SS-net: split and spatial attention network for vessel segmentation of retinal OCT angiography.

Optical coherence tomography angiography (OCTA) has been widely used in clinical fields because of its noninvasive, high-resolution qualities. Accurate vessel segmentation on OCTA images plays an important role in disease diagnosis. Most deep learning methods are based on region segmentation, which may lead to inaccurate segmentation for the extremely complex curve structure of retinal vessels. We propose a U-shaped network called SS-Net that is based on the attention mechanism to solve the problem of continuous segmentation of discontinuous vessels of a retinal OCTA. In this SS-Net, the improved SRes Block combines the residual structure and split attention to prevent the disappearance of gradient and gives greater weight to capillary features to form a backbone with an encoder and decoder architecture. In addition, spatial attention is applied to extract key information from spatial dimensions. To enhance the credibility, we use several indicators to evaluate the function of the SS-Net. In two datasets, the important indicators of accuracy reach 0.9258/0.9377, respectively, and a Dice coefficient is achieved, with an improvement of around 3% compared to state-of-the-art models in segmentation.

Controllable Synthesis of Zn-Doped α-Fe2O3 Nanowires for H2S Sensing.

One-dimensional Zn-doped α-Fe2O3 nanowires have been controllably synthesized by using the pure pyrite as the source of Fe element through a two-step synthesis route, including the preparation of Fe source solution by a leaching process and the thermal conversion of the precursor solution into α-Fe2O3 nanowires by the hydrothermal and calcination process. The microstructure, morphology, and surface composition of the obtained products were characterized by X-ray diffraction, scanning electron microscopy, transmission electron microscopy, and X-ray photoelectron spectroscopy. It was found that the formation process of α-Fe2O3 is significantly influenced by the introduction of Zn2+. The gas sensing measurements indicated that the sensor based on 1% Zn-doped α-Fe2O3 nanowires showed excellent H2S sensing properties at the optimum operating temperature of 175 °C. Notably, the sensor showed a low H2S detection limit of 50 ppb with a sensor response of 1.5. Such high-performance sensing would be ascribed to the one-dimensional structure and high specific surface area of the prepared 1% Zn-doped α-Fe2O3 nanowires, which can not only provide a large number of surface active sites for the adsorption and reaction of the oxygen and H2S molecules, but also facilitate the diffusion of the gas molecules towards the entire sensing materials.