Development and validation of CNN-MLP models for predicting anti-VEGF therapy outcomes in diabetic macular edema.

Diabetic macular edema (DME) is a common complication of diabetes that can lead to vision loss, and anti-vascular endothelial growth factor (anti-VEGF) therapy is the standard of care for DME, but the treatment outcomes vary widely among patients. This study collected optical coherence tomography (OCT) images and clinical data from DME patients who received anti-VEGF treatment to develop and validate deep learning (DL) models for predicting the anti-VEGF outcomes in DME patients based on convolutional neural network (CNN) and multilayer perceptron (MLP) combined architecture by using multimodal data. An Xception-MLP architecture was utilized to predict best-corrected visual acuity (BCVA), central subfield thickness (CST), cube volume (CV), and cube average thickness (CAT).

Cellulose nanofibers enabled strong and flexible plant-derived thermoplastic polyester elastomer foams for high-performance thermally insulating applications.

Flexible thermal insulation materials have garnered significant attention owing to the proliferation of flexible electronic devices and their diverse application environments. Plant-derived thermoplastic polyester elastomer (TPEE) foams emerge as promising candidates in the field of flexible thermal insulation. However, inevitable shrinkage behavior of TPEE foams would result in reduced porosity and inferior thermal insulation performance.

High performance plant-derived thermoplastic polyester elastomer foams achieved by manipulating charging order of mixed blowing agents.

Plant-derived thermoplastic polyester elastomer (TPEE) is an environment friendly polymer known for its exceptional tear strength and mechanical properties, whose monomers are generated from crops. To prepare high-performance TPEE foams is still challenging due to the intrinsic shrinkage behavior. Herein, two microcellular foaming routes with different charging orders of mixed blowing agents, namely "CO firstly charging process (CO-F-process)" and "N firstly charging process (N-F-process)", were developed to elucidate the effects of mixed blowing agents on foaming behavior.

Extraordinarily Time- and Memory-Efficient Large-Scale Canonical Correlation Analysis in Fourier Domain: From Shallow to Deep.

Canonical correlation analysis (CCA) is a correlation analysis technique that is widely used in statistics and the machine-learning community. However, the high complexity involved in the training process lays a heavy burden on the processing units and memory system, making CCA nearly impractical in large-scale data. To overcome this issue, a novel CCA method that tries to carry out analysis on the dataset in the Fourier domain is developed in this article.

Absolute measurement approach for crystal growth height based on a polarization-synchronized phase-shifting interferometer.

The quality of the solid deuterium-deuterium (D-D) layer in the inertial confinement fusion (ICF) target plays a vital role in the success of fusion experiments. A good understanding of how the quality is affected by the unstable growth of D-D crystal is required. This article provides an approach of measuring D-D layer absolute height in real time by combining monitoring algorithms and a synchronous phase-shifting interferometer.

Tobacco Use and Exposure to Second-Hand Smoke among Urban Residents: A Community-Based Investigation.

Objectives: In 2005, China acceded to the World Health Organization Framework Convention on Tobacco Control (WHO FCTC), the foundation for the global fight against tobacco. Certain cities in China have established local regulations to control tobacco use ahead of national policy; however, without the enforcement of statutory law, some of these regulations are merely lip service. The aim of the study was to assess the effects of city policy on smoking prevalence and on second-hand smoke (SHS) exposure status among non-smokers in Changchun City.