Every year approximately 1.24 million people are diagnosed with blood cancer. While the rate increases each year, the availability of data for each kind of blood cancer remains scarce. It is essential to produce enough data for each blood cell type obtained from bone marrow aspirate smears to diagnose rare types of cancer. Generating data would help easy and quick diagnosis, which are the most critical factors in cancer. Generative adversarial networks (GAN) are the latest emerging framework for generating synthetic images and time-series data. This paper takes microscopic cell images, preprocesses them, and uses a hybrid GAN architecture to generate synthetic images of the cell types containing fewer data. We prepared a single dataset with expert intervention by combining images from three different sources. The final dataset consists of 12 cell types and has 33,177 microscopic cell images. We use the discriminator architecture of auxiliary classifier GAN (AC-GAN) and combine it with the Wasserstein GAN with gradient penalty model (WGAN-GP). We name our model as WGAN-GP-AC. The discriminator in our proposed model works to identify real and generated images and classify every image with a cell type. We provide experimental results demonstrating that our proposed model performs better than existing individual and hybrid GAN models in generating microscopic cell images. We use the generated synthetic data with classification models, and the results prove that the classification rate increases significantly. Classification models achieved 0.95 precision and 0.96 recall value for synthetic data, which is higher than the original, augmented, or combined datasets.

A stroke is a serious life-threatening condition and a leading cause of death and disability that happens when the blood vessels to part of the brain are blocked or burst. While major advances in the understanding of the ischemic cascade in stroke was made over several decades, limited therapeutic options and high mortality and disability have caused researchers to extend the focus toward peripheral changes beyond brain. The largest proportion of microbes in human body reside in the gut and the interaction between host and microbiota in health and disease is well known. Our study aimed to explore the gut microbiota in patients with stroke with comparison to control group. Fecal samples were obtained from 51 subjects: 25 stroke patients (18 hemorrhagic, 7 ischemic) and 26 healthy control subjects. The variable region V3–V4 of the 16S rRNA gene was sequenced using the Illumina MiSeq platform. PICRUSt2 was used for prediction of metagenomics functions. Our results show taxonomic dysbiosis in stroke patients in parallel with functional dysbiosis. Here, we show that stroke patients have (1) increased Parabacteroides and Escherichia_Shigella, but decreased Prevotella and Fecalibacterium; (2) higher transposase and peptide/nickel transport system substrate-binding protein, but lower RNA polymerase sigma-70 factor and methyl-accepting chemotaxis protein, which are suggestive of malnutrition. Nutrients are essential regulators of both host and microbial physiology and function as key coordinators of host–microbe interactions. Manipulation of nutrition is expected to alleviate gut dysbiosis and prognosis and improve disability and mortality in the management of stroke.

Shin Young Park, Woo Jin Kim. JOMES 2018;27:233-7. https://doi.org/10.7570/jomes.2018.27.4.233