Evaluation of an artificial intelligence-facilitated sperm detection tool in azoospermic samples for use in ICSI.

RESEARCH QUESTION: Can artificial intelligence (AI) improve the efficiency and efficacy of sperm searches in azoospermic samples? DESIGN: This two-phase proof-of-concept study began with a training phase using eight azoospermic patients (>10,000 sperm images) to provide a variety of surgically collected samples for sperm morphology and debris variation to train a convolutional neural network to identify spermatozoa. Second, side-by-side testing was undertaken on two cohorts of non-obstructive azoospermia patient samples: an embryologist versus the AI identifying all the spermatozoa in the still images (cohort 1, n = 4), and a side-by-side test with a simulated clinical deployment of the AI model with an intracytoplasmic sperm injection microscope and the embryologist performing a search with and without the aid of the AI (cohort 2, n = 4). RESULTS: In cohort 1, the AI model showed an improvement in the time taken to identify all the spermatozoa per field of view (0.02 ± 0.30  ×  10-5s versus 36.10 ± 1.18s, P < 0.0001) and improved recall (91.95 ± 0.81% versus 86.52 ± 1.34%, P < 0.001) compared with an embryologist. From a total of 2660 spermatozoa to find in all the samples combined, 1937 were found by an embryologist and 1997 were found by the AI in less than 1000th of the time. In cohort 2, the AI-aided embryologist took significantly less time per droplet (98.90 ± 3.19 s versus 168.7 ± 7.84 s, P < 0.0001) and found 1396 spermatozoa, while 1274 were found without AI, although no significant difference was observed. CONCLUSIONS: AI-powered image analysis has the potential for seamless integration into laboratory workflows, to reduce the time to identify and isolate spermatozoa from surgical sperm samples from hours to minutes, thus increasing success rates from these treatments.

Microfluidics facilitating the use of small extracellular vesicles in innovative approaches to male infertility.

Sperm are transcriptionally and translationally quiescent and, therefore, rely on the seminal plasma microenvironment for function, survival and fertilization of the oocyte in the oviduct. The male reproductive system influences sperm function via the binding and fusion of secreted epididymal (epididymosomes) and prostatic (prostasomes) small extracellular vesicles (S-EVs) that facilitate the transfer of proteins, lipids and nucleic acids to sperm. Seminal plasma S-EVs have important roles in sperm maturation, immune and oxidative stress protection, capacitation, fertilization and endometrial implantation and receptivity. Supplementing asthenozoospermic samples with normospermic-derived S-EVs can improve sperm motility and S-EV microRNAs can be used to predict non-obstructive azoospermia. Thus, S-EV influence on sperm physiology might have both therapeutic and diagnostic potential; however, the isolation of pure populations of S-EVs from bodily fluids with current conventional methods presents a substantial hurdle. Many conventional techniques lack accuracy, effectiveness, and practicality; yet microfluidic technology has the potential to simplify and improve S-EV isolation and detection.

Unique Deep Radiomic Signature Shows NMN Treatment Reverses Morphology of Oocytes from Aged Mice.

The purpose of this study is to develop a deep radiomic signature based on an artificial intelligence (AI) model. This radiomic signature identifies oocyte morphological changes corresponding to reproductive aging in bright field images captured by optical light microscopy. Oocytes were collected from three mice groups: young (4- to 5-week-old) C57BL/6J female mice, aged (12-month-old) mice, and aged mice treated with the NAD+ precursor nicotinamide mononucleotide (NMN), a treatment recently shown to rejuvenate aspects of fertility in aged mice. We applied deep learning, swarm intelligence, and discriminative analysis to images of mouse oocytes taken by bright field microscopy to identify a highly informative deep radiomic signature (DRS) of oocyte morphology. Predictive DRS accuracy was determined by evaluating sensitivity, specificity, and cross-validation, and was visualized using scatter plots of the data associated with three groups: Young, old and Old + NMN. DRS could successfully distinguish morphological changes in oocytes associated with maternal age with 92% accuracy (AUC~1), reflecting this decline in oocyte quality. We then employed the DRS to evaluate the impact of the treatment of reproductively aged mice with NMN. The DRS signature classified 60% of oocytes from NMN-treated aged mice as having a 'young' morphology. In conclusion, the DRS signature developed in this study was successfully able to detect aging-related oocyte morphological changes. The significance of our approach is that DRS applied to bright field oocyte images will allow us to distinguish and select oocytes originally affected by reproductive aging and whose quality has been successfully restored by the NMN therapy.

Multispectral autofluorescence characteristics of reproductive aging in old and young mouse oocytes.

Increasing age has a major detrimental impact on female fertility, which, with an ageing population, has major sociological implications. This impact is primarily mediated through deteriorating quality of the oocyte. Deteriorating oocyte quality with biological age is the greatest rate-limiting factor to female fertility. Here we have used label-free, non-invasive multi-spectral imaging to identify unique autofluorescence profiles of oocytes from young and aged animals. Discriminant analysis demonstrated that young oocytes have a distinct autofluorescent profile which accurately distinguishes them from aged oocytes. We recently showed that treatment with the nicotinamide adenine dinucleotide (NAD+) precursor nicotinamide mononucleotide (NMN) restored oocyte quality and fertility in aged animals, and when our analysis was applied to oocytes from aged animals treated with NMN, 85% of these oocytes were classified as having the autofluorescent signature of young animals. Spectral unmixing using the Robust Dependent Component Analysis (RoDECA) algorithm demonstrated that NMN treatment altered the metabolic profile of oocytes, increasing free NAD(P)H, protein bound NAD(P)H, redox ratio and the ratio of bound to free NAD(P)H. The frequency of oocytes with simultaneously high NAD(P)H and flavin content was also significantly increased in mice treated with NMN. Young and Aged + NMN oocytes had a smoother spectral distribution, with the distribution of NAD(P)H in young oocytes specifically differing from that of aged oocytes. Identifying the multispectral profile of oocyte autofluorescence during aging could have utility as a non-invasive and sensitive measure of oocyte quality.

NAD+ Repletion Rescues Female Fertility during Reproductive Aging.

Reproductive aging in female mammals is an irreversible process associated with declining oocyte quality, which is the rate-limiting factor to fertility. Here, we show that this loss of oocyte quality with age accompanies declining levels of the prominent metabolic cofactor nicotinamide adenine dinucleotide (NAD+). Treatment with the NAD+ metabolic precursor nicotinamide mononucleotide (NMN) rejuvenates oocyte quality in aged animals, leading to restoration in fertility, and this can be recapitulated by transgenic overexpression of the NAD+-dependent deacylase SIRT2, though deletion of this enzyme does not impair oocyte quality. These benefits of NMN extend to the developing embryo, where supplementation reverses the adverse effect of maternal age on developmental milestones. These findings suggest that late-life restoration of NAD+ levels represents an opportunity to rescue female reproductive function in mammals.