Severity of Disorganization of Retinal Layers and Visual Function Impairment in Diabetic Retinopathy.

PURPOSE: To evaluate best-corrected visual acuity (BCVA), retina sensitivity (RS), and fixation impairment by microperimetry (MP) due to the presence and severity of disorganization of retinal inner and outer layers (DRIL/DROL) and ischemia in OCT/OCT angiography (OCTA) in diabetic retinopathy (DR). DESIGN: Retrospective case-control study. SUBJECTS: Seventy-six eyes (65 patients) with DR were analyzed. Major exclusion criteria were: center-involving diabetic macular edema (DME), significant media opacity, nondiabetic macular pathology, and active proliferative DR. Patients with DRIL and DROL within central 3 mm were enrolled as cases. Patients with DR and no retina disorganization were considered as controls. METHODS: A detailed grading of MP and OCT/OCTA images using Image J software, and specific Image Manipulation Program was applied to colocalize the presence of retina disorganization and RS. Best-corrected visual acuity and RS were correlated with the disorganization of retina layers' characteristics and grading (grade 1-DRIL; grade 2-DROL; grade 3-DROL plus, with involvement of the ellipsoid zone). The same procedure of colocalization was applied to the vascular layers on OCTA using MATLAB. MAIN OUTCOME MEASURES: Correlation between BCVA and MP parameters with disorganization of retina layers grading and OCTA parameters. RESULTS: Best-corrected visual acuity, mean RS within 1 mm and central 3 mm (overall RS [oRS]), perfusion density, vessel density, and geometric perfusion deficit in intermediate and deep capillary plexuses were lower in cases versus controls (P < 0.001). Mean RS within 1 mm (21.4 decibels [dB] ± 2.4 vs. 13.8 dB ± 5.4, P = 0.002), oRS (22.0 dB ± 2.1 vs. 14.4 dB ± 4.6, P < 0.001), and BCVA (76.1 ± 7.4 vs. 61.2 ± 20.4 ETDRS letters; P = 0.02), had a significant decrease from grade 1 to grade 3 retina disorganization. Choriocapillaris flow voids (CC-FVs) increased from grade 1 to grade 3 (DROL plus) (P = 0.004). Overall retina sensitivity and CC-FV were identified as significant predictors of retina disorganization grade with an adjusted coefficient of determination, R2 = 0.45. Cases had more dense scotomas (P = 0.03) than controls with a positive correlation between the worsening of fixation stability and the severity of DRIL/DROL (P = 0.04). CONCLUSIONS: Microperimetry and BCVA documented a reduction in visual function in patients with DR and disorganization of retina layers at different grades, with greater functional impairment when outer retina layers and photoreceptors are involved. The severity of retina disorganization and the presence of ischemia could serve as a potential biomarker of functional impairment. FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Acceleration of Hyperspectral Skin Cancer Image Classification through Parallel Machine-Learning Methods.

Hyperspectral imaging (HSI) has become a very compelling technique in different scientific areas; indeed, many researchers use it in the fields of remote sensing, agriculture, forensics, and medicine. In the latter, HSI plays a crucial role as a diagnostic support and for surgery guidance. However, the computational effort in elaborating hyperspectral data is not trivial. Furthermore, the demand for detecting diseases in a short time is undeniable. In this paper, we take up this challenge by parallelizing three machine-learning methods among those that are the most intensively used: Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGB) algorithms using the Compute Unified Device Architecture (CUDA) to accelerate the classification of hyperspectral skin cancer images. They all showed a good performance in HS image classification, in particular when the size of the dataset is limited, as demonstrated in the literature. We illustrate the parallelization techniques adopted for each approach, highlighting the suitability of Graphical Processing Units (GPUs) to this aim. Experimental results show that parallel SVM and XGB algorithms significantly improve the classification times in comparison with their serial counterparts.

Ambient assisted living for frail people through human activity recognition: state-of-the-art, challenges and future directions.

Ambient Assisted Living is a concept that focuses on using technology to support and enhance the quality of life and well-being of frail or elderly individuals in both indoor and outdoor environments. It aims at empowering individuals to maintain their independence and autonomy while ensuring their safety and providing assistance when needed. Human Activity Recognition is widely regarded as the most popular methodology within the field of Ambient Assisted Living. Human Activity Recognition involves automatically detecting and classifying the activities performed by individuals using sensor-based systems. Researchers have employed various methodologies, utilizing wearable and/or non-wearable sensors, and employing algorithms ranging from simple threshold-based techniques to more advanced deep learning approaches. In this review, literature from the past decade is critically examined, specifically exploring the technological aspects of Human Activity Recognition in Ambient Assisted Living. An exhaustive analysis of the methodologies adopted, highlighting their strengths and weaknesses is provided. Finally, challenges encountered in the field of Human Activity Recognition for Ambient Assisted Living are thoroughly discussed. These challenges encompass issues related to data collection, model training, real-time performance, generalizability, and user acceptance. Miniaturization, unobtrusiveness, energy harvesting and communication efficiency will be the crucial factors for new wearable solutions.

Corrigendum: Reconstruction and Simulation of a Scaffold Model of the Cerebellar Network.

[This corrects the article DOI: 10.3389/fninf.2019.00037.].

Reconstruction and Simulation of a Scaffold Model of the Cerebellar Network.

Reconstructing neuronal microcircuits through computational models is fundamental to simulate local neuronal dynamics. Here a scaffold model of the cerebellum has been developed in order to flexibly place neurons in space, connect them synaptically, and endow neurons and synapses with biologically-grounded mechanisms. The scaffold model can keep neuronal morphology separated from network connectivity, which can in turn be obtained from convergence/divergence ratios and axonal/dendritic field 3D geometries. We first tested the scaffold on the cerebellar microcircuit, which presents a challenging 3D organization, at the same time providing appropriate datasets to validate emerging network behaviors. The scaffold was designed to integrate the cerebellar cortex with deep cerebellar nuclei (DCN), including different neuronal types: Golgi cells, granule cells, Purkinje cells, stellate cells, basket cells, and DCN principal cells. Mossy fiber inputs were conveyed through the glomeruli. An anisotropic volume (0.077 mm3) of mouse cerebellum was reconstructed, in which point-neuron models were tuned toward the specific discharge properties of neurons and were connected by exponentially decaying excitatory and inhibitory synapses. Simulations using both pyNEST and pyNEURON showed the emergence of organized spatio-temporal patterns of neuronal activity similar to those revealed experimentally in response to background noise and burst stimulation of mossy fiber bundles. Different configurations of granular and molecular layer connectivity consistently modified neuronal activation patterns, revealing the importance of structural constraints for cerebellar network functioning. The scaffold provided thus an effective workflow accounting for the complex architecture of the cerebellar network. In principle, the scaffold can incorporate cellular mechanisms at multiple levels of detail and be tuned to test different structural and functional hypotheses. A future implementation using detailed 3D multi-compartment neuron models and dynamic synapses will be needed to investigate the impact of single neuron properties on network computation.