CA-UNet Segmentation Makes a Good Ischemic Stroke Risk Prediction.

Stroke is still the World's second major factor of death, as well as the third major factor of death and disability. Ischemic stroke is a type of stroke, in which early detection and treatment are the keys to preventing ischemic strokes. However, due to the limitation of privacy protection and labeling difficulties, there are only a few studies on the intelligent automatic diagnosis of stroke or ischemic stroke, and the results are unsatisfactory. Therefore, we collect some data and propose a 3D carotid Computed Tomography Angiography (CTA) image segmentation model called CA-UNet for fully automated extraction of carotid arteries. We explore the number of down-sampling times applicable to carotid segmentation and design a multi-scale loss function to resolve the loss of detailed features during the process of down-sampling. Moreover, based on CA-Unet, we propose an ischemic stroke risk prediction model to predict the risk in patients using their 3D CTA images, electronic medical records, and medical history. We have validated the efficacy of our segmentation model and prediction model through comparison tests. Our method can provide reliable diagnoses and results that benefit patients and medical professionals.

Effects of Florfenicol on nirS-Type Denitrification Community Structure of Sediments in an Aquatic Microcosm Model.

Florfenicol is one of the most widely used antibiotics in aquaculture and veterinary clinics because of its low side effects and strong bactericidal effect. A total of 45~60% of florfenicol is not absorbed by the animal body and accumulates in the aquatic environment through a variety of pathways, which affects denitrification. Indoor aquatic microcosm models were constructed and sediment samples were collected at different florfenicol concentrations (0.1, 1, 10, and 100 mg/L) on days 0, 7, 30, and 60 to extract the microbial genome DNA and determine the water properties. qPCR and amplicon sequencing were used to study the dynamic changes in the nirS gene and nirS-type denitrification community structure, diversity, and abundance, respectively. The results showed that high florfenicol stress influenced the sediment's physicochemical properties, reducing conductivity, alkaline dissolved nitrogen, and organic matter content. In addition, the abundance of nirS, a functional denitrification gene, increased obviously with increased florfenicol concentrations but decreased the diversity of nirS-type denitrification microorganisms. Proteobacteria was the dominant denitrifying phylum in the sediment. Our study provides a scientific basis for the rational use of florfenicol in aquaculture to maintain a healthy and stable microecological environment and also provides a preliminary understanding of the response characteristics of water denitrifying microorganisms to florfenicol exposure.