Physiological Characteristics of Nitzschia hantzschia in Response to Nitrobenzene Stress

This study was conducted to investigate the effects of different mass concentrations of nitrobeneze on the growth, soluble sugar content, soluble protein content, chlorophyll a content and algal cell conductivity of Nitzschia hantzschia. The results showed that as the concentration of nitrobenzene increased, the growth of N. hantzschia was inhibited, and the algal culture liquids gradually changed from dark yellow to light yellow after 5 d of treatment;the soluble sugar content increased after 2 d;and the soluble protein content of the 100 mg/L nitrobenzene treatment group was 89.1% of the control group on day 1, which was the lowest value, and then showed a gradual upward trend. The low-mass concentration of nitrobenzene promoted the chlorophyll a content of algal cells, the medium and high mass concentrations had an inhibitory effect, and the chlorophyll a content of the 50 mg/L treatment gradually recovered after 3 d. The electrical conductivity of algal cells gradually increased with the increase of the mass concentration of nitrobenzene. The electrical conductivity gradually recovered after 3 d of the low mass concentration treatment, while the high mass concentration harmed the algae cells, causing N. hantzschia to gradually die.

Combining Residual Attention Mechanisms and Generative Adversarial Networks for Hippocampus Segmentation

This research discussed a deep learning method based on an improved generative adversarial network to segment the hippocampus.Different convolutional configurations were proposed to capture information obtained by a segmentation network.In addition,a generative adversarial network based on Pixel2Pixel was proposed.The generator was a codec structure combining a residual network and an attention mechanism to capture detailed information.The discriminator used a convolutional neural network to discriminate the segmentation results of the generated model and that of the expert.Through the continuously transmitted losses of the generator and discriminator,the generator reached the optimal state of hippocampus segmentation.T1-weighted magnetic resonance imaging scans and related hippocampus labels of 130 healthy subjects from the Alzheimer’s disease Neuroimaging Initiative dataset were used as training and test data;similarity coefficient,sensitivity,and positive predictive value were used as evaluation indicators.Results showed that the network model could achieve an efficient automatic segmentation of the hippocampus and thus has practical relevance for the correct diagnosis of diseases,such as Alzheimer’s disease.