In a recent Fertility and Sterility review, researchers summarize the available evidence on the applying of artificial intelligence (AI) and machine learning in sperm selection.
All relevant articles were obtained from PubMed Central, Web of Science, and MEDLINE-Academic databases. A complete of 261 articles were present in the initial search; nonetheless, based on the inclusion criteria, 34 articles were chosen.
Study: Artificial Intelligence (AI) for Sperm Selection – a Systematic Review. Image Credit: Inna Dodor / Shutterstock.com
Importance of sperm selection
Globally, over 100 million individuals encounter issues related to infertility, with the male factor contributing to as much as 50% of those cases.
Semen evaluation, which is related to the investigation of sperm morphology, motility, and DNA integrity, is important for the diagnosis and subsequent treatment of male factor infertility. Based on various parameters, embryologists face the daunting task of choosing a single sperm from tens of millions in a sample, a laborious process at a high risk of selection errors.
Semen parameters are strong prognostic indicators of fertilization and pregnancy outcomes. If the evaluation indicates that the semen parameters are suboptimal, assisted reproductive technologies (ART) may be applied to assist the sperm overcome the feminine reproductive tract barrier, thereby improving the likelihood of conception.
The success rates of ART have remained relatively low globally attributable to the shortage of proper sperm selection. Despite technological advancements, the ultimate sperm selection is primarily performed manually by an embryologist following the World Health Organization (WHO) criteria. Sperm selection is crucial, as a single sperm is required for intracytoplasmic sperm injection (ICSI).
The WHO has provided guidance for correct sperm selection based on the morphology, including sperm head length, presence/absence of vacuole, and circularity, in addition to motility. Nonetheless, embryologists would not have adequate time to evaluate a complete sperm holistically, which could impact the success of ART. Here, AI might be applied to enhance the efficiency of sperm selection.
AI and machine learning for sperm selection
Previous studies have indicated that AI can consistently and effectively discover an embryo with optimal developmental and implantation potential. AI may also reduce the embryologist’s effort and time related to visual assessment and manual embryo grading.
Machine learning algorithms are able to processing large data sets, just like the majority of knowledge evaluated during embryo assessment. Subsequently, this system may be applied to automate the sperm selection process by coupling genetic and visual data. Implementing AI and machine learning algorithms within the ART laboratory could significantly improve the embryologist’s sperm selection capabilities.
Favorable sperm morphology is characterised by a smooth and oval head, absence of huge/multiple vacuoles, acrosome covering 40-70% of the top, the slenderness of the midpiece, and residual cytoplasm as much as one-third of the scale of the top. AI algorithms can standardize and expedite sperm analyses based on the available models. Furthermore, sperm morphology together with deep learning algorithms, might be evaluated with an accuracy of around 98%.
The performance of AI and machine learning algorithms rely on the standard of the training dataset images. To acquire greater accuracy in these systems, they need to be trained with larger and high-quality sperm imaging data.
In some cases, sperm cells are highly liable to damage within the sperm head, which results in chromosome aberrations, DNA fragmentation, and telomere shortening. Male fertility is inversely related to DNA fragmentation index (DFI), which is amazingly necessary for sperm selection. Techniques similar to single-cell gel electrophoresis (SCGE), terminal deoxynucleotidyl transferase UTP nick-end labeling (TUNEL), and sperm chromatin structure assay are used to detect DNA fragmentation.
Scientists have developed machine learning algorithms by training the system with sperm images linked to associated DFI values. This standardized system can accurately evaluate the standard of a single sperm based on the trained dataset, thereby eliminating any concerns regarding human subjectivity.
Embryologists use holographic imaging, computer-aided sperm evaluation (CASA), and microfluidic platforms to find out sperm motility. CASA is a high-throughput method that evaluates large amounts of sperm on the sample level but doesn’t analyze easy sperm motility.
This may be resolved with the event of a mathematical model based on the three-dimensional (3D) helical motion of tail beating. High-resolution holographic imaging techniques allow scientists to evaluate the tail-beating patterns in free-swimming sperm.
Multiple data on sperm motility linked to CASA, microfluidic chips, and holographic imaging are used to coach the AI system, coupled with other male fertility parameters to pick optimal sperm for ART. Thus, applications of AI and machine learning techniques have significantly improved conception rates and successful pregnancy outcomes following ART.
Journal reference:
- Cherouveim, P., Velmahos, C., & Bormann, C. L. (2023). Artificial Intelligence (AI) for Sperm Selection – a Systematic Review. Fertility and Sterility. doi:10.1016/j.fertnstert.2023.05.157