This study developed an automated image analysis framework for diagnosing hair disorders using trichoscopic images, reporting a Random Forest classifier as having an 86.67% accuracy in distinguishing between different scalp pathologies based on quantitative image features.
April 2026 in “Scientific Reports” In this study, the proposed MSF-VMDNet, combining dual encoder networks with a multi-frequency domain mechanism, significantly outperformed existing methods in segmenting skin cancer tissues from histological slide images, achieving high accuracy with an MIoU of 95.37% and a Dice coefficient of 95.11%.
November 2024 in “Image Analysis & Stereology” This study introduced a novel, weakly supervised method for segmenting hair in Scanning Electron Microscope images using simple image-level annotations, achieving over 30% improvement in mean Hausdorff Distance compared to Unet and SAM, while enhancing interpretability and refinement.
January 2013 in “Japan labor review” This study quantified relationships among various occupations in Japan, enabling comparisons with vocational aptitude test results using new numerical criteria developed from analysis of over three million survey panels.
4 citations
,
December 2021 in “Electronics” In this study, a novel GAN-based image translation method focusing on regions of interest showed improved predictive performance for post-hair transplant images compared to existing methods, using an ensemble approach to enhance robustness and detection accuracy.