Reimerlarkin3943

To develop an artificial intelligence (AI)-based structure-function (SF) map relating retinal nerve fiber layer (RNFL) damage on spectral domain optical coherence tomography (SDOCT) to functional loss on standard automated perimetry (SAP).

The study included 26,499 pairs of SAP and SDOCT from 15,173 eyes of 8878 patients with glaucoma or suspected of having the disease extracted from the Duke Glaucoma Registry. The data set was randomly divided at the patient level in training and test sets. A convolutional neural network (CNN) was initially trained and validated to predict the 52 sensitivity threshold points of the 24-2 SAP from the 768 RNFL thickness points of the SDOCT peripapillary scan. Simulated localized RNFL defects of varied locations and depths were created by modifying the normal average peripapillary RNFL profile. The simulated profiles were then fed to the previously trained CNN, and the topographic SF relationships between structural defects and SAP functional losses were investigated.

The CNN predictions had an average correlation coefficient of 0.60 (

< 0.001) with the measured values from SAP and a mean absolute error of 4.25 dB. Simulated RNFL defects led to well-defined arcuate or paracentral visual field losses in the opposite hemifield, which varied according to the location and depth of the simulations.

A CNN was capable of predicting SAP sensitivity thresholds from SDOCT RNFL thickness measurements and generate an SF map from simulated defects.

AI-based SF map improves the understanding of how SDOCT losses translate into detectable SAP damage.

AI-based SF map improves the understanding of how SDOCT losses translate into detectable SAP damage.

To develop a deep neural network that detects the scleral spur in anterior segment optical coherence tomography (AS-OCT) images.

Participants in the Chinese American Eye Study, a population-based study in Los Angeles, California, underwent complete ocular examinations, including AS-OCT imaging with the Tomey CASIA SS-1000. One human expert grader provided reference labels of scleral spur locations in all images. A convolutional neural network (CNN)-based on the ResNet-18 architecture was developed to detect the scleral spur in each image. Performance of the CNN model was assessed by calculating prediction errors, defined as the difference between the Cartesian coordinates of reference and CNN-predicted scleral spur locations. Prediction errors were compared with intragrader variability in detecting scleral spur locations by the reference grader.

The CNN was developed using a training dataset of 17,704 images and tested using an independent dataset of 921 images. The mean absolute prediction errors of the CNN model were 49.27 ± 42.07 µm for X-coordinates and 47.73 ± 39.70 µm for Y-coordinates. The mean absolute intragrader variability was 52.31 ± 47.75 µm for X-coordinates and 45.88 ± 45.06 µm for Y-coordinates. Distributions of prediction errors for the CNN and intragrader variability for the reference grader were similar for X-coordinates (

= 0.609) and Y-coordinates (

= 0.378). The mean absolute prediction error of the CNN was 73.08 ± 52.06 µm and the mean absolute intragrader variability was 73.92 ± 60.72 µm.

A deep neural network can detect the scleral spur on AS-OCT images with performance similar to that of a human expert grader.

Deep learning methods that automate scleral spur detection can facilitate qualitative and quantitative assessments of AS-OCT images.

Deep learning methods that automate scleral spur detection can facilitate qualitative and quantitative assessments of AS-OCT images.

We applied a deep convolutional neural network model for automatic identification of ellipsoid zone (EZ) in spectral domain optical coherence tomography B-scans of retinitis pigmentosa (RP).

Midline B-scans having visible EZ from 220 patients with RP and 20 normal subjects were manually segmented for inner limiting membrane, inner nuclear layer, EZ, retinal pigment epithelium, and Bruch's membrane. A total of 2.87 million labeled image patches (33 × 33 pixels) extracted from 480 B-scans were used for training a convolutional neural network model implemented in MATLAB. B-scans from a separate group of 80 patients with RP were used for testing the model. A local connected area searching algorithm was developed to process the model output for reconstructing layer boundaries. Correlation and Bland-Altman analyses were conducted to compare EZ width measured by the model to those by manual segmentation.

The accuracy of the trained model to identify inner limiting membrane, inner nuclear layer, EZ, retinal pigment epithelium, and Bruch's membrane patches in the test dataset was 98%, 89%, 91%, 94%, and 96%, respectively. The EZ width measured by the model was highly correlated with that by two graders (r = 0.97;

< 0.0001). Bland-Altman analysis revealed a mean EZ width difference of 0.30 mm (coefficient of repeatability = 0.9 mm) between the model and the graders, comparable to the mean difference of 0.34mm (coefficient of repeatability = 0.8 mm) between two graders.

The results demonstrated the capability of a deep machine learning-based method for automatic identification of EZ in RP, suggesting that the method can be used to quantify structural deficits in RP for detecting disease progression and for evaluating treatment effect.

A deep machine learning model has the potential to replace humans for grading spectral domain optical coherence tomography images in RP.

A deep machine learning model has the potential to replace humans for grading spectral domain optical coherence tomography images in RP.SARS-CoV-2 has resulted in numerous cases of Coronavirus Disease 2019 (COVID-19) worldwide. In addition to fever and respiratory symptoms, digestive symptoms also are observed in some patients with COVID-19. Angiotensin-converting enzyme 2 (ACE2) was reported to be the receptor for SARS-CoV-2. The aim of this study was to comprehensively investigate the digestive symptoms that occur in COVID-19 patients, and the potential pathogenic route of the SARS-CoV-2 infection in digestive tract organs (from the oral cavity to the gastrointestinal tract). We investigated the digestive symptoms of 48 patients with COVID-19 and explored ACE2 expression in digestive tract and lung cancers, based on a series of bulk and single-cell RNA sequencing data obtained from public databases. We found that 25% (12/48) of the patients with COVID-19 suffered from digestive symptoms, among which pharyngalgia (7/48) was the most common manifestation, followed by diarrhea (3/48), anorexia (3/48), and nausea (1/48). The bulk tissue RNA sequencing analysis indicated that digestive tract organs had higher ACE2 expression levels compared to the lung, and the expression of ACE2 in the lung increased with age. Single-cell RNA-Seq results showed that the ACE2-positive-cell ratio in digestive tract organs was significantly higher compared to the lung. ACE2 expression was higher in tumor cells compared to normal control (NC) tissues. While in gastric tissues, ACE2 expression gradually increased from chronic gastritis to metaplasia, to early cancer. Our data might provide a theoretical basis for screening the SARS-CoV-2 susceptible population and for the clinical classification of treatment of patients with COVID-19.We aimed to investigate the exact effect of IL-17 on regulating neural stem cells (NSCs) stemness and adult neurogenesis in ischemic cortex after stroke, how Astragaloside IV(As-IV) regulated IL-17 expression and the underlying mechanism. Photochemical brain ischemia model was established and IL-17 protein expression was observed at different time after stroke in WT mice. At 3 days after stroke, when IL-17 expression peaked, IL-17 knock out (KO) mice were used to observe cell proliferation and neurogenesis in ischemic cortex. Then, As-IV was administered intravenously to assess cell apoptosis, proliferation, neurogenesis, and cognitive deficits by immunochemistry staining, western blots, and animal behavior tests in WT mice. Furthermore, IL-17 KO mice and As-IV were used simultaneously to evaluate the mechanism of cell apoptosis and proliferation after stroke in vivo. LY2880070 mw Besides, in vitro, As-IV and recombinant mouse IL-17A was administered, respectively, into NSCs culture, and then their diameters, viable cell proliferation and pathway relevant protein was assessed. The results showed knocking out IL-17 contributed to regulating PI3K/Akt pathway, promoting NSCs proliferation, and neurogenesis after ischemic stroke. Moreover, As-IV treatment helped inhibit neural apoptosis, promote the neurogenesis and eventually relieve mice anxiety after stroke. Unsurprisingly, IL-17 protein expression could be downregulated by As-IV in vivo and in vitro and they exerted antagonistic effect on neurogenesis by regulating Akt/GSK-3β pathway, with significant regulation for apoptosis. In conclusion, IL-17 exerts negative effect on promoting NSCs proliferation, neurogenesis and cognitive deficits after ischemic stroke, which could be reversed by As-IV.Neonatal maternal separation (NMS), as an early-life stress (ELS), is a risk factor to develop emotional disorders. However, the exact mechanisms remain to be defined. In the present study, we investigated the mechanisms involved in developing emotional disorders caused by NMS. First, we confirmed that NMS provoked impulsive behavior, orienting and nonselective attention-deficit, abnormal grooming, and depressive-like behaviors in adolescence. Excitatory amino acid carrier 1 (EAAC1) is an excitatory amino acid transporter expressed specifically by neurons and is the route for the neuronal uptake of glutamate/aspartate/cysteine. Compared with that in the normal control group, EAAC1 expression was remarkably reduced in the ventral hippocampus and cerebral cortex in the NMS group. Additionally, EAAC1 expression was reduced in parvalbumin-positive hippocampal GABAergic neurons in the NMS group. We also found that EAAC1-knockout (EAAC1-/-) mice exhibited impulsive-like, nonselective attention-deficit, and depressive-like behaviors compared with WT mice in adolescence, characteristics similar to those of the NMS behavior phenotype. link2 Taken together, our results revealed that ELS induced a reduction in EAAC1 expression, suggesting that reduced EAAC1 expression is involved in the pathophysiology of attention-deficit and depressive behaviors in adolescence caused by NMS.The majority of periprosthetic femoral fractures are treated surgically.Surgical treatment may be revision only, revision in combination with open reduction and internal fixation (ORIF), or ORIF only.The treatment decision is dependent on whether the stem is loose or not, but loose stems are not always identified, resulting in unsatisfactory treatments.This article presents an algorithmic approach to identifying loose stems around proximal femoral periprosthetic fractures, taking patient history, stem design, and plain radiographs into consideration. This approach may help identifying loose stems and increase the probability of effective treatments. link3 Cite this article EFORT Open Rev 2020;5449-456. DOI 10.1302/2058-5241.5.190086.