Perimetry (visual field testing) quantifies a patient’s retinal sensitivity to light and clarifies a deviation from normal retinal sensitivity. Visual field tests generally require high patient concentration, which can be exhausted. We constructed a framework for deep reinforcement learning to train ViFT (Visual Field Transformer), which controls all processes of visual field testing. ViFT achieves the same or higher accuracy than the state-of-the-art strategies, with less than half the test time of the state-of-the-art strategies.

An international research group led by The University of Osaka has developed scODIN, a novel computational tool to classify cell types from single-cell RNA sequencing (scRNA-seq) data. Existing methods struggle to balance speed and accuracy, often misclassifying rare or transitional cells. scODIN overcomes this limitation by combining a hierarchical classification system (Tier system) with k-nearest neighbor inference. This approach allows for the rapid and accurate classification of large datasets, processing 650,000 cells in just six minutes. The tool's improved accuracy stems from its ability to identify cells at varying levels of detail, recognize intermediate phenotypes through double labeling, and recover cells affected by dropout events. scODIN promises to accelerate biomedical discoveries by enabling more precise and efficient analysis of complex biological processes and disease mechanisms.

A research team led by Director C. Justin LEE of the Center for Cognition and Sociality at the Institute for Basic Science (IBS), in collaboration with Professor HA Yoon of Yonsei University College of Medicine, identified that the inhibitory neurotransmitter GABA, produced by astrocytes in the spinal cord through the enzyme monoamine oxidase B (MAOB), is the key factor that blocks recovery after spinal cord injury. Furthermore, they demonstrated the therapeutic potential of targeting this pathway by showing that MAOB inhibition promotes spinal cord repair.