Assessment of Nonalcoholic Fatty Liver Disease Symptoms and Gut-Liver Axis Status in Zebrafish after Exposure to Polystyrene Microplastics and Oxytetracycline, Alone and in Combination.

BACKGROUND: Environmental pollution may give rise to the incidence and progression of nonalcoholic fatty liver disease (NAFLD), the most common cause for chronic severe liver lesions. Although knowledge of NAFLD pathogenesis is particularly important for the development of effective prevention, the relationship between NAFLD occurrence and exposure to emerging pollutants, such as microplastics (MPs) and antibiotic residues, awaits assessment. OBJECTIVES: This study aimed to evaluate the toxicity of MPs and antibiotic residues related to NAFLD occurrence using the zebrafish model species. METHODS: Taking common polystyrene MPs and oxytetracycline (OTC) as representatives, typical NAFLD symptoms, including lipid accumulation, liver inflammation, and hepatic oxidative stress, were screened after 28-d exposure to environmentally realistic concentrations of MPs (0.69mg/L) and antibiotic residue (3.00µg/L). The impacts of MPs and OTC on gut health, the gut-liver axis, and hepatic lipid metabolism were also investigated to reveal potential affecting mechanisms underpinning the NAFLD symptoms observed. RESULTS: Compared with the control fish, zebrafish exposed to MPs and OTC exhibited significantly higher levels of lipid accumulation, triglycerides, and cholesterol contents, as well as inflammation, in conjunction with oxidative stress in their livers. In addition, a markedly smaller proportion of Proteobacteria and higher ratios of Firmicutes/Bacteroidetes were detected by microbiome analysis of gut contents in treated samples. After the exposures, the zebrafish also experienced intestinal oxidative injury and yielded significantly fewer numbers of goblet cells. Markedly higher levels of the intestinal bacteria-sourced endotoxin lipopolysaccharide (LPS) were also detected in serum. Animals treated with MPs and OTC exhibited higher expression levels of LPS binding receptor (LBP) and downstream inflammation-related genes while also exhibiting lower activity and gene expression of lipase. Furthermore, MP-OTC coexposure generally exerted more severe effects compared with single MP or OTC exposure. DISCUSSION: Our results suggested that exposure to MPs and OTC may disrupt the gut-liver axis and be associated with NAFLD occurrence. https://doi.org/10.1289/EHP11600.

Continual Learning for Blind Image Quality Assessment.

The explosive growth of image data facilitates the fast development of image processing and computer vision methods for emerging visual applications, meanwhile introducing novel distortions to processed images. This poses a grand challenge to existing blind image quality assessment (BIQA) models, which are weak at adapting to subpopulation shift. Recent work suggests training BIQA methods on the combination of all available human-rated IQA datasets. However, this type of approach is not scalable to a large number of datasets and is cumbersome to incorporate a newly created dataset as well. In this paper, we formulate continual learning for BIQA, where a model learns continually from a stream of IQA datasets, building on what was learned from previously seen data. We first identify five desiderata in the continual setting with three criteria to quantify the prediction accuracy, plasticity, and stability, respectively. We then propose a simple yet effective continual learning method for BIQA. Specifically, based on a shared backbone network, we add a prediction head for a new dataset and enforce a regularizer to allow all prediction heads to evolve with new data while being resistant to catastrophic forgetting of old data. We compute the overall quality score by a weighted summation of predictions from all heads. Extensive experiments demonstrate the promise of the proposed continual learning method in comparison to standard training techniques for BIQA, with and without experience replay. We made the code publicly available at https://github.com/zwx8981/BIQA_CL.

Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild.

Performance of blind image quality assessment (BIQA) models has been significantly boosted by end-to-end optimization of feature engineering and quality regression. Nevertheless, due to the distributional shift between images simulated in the laboratory and captured in the wild, models trained on databases with synthetic distortions remain particularly weak at handling realistic distortions (and vice versa). To confront the cross-distortion-scenario challenge, we develop a unified BIQA model and an approach of training it for both synthetic and realistic distortions. We first sample pairs of images from individual IQA databases, and compute a probability that the first image of each pair is of higher quality. We then employ the fidelity loss to optimize a deep neural network for BIQA over a large number of such image pairs. We also explicitly enforce a hinge constraint to regularize uncertainty estimation during optimization. Extensive experiments on six IQA databases show the promise of the learned method in blindly assessing image quality in the laboratory and wild. In addition, we demonstrate the universality of the proposed training strategy by using it to improve existing BIQA models.