Automated Brain Region Segmentation for Single Cell Resolution Histological Images Based on Markov Random Field.

The brain consists of massive regions with different functions and the precise delineation of brain region boundaries is important for brain region identification and atlas illustration. In this paper we propose a hierarchical Markov random field (MRF) model for brain region segmentation, where a MRF is applied to the downsampled low-resolution images and the result is used to initialize another MRF for the original high-resolution images. A fractional differential feature and a gray level co-occurrence matrix are extracted as the observed vector for the MRF and a new potential energy function, which can capture the spatial characteristic of brain regions, is proposed as well. A fuzzy entropy criterion is used to fine-tune the boundary from the hierarchical MRF model. We test the model both on synthetic images and real histological mouse brain images. The result suggests that the model can accurately identify target regions and even the whole mouse brain outline as a special case. An interesting observation is that the model cannot only segment regions with different cell density but also can segment regions with similar cell density and different cell morphology texture. Thus this model shows great potential for building the high-resolution 3D brain atlas.

[Spatial and Temporal Variations in Fertilizer Use Across Prefecture-level Cities in China from 2000 to 2015].

Chemical fertilizer plays an important role in increasing grain production in agricultural systems but overuse also brings a series of environmental problems, such as eutrophication of surface water, deterioration of soil structure, and the decline of agricultural carrying capacity. At present, research on chemical fertilizer use mainly focuses on utilization efficiency while studies on the spatial characteristics of its use are limited. It is also of great significance for the sustainable development of agriculture in China to fully understand the spatial changes in the use of chemical fertilizers. Based on data of pure chemical fertilizer use, sown area, and grain yield in prefecture-level cities from 2000 to 2015, spatial autocorrelation analysis, cold and hot spot analysis, nuclear density analysis, and standard deviation ellipse analysis were applied. The temporal and spatial variations in total fertilizer use and fertilizer load per unit area in 2000, 2005, 2010, and 2015 were compared. The results showed that:① The use of chemical fertilizer in China increased linearly from 2000 to 2015 but it has been in a relatively high agglomeration state in the region. The pure use of chemical fertilizer experienced a process of increasing regional aggregation from 2000 to 2005, weakening from 2005 to 2010, and increasing from 2010 to 2015. ② From a spatial perspective, the total amount of chemical fertilizer applied between 2000 and 2015 showed an increasing trend, shown by an increase in the number of prefecture-level cities and regions in which the use of chemical fertilizer exceeded the standard. The eastern regions of China, which have experienced rapid economic development, such as Guangdong Province and Fujian Province, are over the critical load of chemical fertilizer more and denser than other prefecture-level cities because the proportional reduction in sown area is greater than the increase in chemical fertilizer use. ③ The movement track of the grain production center in China from 2000 to 2015 was not consistent with the movement track of chemical fertilizer usage. Specifically, the center of grain production moves to the northeast, while the center of chemical fertilizer use moves to the west. This demonstrates that the status of commercial grain production in Northeast China is becoming more and more important, and that the use of chemical fertilizer in the western regions of China is gradually increasing. Here, there is a trend for exceeding the standard, which required further attention.