Artificial intelligence spots hidden signs of depression in students’ facial expressions
Peer-Reviewed Publication
Updates every hour. Last Updated: 20-Dec-2025 11:11 ET (20-Dec-2025 16:11 GMT/UTC)
Depression is often linked to changes in facial expressions. However, the link between mild depression, known as subthreshold depression, and changes in facial expressions remains unclear. Now, researchers have investigated whether subthreshold depression shows changes in facial expressions in Japanese young adults using artificial intelligence. The findings reveal distinct muscle movement patterns related to depressive symptoms which may help detect depression early, paving the way for timely and preventative mental health care.
The geometry of standard multi-well cell culture plates restricts oblique illumination angles, preventing matched illumination condition required for accurate tomographic reconstruction. To overcome this limitation, researchers developed the DF-FPDT technique, which leverages non-matched illumination and harnesses it as an intrinsic mechanism for dark-field-like contrast enhancement. By selectively updating high-frequency components using Phase Transfer Function (PTF) filtering, DF-FPDT effectively addresses low-frequency loss, enabling high-resolution, high-contrast live-cell imaging and dynamic screening, making DF-FPDT a powerful tool for biomedical research under realistic laboratory conditions.
Brain cancer remains one of the deadliest cancers, with limited treatment options and poor outcomes. In this review, researchers explore how nuclear receptors (NRs) influence brain tumor growth, invasion, and treatment resistance. The article details specific roles of different NRs and discusses how targeting them with drugs could improve therapy. These findings offer a promising direction for developing more precise, effective treatments against this highly aggressive and treatment-resistant cancer type.
Researchers from The Hong Kong University of Science and Technology and the Southern University of Science and Technology have developed a novel deep learning neural network, Electrode Net. By introducing signed distance fields and three-dimensional convolutional neural networks, this method can significantly accelerate electrode design while maintaining high accuracy. It is widely applicable to fuel cells, water electrolyzers, flow batteries, etc.