| Popis: |
We present a new technique for sperm analysis on individual unstained live cells, measuring DNA fragmentation, morphology with virtual staining, and motility. The method relies on quantitative stain-free interferometric imaging and deep-learning frameworks, and is utilized for male fertility evaluation. In the common clinical practice, only motility evaluation is carried out on live human cells, while full morphological evaluation and DNA fragmentation assays require different staining protocols, and therefore cannot be performed on the same cell, resulting in inconsistencies in fertility evaluation. We use a clinic-ready interferometric module to acquire dynamic sperm cells without chemical staining, and deep learning to evaluate all three scores per cell. We show that the number of cells that pass each criterion separately does not accurately predict how many would pass all criteria. This stain-free evaluation method is expected to decrease uncertainty in infertility diagnosis, increasing treatment success rates. |
