Segmentation of pancreas is important for medical image analysis, yet it faces great challenges of class imbalance, background distractions and non-rigid geometrical features. To address these difficulties, we introduce a Deep Q Network(DQN) driven approach with deformable U-Net to accurately segment the pancreas by explicitly interacting with contextual information and extract anisotropic features from pancreas. The DQN based model learns a context-adaptive localization policy to produce a visually tightened and precise localization bounding box of the pancreas. Furthermore, deformable U-Net captures geometryaware information of pancreas by learning geometrically deformable filters for feature extraction. Experiments on NIH dataset validate the effectiveness of the proposed framework in pancreas segmentation.

No abstract

No abstract

No abstract

Contamination of industry-derived antimony (Sb) is currently of great concern. This study was conducted to identify the source of Sb together with other potential toxic elements (PTEs) in a typical industrial area in China and emphasize the contribution of Sb to ecological risk in the local aquatic environment. By investigating the distribution of nine PTEs in surface water in Wujiang County in dry and wet seasons, this study revealed that textile wastewater was the main source of Sb. The distribution of Sb (0.48~21.4 μg/L) showed the least seasonal variation among the nine elements. Factor analysis revealed that the factor that controlled Sb distribution is unique. In general, Sb was more concentrated in the southeastern part of the study area where there was a large number of textile industries, and was affected by the specific conductivity and total dissolved solids in water (p < 0.01). Sb concentration in 35.71% of samples collected from the drainage outlet exceeded the standard limit of 10 μg/L. Results from three pollution assessment methods suggested that >5% of the sampling sites were slightly too heavily polluted and Sb contributed the most. Therefore, it is necessary to strengthen the administrative supervision of local textile enterprises and elevate the local standard of textile wastewater emission.