Surface tracking integrated extended depth-of-field microscopy for rapid non-contact examination of conjunctival goblet cells in humans.

Conjunctival goblet cells (CGCs) are specialized epithelial cells playing key roles for ocular surface homeostasis, and their examination is important for diagnosing ocular surface diseases. Despite recent advancements in high-contrast CGC imaging for non-invasive examination, significant challenges remain for human applications. High-speed large-area imaging over the curved ocular surface is needed to assess statistically meaningful CGCs in the extensive human conjunctiva. To address this challenge, we developed a novel surface detection method and an integrated microscopy system for human use. With both a long detection range of 2 mm and a high update rate of 50 Hz, the surface detection method enabled real-time surface tracking during large-area imaging. The integrated microscopy could complete 5 × 2 patch imaging in approximately 10 s. CGC density analysis showed significantly reduced uncertainties with large-area imaging. This is the first demonstration of non-contact large-area cellular examination in humans, and this new development holds promise for non-invasive CGC examination and accurate diagnosis of ocular surface diseases.

Deep learning framework for automated goblet cell density analysis in in-vivo rabbit conjunctiva.

Goblet cells (GCs) in the conjunctiva are specialized epithelial cells secreting mucins for the mucus layer of protective tear film and playing immune tolerance functions for ocular surface health. Because GC loss is observed in various ocular surface diseases, GC examination is important for precision diagnosis. Moxifloxacin-based fluorescence microscopy (MBFM) was recently developed for non-invasive high-contrast GC visualization. MBFM showed promise for GC examination by high-speed large-area imaging and a robust analysis method is needed to provide GC information. In this study, we developed a deep learning framework for GC image analysis, named dual-channel attention U-Net (DCAU-Net). Dual-channel convolution was used both to extract the overall image texture and to acquire the GC morphological characteristics. A global channel attention module was adopted by combining attention algorithms and channel-wise pooling. DCAU-Net showed 93.1% GC segmentation accuracy and 94.3% GC density estimation accuracy. Further application to both normal and ocular surface damage rabbit models revealed the spatial variations of both GC density and size in normal rabbits and the decreases of both GC density and size in damage rabbit models during recovery after acute damage. The GC analysis results were consistent with histology. Together with the non-invasive high-contrast imaging method, DCAU-Net would provide GC information for the diagnosis of ocular surface diseases.