-spectrum and can be long-lasting, but is rarely complete, with most inducing agents reducing disease by between 20 and 85%. Since induced resistance is a host response, its expression under field conditions is likely to be influenced by a number of factors, including the environment, genotype, crop nutrition and the extent to which plants are already induced. Although research in this area has increased over the last few years, our understanding of the impact of these influences on the expression of induced resistance is still poor. There have also been a number of studies in recent years aimed at understanding of how best to use induced resistance in practical crop protection. However, such studies are relatively rare and further research geared towards incorporating induced resistance into disease management programmes, if appropriate, is required.
We present a significantly improved data‐driven global weather forecasting framework using a deep convolutional neural network (CNN) to forecast several basic atmospheric variables on a global grid. ...New developments in this framework include an off‐line volume‐conservative mapping to a cubed‐sphere grid, improvements to the CNN architecture and the minimization of the loss function over multiple steps in a prediction sequence. The cubed‐sphere remapping minimizes the distortion on the cube faces on which convolution operations are performed and provides natural boundary conditions for padding in the CNN. Our improved model produces weather forecasts that are indefinitely stable and produce realistic weather patterns at lead times of several weeks and longer. For short‐ to medium‐range forecasting, our model significantly outperforms persistence, climatology, and a coarse‐resolution dynamical numerical weather prediction (NWP) model. Unsurprisingly, our forecasts are worse than those from a high‐resolution state‐of‐the‐art operational NWP system. Our data‐driven model is able to learn to forecast complex surface temperature patterns from few input atmospheric state variables. On annual time scales, our model produces a realistic seasonal cycle driven solely by the prescribed variation in top‐of‐atmosphere solar forcing. Although it currently does not compete with operational weather forecasting models, our data‐driven CNN executes much faster than those models, suggesting that machine learning could prove to be a valuable tool for large‐ensemble forecasting.
Plain Language Summary
Recent work has begun to explore building global weather prediction models using only machine learning techniques trained on large amounts of atmospheric data. We develop a vastly improved machine learning algorithm capable of operating like traditional weather models and predicting several fundamental atmospheric variables, including near‐surface temperature. While our model does not yet compete with the state‐of‐the‐art in numerical weather prediction, it computes realistic forecasts that perform well and execute extremely quickly, offering a potential avenue for future developments in probabilistic weather forecasting.
Key Points
A convolutional neural net (CNN) is developed for global weather forecasts on the cubed sphere
Our CNN produces skillful global forecasts of key atmospheric variables at lead times up to 7 days
Our CNN computes stable 1‐year simulations of realistic atmospheric states in 3 seconds
Over the past few years, new-generation cell-based assays have demonstrated a robust association of autoantibodies to full-length human myelin oligodendrocyte glycoprotein (MOG-IgG) with (mostly ...recurrent) optic neuritis, myelitis and brainstem encephalitis, as well as with acute disseminated encephalomyelitis (ADEM)-like presentations. Most experts now consider MOG-IgG-associated encephalomyelitis (MOG-EM) a disease entity in its own right, immunopathogenetically distinct from both classic multiple sclerosis (MS) and aquaporin-4 (AQP4)-IgG-positive neuromyelitis optica spectrum disorders (NMOSD). Owing to a substantial overlap in clinicoradiological presentation, MOG-EM was often unwittingly misdiagnosed as MS in the past. Accordingly, increasing numbers of patients with suspected or established MS are currently being tested for MOG-IgG. However, screening of large unselected cohorts for rare biomarkers can significantly reduce the positive predictive value of a test. To lessen the hazard of overdiagnosing MOG-EM, which may lead to inappropriate treatment, more selective criteria for MOG-IgG testing are urgently needed. In this paper, we propose indications for MOG-IgG testing based on expert consensus. In addition, we give a list of conditions atypical for MOG-EM ("red flags") that should prompt physicians to challenge a positive MOG-IgG test result. Finally, we provide recommendations regarding assay methodology, specimen sampling and data interpretation.
Use adjudication to quantify errors in diabetic retinopathy (DR) grading based on individual graders and majority decision, and to train an improved automated algorithm for DR grading.
Retrospective ...analysis.
Retinal fundus images from DR screening programs.
Images were each graded by the algorithm, U.S. board-certified ophthalmologists, and retinal specialists. The adjudicated consensus of the retinal specialists served as the reference standard.
For agreement between different graders as well as between the graders and the algorithm, we measured the (quadratic-weighted) kappa score. To compare the performance of different forms of manual grading and the algorithm for various DR severity cutoffs (e.g., mild or worse DR, moderate or worse DR), we measured area under the curve (AUC), sensitivity, and specificity.
Of the 193 discrepancies between adjudication by retinal specialists and majority decision of ophthalmologists, the most common were missing microaneurysm (MAs) (36%), artifacts (20%), and misclassified hemorrhages (16%). Relative to the reference standard, the kappa for individual retinal specialists, ophthalmologists, and algorithm ranged from 0.82 to 0.91, 0.80 to 0.84, and 0.84, respectively. For moderate or worse DR, the majority decision of ophthalmologists had a sensitivity of 0.838 and specificity of 0.981. The algorithm had a sensitivity of 0.971, specificity of 0.923, and AUC of 0.986. For mild or worse DR, the algorithm had a sensitivity of 0.970, specificity of 0.917, and AUC of 0.986. By using a small number of adjudicated consensus grades as a tuning dataset and higher-resolution images as input, the algorithm improved in AUC from 0.934 to 0.986 for moderate or worse DR.
Adjudication reduces the errors in DR grading. A small set of adjudicated DR grades allows substantial improvements in algorithm performance. The resulting algorithm's performance was on par with that of individual U.S. Board-Certified ophthalmologists and retinal specialists.
The genomics era provides opportunities to assess the genetic overlap across phenotypes at the measured genotype level; however, current approaches require individual-level genome-wide association ...(GWA) single nucleotide polymorphism (SNP) genotype data in one or both of a pair of GWA samples. To facilitate the discovery of pleiotropic effects and examine genetic overlap across two phenotypes, I have developed a user-friendly web-based application called SECA to perform SNP effect concordance analysis using GWA summary results. The method is validated using publicly available summary data from the Psychiatric Genomics Consortium.
http://neurogenetics.qimrberghofer.edu.au/SECA.
Owing to the frequent incidence of blast-induced traumatic brain injury (bTBI) in recent military conflicts, there is an urgent need to develop effective therapies for bTBI-related pathologies. ...Blood-brain barrier (BBB) breakdown has been reported to occur after primary blast exposure, making restoration of BBB function and integrity a promising therapeutic target. We tested the hypothesis that treatment with dexamethasone (DEX) after primary blast injury potentiates recovery of an in vitro BBB model consisting of mouse brain endothelial cells (bEnd.3). DEX treatment resulted in complete recovery of transendothelial electrical resistance and hydraulic conductivity 1 day after injury, compared with 3 days for vehicle-treated injured cultures. Administration of RU486 (mifepristone) inhibited effects of DEX, confirming that barrier restoration was mediated by glucocorticoid receptor signaling. Potentiated recovery with DEX treatment was accompanied by stronger zonula occludens (ZO)-1 tight junction immunostaining and expression, suggesting that increased ZO-1 expression was a structural correlate to BBB recovery after blast. Interestingly, augmented ZO-1 protein expression was associated with specific upregulation of the α+ isoform but not the α− isoform. This is the first study to provide a mechanistic basis for potentiated functional recovery of an in vitro BBB model because of glucocorticoid treatment after primary blast injury.