Segmentation, feature extraction and classification of leukocytes leveraging neural networks, a comparative study.

The gold standard of leukocyte differentiation is a manual examination of blood smears, which is not only time and labor intensive but also susceptible to human error. As to automatic classification, there is still no comparative study of cell segmentation, feature extraction, and cell classification, where a variety of machine and deep learning models are compared with home-developed approaches. In this study, both traditional machine learning of K-means clustering versus deep learning of U-Net, U-Net + ResNet18, and U-Net + ResNet34 were used for cell segmentation, producing segmentation accuracies of 94.36% versus 99.17% for the dataset of CellaVision and 93.20% versus 98.75% for the dataset of BCCD, confirming that deep learning produces higher performance than traditional machine learning in leukocyte classification. In addition, a series of deep-learning approaches, including AlexNet, VGG16, and ResNet18, was adopted to conduct feature extraction and cell classification of leukocytes, producing classification accuracies of 91.31%, 97.83%, and 100% of CellaVision as well as 81.18%, 91.64% and 97.82% of BCCD, confirming the capability of the increased deepness of neural networks in leukocyte classification. As to the demonstrations, this study further conducted cell-type classification of ALL-IDB2 and PCB-HBC datasets, producing high accuracies of 100% and 98.49% among all literature, validating the deep learning model used in this study.

Toxic and non-toxic strains of Microcystis aeruginosa induce temperature dependent allelopathy toward growth and photosynthesis of Chlorella vulgaris.

Global warming was believed to accelerate the expansion of cyanobacterial blooms. However, the impact of changes due to the allelopathic effects of cyanobacterial blooms with or without algal toxin production on the ecophysiology of its coexisting phytoplankton species arising from global warming were unknown until recently. In this study, the allelopathic effects of toxic and non-toxic Microcystis aeruginosa strains on the growth of green alga Chlorella vulgaris and photosynthesis of the co-cultivations of C. vulgaris and toxic M. aeruginosa FACHB-905 or non-toxic M. aeruginosa FACHB-469 were investigated at different temperatures. The growth of C. vulgaris, co-cultured with the toxic or non-toxic M. aeruginosa strains, was promoted at 20°C but inhibited at temperatures ≥25°C. The inhibitory effects of the toxic and non-toxic M. aeruginosa strains on of the co-cultivations (C. vulgaris and non-toxic M. aeruginosa FACHB-469 or toxic M. aeruginosa FACHB-905) also linearly increased with elevated temperatures. Furthermore, toxic M. aeruginosa FACHB-905 induced more inhibition toward growth of C. vulgaris or Pmax and Rd of the mixtures than non-toxic M. aeruginosa FACHB-469. C. vulgaris dominated over non-toxic M. aeruginosa FACHB-469 but toxic M. aeruginosa FACHB-905 overcame C. vulgaris when they were co-cultured in mesocosms in water temperatures from 20 to 25°C. The results indicate that allelopathic effects of M. aeruginosa strains on C. vulgaris are both temperature- and species-dependent: it was stimulative for C. vulgaris at low temperatures such as 20°C, but inhibitory at high temperatures (≥25°C); the toxic strain was determined to be more harmful to C. vulgaris than the non-toxic one. This suggests that global warming may aggravate the ecological risk of cyanobacteria blooms, especially those with toxic species as the main contributors.