April 2023 in “Journal of Investigative Dermatology” This study reports that improvements to the EczemaNet pipeline, incorporating pixel-level segmentation and data augmentation, enhanced the reliability and interpretability of assessing atopic dermatitis severity from digital images.
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.
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%.
February 2023 in “International Journal of Multimedia Computing” In this study, improved hidden Markov algorithms based on Bayesian methods enhanced the resolution and segmentation accuracy of low-dose CT images significantly more than naive Bayesian methods.
1 citations
,
December 2022 in “JAMA Dermatology” This study found that the HairComb algorithm achieved high accuracy in quantifying percentage hair loss across various types of alopecia, suggesting its potential for standardized automated assessments.
