Investigation of the usefulness of a bile duct biopsy and bile cytology using a hyperspectral camera and machine learning.

To improve the efficiency of pathological diagnoses, the development of automatic pathological diagnostic systems using artificial intelligence (AI) is progressing; however, problems include the low interpretability of AI technology and the need for large amounts of data. We herein report the usefulness of a general-purpose method that combines a hyperspectral camera with machine learning. As a result of analyzing bile duct biopsy and bile cytology specimens, which are especially difficult to determine as benign or malignant, using multiple machine learning models, both were able to identify benign or malignant cells with an accuracy rate of more than 80% (93.3% for bile duct biopsy specimens and 83.2% for bile cytology specimens). This method has the potential to contribute to the diagnosis and treatment of bile duct cancer and is expected to be widely applied and utilized in general pathological diagnoses.

Novel predator-induced phenotypic plasticity by hemoglobin and physiological changes in the brain of Xenopus tropicalis.

Organisms adapt to changes in their environment to survive. The emergence of predators is an example of environmental change, and organisms try to change their external phenotypic systems and physiological mechanisms to adapt to such changes. In general, prey exhibit different phenotypes to predators owing to historically long-term prey-predator interactions. However, when presented with a novel predator, the extent and rate of phenotypic plasticity in prey are largely unknown. Therefore, exploring the physiological adaptive response of organisms to novel predators is a crucial topic in physiology and evolutionary biology. Counterintuitively, Xenopus tropicalis tadpoles do not exhibit distinct external phenotypes when exposed to new predation threats. Accordingly, we examined the brains of X. tropicalis tadpoles to understand their response to novel predation pressure in the absence of apparent external morphological adaptations. Principal component analysis of fifteen external morphological parameters showed that each external morphological site varied nonlinearly with predator exposure time. However, the overall percentage change in principal components during the predation threat (24 h) was shown to significantly (p < 0.05) alter tadpole morphology compared with that during control or 5-day out treatment (5 days of exposure to predation followed by 5 days of no exposure). However, the adaptive strategy of the altered sites was unknown because the changes were not specific to a particular site but were rather nonlinear in various sites. Therefore, RNA-seq, metabolomic, Ingenuity Pathway Analysis, and Kyoto Encyclopedia of Genes and Genomes analyses were performed on the entire brain to investigate physiological changes in the brain, finding that glycolysis-driven ATP production was enhanced and ß-oxidation and the tricarboxylic acid cycle were downregulated in response to predation stress. Superoxide dismutase was upregulated after 6 h of exposure to new predation pressure, and radical production was reduced. Hemoglobin was also increased in the brain, forming oxyhemoglobin, which is known to scavenge hydroxyl radicals in the midbrain and hindbrain. These suggest that X. tropicalis tadpoles do not develop external morphological adaptations that are positively correlated with predation pressure, such as tail elongation, in response to novel predators; however, they improve their brain functionality when exposed to a novel predator.