Quality prediction of air-cured cigar tobacco leaf using region-based neural networks combined with visible and near-infrared hyperspectral imaging.

Visible and Near-infrared hyperspectral imaging (VNIR-HSI) combined with machine learning has shown its effectiveness in various detection applications. Specifically, the quality of cigar tobacco leaves undergoes subtle changes due to environmental differences during the air-curing phase. This study aims to evaluate the feasibility of deep learning methods in overcoming data limitations to develop a VNIR-HSI prediction model for the quality of cigar tobacco leaves at different air-curing levels.

Characterization of Microcystin-Induced Dualistic Toxic Effects on Primary Rat Hepatocytes.

Microcystins (MCs) comprise a group of widely characterized cyclic heptapeptides able to induce a series of liver injuries, including acute liver failure and primary liver cancer. Although the dualistic effects of MCs have been postulated, the specific action mode according to the exposure dosage of MCs remains unknown. In the present study, primarily cultured rat hepatocytes were used to systematically investigate hepatotoxic characteristics of MC-LR (one of the most abundant and toxic MCs variants).