Publications by authors named "Jikai Yu"
Exploring multi-instance learning in whole slide imaging: Current and future perspectives.
Pathol Res Pract
July 2025
Whole slide images (WSI), due to their gigabyte-scale size and ultra-high resolution, play a significant role in diagnostic pathology. However, the enormous data size makes it difficult to directly input these images into image processing units (GPU) for computation, limiting the development of automated screening and diagnostic algorithms. As an effective computational framework, multi-instance learning (MIL) has provided strong support in addressing this challenge.
View Article and Find Full Text PDFBackground: This study aimed to investigate prefrontal function in patients with generalized anxiety disorder (GAD), major depressive disorder (MDD), and the comorbidity of MDD and GAD (CMG), using the fNIRS-VFT task. And to assess the reliability of functional near-infrared spectroscopy (fNIRS) devices as a clinical aid for diagnostic tools when performing cognitive tasks by building a deep neural network.
Methods: Including 75 patients with GAD, 75 patients with MDD, 71 patients with CMG, and 75 healthy controls (HC).
Article Synopsis
- The study focuses on the development of new thermally activated delayed fluorescence (TADF) materials that enhance reverse intersystem crossing (RISC) to prevent triplet-triplet annihilation.
- Five derivative molecules with different bridging atoms/groups were analyzed using computational modeling to understand their excited state behaviors in toluene.
- A unique RISC mechanism was observed, predominantly involving T states instead of the usual transitions, which has implications for designing more efficient TADF compounds.