Recognizing and counting Dendrocephalus brasiliensis (Crustacea: Anostraca) cysts using deep learning.

The Dendrocephalus brasiliensis, a native species from South America, is a freshwater crustacean well explored in conservational and productive activities. Its main characteristics are its rusticity and resistance cysts production, in which the hatching requires a period of dehydration. Independent of the species utilization nature, it is essential to manipulate its cysts, such as the counting using microscopes. Manually counting is a difficult task, prone to errors, and that also very time-consuming. In this paper, we propose an automatized approach for the detection and counting of Dendrocephalus brasiliensis cysts from images captured by a digital microscope. For this purpose, we built the DBrasiliensis dataset, a repository with 246 images containing 5141 cysts of Dendrocephalus brasiliensis. Then, we trained two state-of-the-art object detection methods, YOLOv3 (You Only Look Once) and Faster R-CNN (Region-based Convolutional Neural Networks), on DBrasiliensis dataset in order to compare them under both cyst detection and counting tasks. Experiments showed evidence that YOLOv3 is superior to Faster R-CNN, achieving an accuracy rate of 83,74%, R2 of 0.88, RMSE (Root Mean Square Error) of 3.49, and MAE (Mean Absolute Error) of 2.24 on cyst detection and counting. Moreover, we showed that is possible to infer the number of cysts of a substrate, with known weight, by performing the automated counting of some of its samples. In conclusion, the proposed approach using YOLOv3 is adequate to detect and count Dendrocephalus brasiliensis cysts. The DBrasiliensis dataset can be accessed at: https://doi.org/10.6084/m9.figshare.13073240.

Effects of pH and nitrites on the toxicity of a cypermethrin-based pesticide to zebrafish embryos.

Physical and chemical water parameters have an important role on the toxicity of environmental contaminants by affecting their degradation, transformation and bioavailability. The objective of this study was to evaluate the effects of pH and nitrite variation on the toxicity of the cypermethrin based pesticide Barrage®. Zebrafish embryos (Danio rerio) were exposed to a combination of pH or nitrite and cypermethrin through the Barrage® formulation for 96 h and lethal and developmental endpoints assessed. Concerning mortality, pH seemed to increase Barrage® toxicity, while nitrite concentrations tested did not seem to change Barrage® lethality. At sublethal level, either for combinations involving pH or nitrites, results suggested some interactive effects of environmental and chemical factors, highlighting the need of further research. This work suggests that sublethal endpoints should be included in the assessment of combined effects of compounds given that they can provide important information not obtained through lethality.

Effects of pH and nitrites on the toxicity of a cypermetrin-based pesticide to shrimps.

The Pantanal (Brazil) is a wetland region characterized by seasonal flooding. Hydrological cycles influence the water physicochemical parameters, causing seasonal variations in pH and nitrites. Thus, the objective of this study was to evaluate the effects of varying pH and nitrite concentrations on the toxicity of the cypermethrin-based pesticide Barrage®, considering both lethal (mortality) and sublethal endpoints (growth and development). Larvae of the endemic shrimp Macrobrachium pantanalense and of the estuarine Amazonian congener Macrobrachium amazonicum were exposed to cypermethrin (through Barrage®) under several pH levels (6.5, 7.5 and 8.5) or nitrite concentrations (0.1, 0.2 and 0.4 mg/L). The pH had direct effects on all the tested endpoints for both species. For M. pantanalense, the lethal effects of the cypermethrin formulation were more pronounced at low pH (96-h LC50 = 0.004 µg/L at pH 6.5, and 0.146 µg/L at pH 8.5). For M. amazonicum, an opposite response was observed, with increased toxicity of the formulation at high pH (96-h LC50 = 0.110 µg/L at pH 6.5 and 0.044 µg/L at pH 8.5). Variations in pH also seemed to modify the sublethal effects of the formulation on larval growth and development of M. pantanalense. Nitrite concentrations affected larval growth of both species, modifying also the effects of the cypermethrin formulation on the larval development of M. amazonicum. This work shows the importance of considering abiotic factors for risk assessment either due to possible direct effects on the physiology of organisms and/or due to interactions with other stressors, particularly in fragile biomes such as Pantanal.

Cypermethrin-based formulation Barrage® induces histological changes in gills of the Pantanal endemic shrimp Macrobrachium pantanalense.

Pantanal shrimp Macrobrachium pantanalense was exposed for 96 h to the cypermethrin-based formulation Barrage®. Population-relevant endpoints (survival, swimming behavior) as well as histopathology of gills were analyzed. A 96 h-LC50 of 0.93 µg/L of cypermethrin was calculated while equilibrium disturbances were observed at 1.25 µg/L. Histological examination showed predominantly regressive changes in the gills of shrimp exposed to concentrations of 0.25 and 1.25 µg/L. Three levels of lesions were observed in the gills: I- Intercellular edema, epithelial lifting of the lamellae and lamellar fusion, fat vacuoles and hypertrophy of gill epithelial cells or mucous cells; II- nuclear changes, atrophy (reduction of volume and number) and hyperplasia of gill epithelia and III- necrosis. This study shows the high sensitivity of the shrimp M. pantanalense to the pesticide Barrage® highlighting the importance of monitoring agrochemicals residues in the Pantanal region (Brazil) and conduct risk evaluation studies to prevent deleterious effects on the aquatic communities of Pantanal.

Endemic shrimp Macrobrachium pantanalense as a test species to assess potential contamination by pesticides in Pantanal (Brazil).

Pantanal is a biome characterized by an extraordinary diversity and abundance of wildlife and houses several endemic species such as the freshwater shrimp Macrobrachium pantanalense. However, the increase in agriculture and husbandry activities in the region has contributed with residues of pesticides reaching aquatic systems. The main objective of this study is to assess the sensitivity of the endemic shrimp M. pantanalense compared with other freshwater species: the shrimp M. amazonicum, the crustacean Daphnia similis and the fish Danio rerio. The sensitivity of these organisms was assessed through acute exposure to copper and cypermethrin (through the formulation Barrage®, widely used in Pantanal). For copper the species sensitivity decreased in the following order: D. similis (48 h-EC50 0.051 mg/L) > M. pantanalense > D. rerio > M. amazonicum (48 h-LC50 26.34 mg/L). Copper caused reduced length of shrimps and zebrafish and reduced heartbeat of zebrafish embryos. For cypermethrin the species sensitivity decreased in the following order: M. pantanalense (96 h-LC50 0.05 µg/L) > M. amazonicum > D. similis > D. rerio (144 h-LC50 1680 µg/L). Major effects of cypermethrin included reduced length of shrimps and zebrafish, as well as early hatching and increased incidence of developmental deformities in zebrafish embryos. This study highlights the importance of using endemic species for risk evaluations in sensitive biomes such as Pantanal. Moreover, it emphasizes the importance of testing pesticides toxicity as commercial formulations. Furthermore, we suggest that the endemic shrimp species M. pantanalense can be successfully used as a test species in ecotoxicology.