A preliminary study of sperm identification in microdissection testicular sperm extraction samples with deep convolutional neural networks

Associations between dietary macronutrient quality and asthenozoospermia risk: a hospital-based case-control study

Background & aims: Macronutrients are the main part of the human diet and can affect multiple health outcomes. Nevertheless, associations between dietary macronutrient quality and asthenozoospermia risk have not been reported to date. Thus, this study aimed to be the first to explore the associations between macronutrient quality and asthenozoospermia risk using the novel multidimensional macronutrient quality index (MQI). Methods: A case-control study was conducted at infertility clinics of Shengjing Hospital of China Medical University during June and December 2020, including 552 asthenozoospermia cases and 585 normozoospermia controls. Data on diet were collected using a validated food frequency questionnaire. MQI was estimated according to the carbohydrate quality index (CQI), fat quality index (FQI), and protein quality index (PQI). Binary logistic regression models were performed to calculate the odds ratio (OR) with a 95% confidence interval (CI). Subgroup and interaction analyses were performed based on age, body mass index, physical activity, smoking, drinking, and education level. Dose-response relationships were evaluated by restricted cubic splines. Sensitivity analyses were performed in two ways. First, participants with a dietary change were excluded to lower potential reverse causation. Then, we used the healthy plate protein source quality index instead of PQI to redefine MQI. Results: No statistically significant association was observed between dietary MQI and asthenozoospermia risk (OR = 1.24, 95% CI: 0.88-1.73). The sub-indices of MQI, CQI, FQI, and PQI, failed to be identified as having a statistically significant association with asthenozoospermia risk (OR = 1.35, 95% CI: 0.92-1.97 for CQI; OR = 1.13, 95% CI: 0.84-1.53 for FQI; OR = 1.28, 95% CI: 0.92-1.78 for PQI). However, CQI showed a positive association with the risk of asthenozoospermia among non-drinkers (Ptrend < 0.05) and highly educated participants (OR = 1.82, 95% CI: 1.13-2.94; Ptrend < 0.05). Additionally, there was a multiplicative interaction between CQI and education level for asthenozoospermia risk (P < 0.05). Conclusions: Our findings demonstrated no association of MQI and its sub-indices with asthenozoospermia risk except for CQI. Although our findings are mostly non-significant, they contribute novel knowledge to this research field and lay the foundation for future studies.

The Role of Autophagy in Erectile Dysfunction

Autophagy is a conservative lysosome-dependent material catabolic pathway, and exists in all eukaryotic cells. Autophagy controls cell quality and survival by eliminating intracellular dysfunction substances, and plays an important role in various pathophysiology processes. Erectile dysfunction (ED) is a common male disease. It is resulted from a variety of causes and pathologies, such as diabetes, hypertension, hyperlipidemia, aging, spinal cord injury, or cavernous nerve injury caused by radical prostatectomy, and others. In the past decade, autophagy has begun to be investigated in ED. Subsequently, an increasing number of studies have revealed the regulation of autophagy contributes to the recovery of ED, and which is mainly involved in improving endothelial function, smooth muscle cell apoptosis, penile fibrosis, and corpus cavernosum nerve injury. Therefore, in this review, we aim to summarize the possible role of autophagy in ED from a cellular perspective, and we look forward to providing a new idea for the pathogenesis investigation and clinical treatment of ED in the future.

The prospect of artificial intelligence to personalize assisted reproductive technology

Infertility affects 1-in-6 couples, with repeated intensive cycles of assisted reproductive technology (ART) required by many to achieve a desired live birth. In ART, typically, clinicians and laboratory staff consider patient characteristics, previous treatment responses, and ongoing monitoring to determine treatment decisions. However, the reproducibility, weighting, and interpretation of these characteristics are contentious, and highly operator-dependent, resulting in considerable reliance on clinical experience. Artificial intelligence (AI) is ideally suited to handle, process, and analyze large, dynamic, temporal datasets with multiple intermediary outcomes that are generated during an ART cycle. Here, we review how AI has demonstrated potential for optimization and personalization of key steps in a reproducible manner, including: drug selection and dosing, cycle monitoring, induction of oocyte maturation, and selection of the most competent gametes and embryos, to improve the overall efficacy and safety of ART.

Current Updates on Involvement of Artificial Intelligence and Machine Learning in Semen Analysis

Background and Objectives: Infertility rates and the number of couples undergoing reproductive care have both increased substantially during the last few decades. Semen analysis is a crucial step in both the diagnosis and the treatment of male infertility. The accuracy of semen analysis results remains quite poor despite years of practice and advancements. Artificial intelligence (AI) algorithms, which can analyze and synthesize large amounts of data, can address the unique challenges involved in semen analysis due to the high objectivity of current methodologies. This review addresses recent AI advancements in semen analysis. Materials and Methods: A systematic literature search was performed in the PubMed database. Non-English articles and studies not related to humans were excluded. We extracted data related to AI algorithms or models used to evaluate semen parameters from the original studies, excluding abstracts, case reports, and meeting reports. Results: Of the 306 articles identified, 225 articles were rejected in the preliminary screening. The evaluation of the full texts of the remaining 81 publications resulted in the exclusion of another 48 articles, with a final inclusion of 33 original articles in this review. Conclusions: AI and machine learning are becoming increasingly popular in biomedical applications. The examination and selection of sperm by andrologists and embryologists may benefit greatly from using these algorithms. Furthermore, when bigger and more reliable datasets become accessible for training, these algorithms may improve over time.

Study on Sperm-Cell Detection Using YOLOv5 Architecture with Labaled Dataset

Infertility has recently emerged as a severe medical problem. The essential elements in male infertility are sperm morphology, sperm motility, and sperm density. In order to analyze sperm motility, density, and morphology, laboratory experts do a semen analysis. However, it is simple to err when using a subjective interpretation based on laboratory observation. In this work, a computer-aided sperm count estimation approach is suggested to lessen the impact of experts in semen analysis. Object detection techniques concentrating on sperm motility estimate the number of active sperm in the semen. This study provides an overview of other techniques that we can compare. The Visem dataset from the Association for Computing Machinery was used to test the proposed strategy. We created a labelled dataset to prove that our network can detect sperms in images. The best not-super tuned result is mAP 72.15.

Evolution of the basic semen analysis and processing sperm

PURPOSE OF REVIEW

The sixth edition of the World Health Organization (WHO) laboratory manual for the examination and processing of human semen was recently published with specific step-by-step instructions for semen evaluation and sperm processing. Point-of-care (POC) testing for semen evaluation and microfluidics for sperm processing are rapidly evolving technologies that could impact how we evaluate and process sperm. Understanding the updated manual in the context of these novel technologies is important.

RECENT FINDINGS

Proper standardization of semen evaluation and sperm processing will allow for consistent high-quality results among laboratories worldwide. POC testing could improve access to semen evaluations that generate referrals to male infertility specialists for further assessment. Microfluidics can select functional sperm with decreased DNA fragmentation in semen and testicular biopsy samples for assisted reproductive technology (ART). Clinical outcomes, such as pregnancy rates and live birth rates, have not been shown to be consistently improved with these technologies compared to conventional techniques, although high level evidence research in this area is limited.

SUMMARY

POC testing and microfluidics have the potential to be combined with machine learning technologies to improve fertility care. If these technologies are appropriately optimized, they could change how we evaluate and process sperm, and potentially lead to improved ART outcomes.

Modern surgical treatment of azoospermia

PURPOSE OF REVIEW

To review noteworthy research from the last 2 years on surgical management of azoospermia.

RECENT FINDINGS

The recommended treatments for nonobstructive and obstructive azoospermia have not appreciably changed. However, recent level-1 evidence has reinforced superiority of micro-dissection testicular sperm extraction over sperm aspiration in men with nonobstructive azoospermia, and several studies have identified genetic and other clinical factors that may aid in selecting candidates for testicular sperm extraction. Machine learning technology has shown promise as a decision support system for patient selection prior to sperm retrieval as well a tool to aid in sperm identification from testis tissue.

SUMMARY

Most men with obstructive azoospermia who desire fertility can be offered either surgical reconstruction or sperm retrieval. For men with nonobstructive azoospermia, sperm retrieval with microdissection testicular sperm extraction remains the gold standard treatment. Uncovering more genetic causes of nonobstructive azoospermia may aid in properly counseling and selecting patients for microdissection testicular sperm extraction. Neural networks and deep learning may have a future role in patient selection for surgical sperm retrieval and postprocedural sperm identification.

Spatiotemporal trends in human semen quality

Over the past four decades, studies of various designs have reported spatial and temporal trends in human semen quality. Several standardized-methodology studies in homogeneous populations that compare specific cities within a country or a continent provide clear evidence of geographical differences in sperm production, even over short distances within the same country. Human sperm production is widely believed to be declining over time, but evidence from the scientific literature is less clear. Studies based on repeated cross-sectional data from a single centre have shown mixed results. Among the numerous retrospective studies conducted in a single centre, only some included homogeneous groups of men and appropriate methods, and most of them suggest a temporal decrease in human sperm production in the geographical areas considered. Conclusions reporting temporal trends in sperm production that came from existing retrospective multicentre studies based on individual semen data and those using means, medians or estimates of sperm production are questionable, owing to intrinsic limitations in the studies performed. Regardless of study design, studies on the percentage of motile or morphologically normal spermatozoa are still limited by the inherent variability in assessment. Overall, available data do not enable us to conclude that human semen quality is deteriorating worldwide or in the Western world, but that a trend is observed in some specific areas. To understand these trends and contrasts in sperm and semen quality, prospective studies should be encouraged and combined with assessment of the male exposome.

Several studies over the past few decades have suggested that sperm quality varies by geographical region and might be subject to a temporal decline worldwide. However, the data supporting these conclusions have come from studies of various methodologies and heterogeneous populations, making them unreliable. In this in-depth Review, Chevrier and colleagues discuss the data surrounding discussion of spatiotemporal trends in semen parameters and consider how these trends and the factors promoting them interact.

The vast literature on human semen quality trends is extremely heterogeneous in terms of the populations studied and study designs, and so these studies have been unable to draw firm conclusions.

Understanding the data around spatiotemporal semen trends requires a focus on the methodological choices and application of criteria to filter findings from the studies with optimal design.

Numerous appropriately designed studies suggest unambiguous geographical contrasts in human sperm production; however, evidence of a decline in sperm production is reliable only in specific populations and cities in which studies with a complete set of quality criteria have been conducted.

By contrast, suggestions of a worldwide drop in human semen quality on the basis of retrospective multicentre studies cannot be substantiated, owing to intrinsic limitations in the studies performed.

Many and varied factors of variation, in particular the diverse modalities of assessment, do not enable us to conclude that clear temporal trends of sperm motility and normal morphology are present.

Progress in our understanding of the highlighted trends and their causal factors requires prospective studies that minimize all known biases combined with the assessment of men’s exposome.

Stereological properties of seminiferous tubules in infertile men with chromosomal and genetic abnormalities

BACKGROUND

Male infertility is caused by genetic anomalies in 15%-30% of cases. This study aimed to determine stereological properties of seminiferous tubules in infertile men with genetic anomalies, including Klinefelter syndrome (KS), Y chromosome microdeletions (MYC) and CFTR gene mutations (CFTR), and to compare them to seminiferous tubules of men with obstructive azoospermia of non-genetic origin (control group).

METHODS

The study was conducted on 28 human testis biopsy specimens obtained from 14 patients with MYC, 18 samples from 9 patients with KS, and 6 samples from 3 patients with CFTR. Whenever possible, a bilateral biopsy was included in the study. The control group had 33 samples from 18 patients (3 of them with a solitary testis). Qualitative and quantitative (stereological) analysis of seminiferous tubules (including the status of spermatogenesis, volume, surface area, length and number of tubules) were performed in all groups.

RESULTS

Qualitative histological analysis revealed significant impairment of spermatogenesis in KS and MYC, whereas testicular parenchyma was fully maintained in CFTR and control groups. Spermatogenesis was most seriously impaired in KS. All stereological parameters were significantly lower in KS and MYC, compared to the CFTR and control groups. The total volume, surface and length of seminiferous tubules were significantly lower in KS compared with MYC.

CONCLUSIONS

Stereological analysis is valuable in evaluating male infertility, whereas qualitative histological analysis can be helpful in assessing sperm presence in testicular tissue of patients with KS or MYK undergoing TESE.

Novel methods to enhance surgical sperm retrieval: a systematic review

Objectives: To explore the use of novel technologies in sperm retrieval in men with azoospermia due to a production defect. Methods: We performed a Preferred Reporting Items for Systemic Reviews and Meta-Analysis (PRISMA)-compliant systemic literature review for manuscripts focussed on novel sperm-retrieval methods. We identified 30 studies suitable for qualitative analysis. Results and Conclusions: We identified multiple new promising technologies, each with its own distinct set of benefits and limitations, to enhance chances of sperm retrieval; these include the use of multiphoton microscopy, Raman spectroscopy, and full-field optical coherence tomography during a microdissection-testicular sperm extraction procedure. ORBEYE and ultrasonography technologies can also serve to better visualise areas of sperm production. Finally, artificial intelligence technology can play a role in the identification of sperm and, perhaps, better-quality sperm for use with assisted reproduction. Abbreviations: AI: artificial intelligence; ANN: artificial neural network; ART: assisted reproductive technology; 3D: three-dimensional; DNN: deep neural networks; FFOCT: full-field optical coherence tomography; H&E: haematoxylin and eosin; ICSI: intracytoplasmic sperm injection; IVF: in vitro fertilisation; MESA: micro-epididymal sperm aspiration; MeSH: Medical Subject Heading; MPM: multiphoton microscopy; (N)OA: (non-)obstructive azoospermia; SCO: Sertoli cell-only syndrome; SRR: sperm retrieval rates; TESA: testicular sperm aspiration; (micro-)TESE: (microdissection-) testicular sperm extraction; (CE)US: (contrast-enhanced) ultrasonography.