Simultaneous Morphology, Motility, and Fragmentation Analysis of Live Individual Sperm Cells for Male Fertility Evaluation

Abstract

A new technique for sperm analysis is presented, measuring DNA fragmentation, morphology with virtual staining, and motility, all three criteria on the same individual unstained live cell. The method relies on quantitative stain‐free interferometric imaging, providing unique topographic structural and content maps of the cell, becoming available for the first time for clinical use, together with deep‐learning frameworks and least‐squares linear approximation. In the common clinical practice, only motility evaluation can be 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. A clinic‐ready interferometric module is used to acquire dynamic sperm cells without chemical staining, together with deep learning to evaluate all three scores per cell with accuracy of 93.1%, 88%, and 90% for morphology, motility, and DNA fragmentation, respectively. It is shown that the expected number of cells that pass all three criteria based on the current evaluations performed separately does not correspond with the number of cells that pass all criteria, demonstrating the importance of the suggested method. The proposed stain‐free evaluation method is expected to decrease uncertainty in infertility diagnosis, increasing treatment success rates.

CatSper and its CaM‐like Ca 2+ sensor EFCAB9 are necessary for the path chirality of sperm

“…7,82 Most of the used setups differ in the time resolution. Whereas some studies recorded with a low time resolution of under 50 fps 51,56 or with a high time resolution of 1000 fps 55 to 2000 fps, 80 we and other studies use a resolution of 100 fps 7 to 300 fps. 76,82 Daloglu and coworkers mention, that 3D imaging of fast-moving objects like sperm need a high depth of field (DOF) to focus on such cells.…”

“…This, in turn, leads to an increase in swimming trajectories in all three dimensions and sperm velocity, resulting in a stronger swimming force, essential for penetration of the zona pellucida. 13 In the past couple of years, several studies used DHM to track sperm cell trajectories in three dimensions 7,34,51,55,[76][77][78][79] to analyze sperm head morphology 56,80,81 or flagellar movement of free-swimming 7,34,76,80 or tethered sperm. 7,82 Most of the used setups differ in the time resolution.…”

“…In recent years, several studies were published, which use digital holographic imaging for a 4D analysis of sperm movement. 7,[53][54][55][56][57] In this study, we also use highspeed DHM for 4D movement analysis of free-swimming murine sperm. DHM allows to perform non-invasive and label-free single-cell analysis.…”

Location Prediction of Sperm Cells Using Long Short‐Term Memory Networks

“…Researchers have also explored the use of various microscopic imaging techniques, including quantitative phase imaging and deep learning algorithms, to predict the quality of sperm cells based on their morphology and estimate the extent of their DNA fragmentation, [13][14][15][16] in addition to their motility. [17] Yet, sperm cell tracking faces many challenges such as overlaying of cells in the semen sample and sperm cells that get out of focus during motion. Moreover, capturing the cell, manually or automatically, requires the ability to predict where the cell would be in the future, when the capturing occurs.…”

Sperm‐cell DNA fragmentation prediction using label‐free quantitative phase imaging and deep learning

“…Recently, machine learning and deep learning have even been used for research in the classification of sperm cells. Some of these works used handcrafted morphological features constructed by following application of the WHO guidelines [9][10][11] while others have used CNN to automatically classify sperm cells without specific hand-crafted feature extraction [12]. Training a CNN requires a significant amount of data, which consists of the images and the ground truth (GT) labels.…”