Label Free
Label-free techniques aim to extract information from images and data without relying on artificial labels or markers, leveraging inherent properties like autofluorescence or phase shifts. Current research focuses on developing deep learning models, including convolutional neural networks, transformers, and diffusion models, to analyze label-free data for tasks such as image segmentation, classification, and quantitative phase imaging. These methods offer significant advantages in various fields, including pathology, microbiology, and biomedical imaging, by reducing costs, increasing efficiency, and enabling analyses previously hindered by labeling limitations. The resulting advancements promise faster, cheaper, and more accessible diagnostic and analytical tools.
Papers
Diagnosis of Multiple Fundus Disorders Amidst a Scarcity of Medical Experts Via Self-supervised Machine Learning
Yong Liu, Mengtian Kang, Shuo Gao, Chi Zhang, Ying Liu, Shiming Li, Yue Qi, Arokia Nathan, Wenjun Xu, Chenyu Tang, Edoardo Occhipinti, Mayinuer Yusufu, Ningli Wang, Weiling Bai, Luigi Occhipinti
SSVT: Self-Supervised Vision Transformer For Eye Disease Diagnosis Based On Fundus Images
Jiaqi Wang, Mengtian Kang, Yong Liu, Chi Zhang, Ying Liu, Shiming Li, Yue Qi, Wenjun Xu, Chenyu Tang, Edoardo Occhipinti, Mayinuer Yusufu, Ningli Wang, Weiling Bai, Shuo Gao, Luigi G. Occhipinti