Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual requires medical technicians to observe blood smears through light microscopy, using their experience and expertise to discriminate and analyze different cells, which is time-consuming, labor-intensive and subjective. The traditional systems based on feature engineering often need to ensure successful segmentation and then manually extract certain quantitative and qualitative features for recognition but still remaining a limitation of poor robustness. The classification pipeline based on convolutional neural network is of automatic feature extraction and free of segmentation but hard to deal with multiple object recognition. In this paper, we take leukocyte recognition as object detection task and apply two remarkable object detection approaches, Single Shot Multibox Detector and An Incremental Improvement Version of You Only Look Once . To improve recognition performance, some key factors involving these object detection approaches are explored and the detection models are generated using the train set of 14,700 annotated images. Finally, we evaluate these detection models on test sets consisting of 1,120 annotated images and 7,868 labeled single object images corresponding to 11 categories of peripheral leukocytes, respectively. A best mean average precision of 93.10% and mean accuracy of 90.09% are achieved while the inference time is 53 ms per image on a NVIDIA GTX1080Ti GPU.

Currently, surfactants are widely distributed in the environment. As organic pollutants, their toxicities have drawn extensive attention. In this study, the effects of anionic [sodium dodecyl sulphate (SDS) ], cationic [dodecyl dimethyl benzyl ammonium chloride (1227)] and non-ionic [fatty alcohol polyoxyethylene ether (AEO) ] surfactants on zebrafish larval behaviour were evaluated. Five behavioural parameters were recorded using a larval rest/wake assay, including rest total, number of rest bouts, rest bouts length, total activity and waking activity. The results revealed that 1227 and AEO at 1 μg/mL were toxic to larval locomotor activity and that SDS had no significant effects. Moreover, we tested the toxicities of the three surfactants in developing zebrafish embryos. AEO exposure resulted in smaller head size, smaller eye size and shorter body length relative to SDS and 1227. All three surfactants incurred concentration-dependent responses. Furthermore, in situ hybridisation indicated that smaller head size may be associated with a decreased expression of krox20. The altered expression of ntl demonstrated that the developmental retardation stemmed from inhibited cell migration and growth. These findings provide references for ecotoxicological assessments of different types of surfactants, and play a warning role in the application of surfactants.

Quantitative OCT with dedicated image processing algorithms allows estimation of human crystalline lens volume, diameter, and equatorial lens position, as validated from ex vivo measurements, where entire lens images are available.

With advances in the development of various disciplines, there is a need to decipher bio-behavioural mechanisms via interdisciplinary means. Here, we present an interdisciplinary study of the role of silica nanoparticles (SiO2-NPs) in disturbing the neural behaviours of zebrafish and a possible physiological mechanism for this phenomenon. We used adult zebrafish as an animal model to evaluate the roles of size (15-nm and 50-nm) and concentration (300 μg/mL and 1000 μg/mL) in SiO2-NP neurotoxicity via behavioural and physiological analyses. With the aid of video tracking and data mining, we detected changes in behavioural phenotypes. We found that compared with 50-nm nanosilica, 15-nm SiO2-NPs produced greater significant changes in advanced cognitive neurobehavioural patterns (colour preference) and caused potentially Parkinson's disease-like behaviour. Analyses at the tissue, cell and molecular levels corroborated the behavioural results, demonstrating that nanosilica acted on the retina and dopaminergic (DA) neurons to change colour preference and to cause potentially Parkinson's disease-like behaviour.