Artificial intelligence for sperm selection—a systematic review

Despite the increasing number of assisted reproductive technologies based treatments being performed worldwide, there has been little improvement in fertilization and pregnancy outcomes. Male infertility is a major contributing factor, and sperm evaluation is a crucial step in diagnosis and treatment. However, embryologists face the daunting task of selecting a single sperm from millions in a sample based on various parameters, which can be time-consuming, subjective, and may even cause damage to the sperm, deeming them unusable for fertility treatments. Artificial intelligence algorithms have revolutionized the field of medicine, particularly in image processing, because of their discerning abilities, efficacy, and reproducibility. Artificial intelligence algorithms have the potential to address the challenges of sperm selection with their large-data processing capabilities and high objectivity. These algorithms could provide valuable assistance to embryologists in sperm analysis and selection. Furthermore, these algorithms could continue to improve over time as larger and more robust datasets become available for their training. Despite the increasing number of assisted reproductive technologies based treatments being performed worldwide, there has been little improvement in fertilization and pregnancy outcomes. Male infertility is a major contributing factor, and sperm evaluation is a crucial step in diagnosis and treatment. However, embryologists face the daunting task of selecting a single sperm from millions in a sample based on various parameters, which can be time-consuming, subjective, and may even cause damage to the sperm, deeming them unusable for fertility treatments. Artificial intelligence algorithms have revolutionized the field of medicine, particularly in image processing, because of their discerning abilities, efficacy, and reproducibility. Artificial intelligence algorithms have the potential to address the challenges of sperm selection with their large-data processing capabilities and high objectivity. These algorithms could provide valuable assistance to embryologists in sperm analysis and selection. Furthermore, these algorithms could continue to improve over time as larger and more robust datasets become available for their training. Infertility is a major global issue affecting >100 million people worldwide (1GBD 2015 Disease and Injury Incidence and Prevalence Collaborators. Global, regional, and national incidence, prevalence, and years lived with disability for 310 diseases and injuries, 1990-2015: a systematic analysis for the Global Burden of Disease Study 2015.Lancet. 2016; 388: 1545-1602Abstract Full Text Full Text PDF PubMed Scopus (4791) Google Scholar, 2Inhorn M.C. Patrizio P. Infertility around the globe: new thinking on gender, reproductive technologies and global movements in the 21st century.Hum Reprod Update. 2015; 21: 411-426Crossref PubMed Scopus (859) Google Scholar). It is estimated that male factor contributes to up to 50% of these cases (3Agarwal A. Mulgund A. Hamada A. Chyatte M.R. A unique view on male infertility around the globe.Reprod Biol Endocrinol. 2015; 13: 37Crossref PubMed Scopus (1104) Google Scholar), which has been increasing over the previous years (4Levine H. Jørgensen N. Martino-Andrade A. Mendiola J. Weksler-Derri D. Mindlis I. et al.Temporal trends in sperm count: a systematic review and meta-regression analysis.Hum Reprod Update. 2017; 23: 646-659Crossref PubMed Scopus (709) Google Scholar, 5Virtanen H.E. Jørgensen N. Toppari J. Semen quality in the 21st century.Nat Rev Urol. 2017; 14: 120-130Crossref PubMed Scopus (112) Google Scholar). Additionally, male factor infertility is often associated with stigma leading to neglection or underestimation of its true impact, especially in developing nations (6Ombelet W. Global access to infertility care in developing countries: a case of human rights, equity and social justice.Facts Views Vis Obgyn. 2011; 3: 257-266PubMed Google Scholar). Semen analysis evaluating a variety of parameters in the laboratory, including morphology, DNA integrity, and motility, is an essential tool for both diagnosis and treatment of male factor infertility (7Björndahl L. Kirkman Brown J. other Editorial Board Members of the WHO Laboratory Manual for the Examination and Processing of Human Semen. The sixth edition of the WHO laboratory manual for the examination and processing of human semen: ensuring quality and standardization in basic examination of human ejaculates.Fertil Steril. 2022; 117: 246-251Abstract Full Text Full Text PDF PubMed Scopus (0) Google Scholar). Semen parameters have been proven to be strong prognostic indicators of fertilization and pregnancy success (8Donnelly E.T. Lewis S.E. McNally J.A. Thompson W. In vitro fertilization and pregnancy rates: the influence of sperm motility and morphology on IVF outcome.Fertil Steril. 1998; 70: 305-314Abstract Full Text Full Text PDF PubMed Scopus (193) Google Scholar). In cases where semen parameters are suboptimal, assisted reproductive technology (ART) based techniques can be used to help sperm overcome the female reproductive tract barrier. The use of ART has been steadily increasing over the past years to overcome the barrier of male factor infertility and increase the chances of conception (9Fauser B.C. Towards the global coverage of a unified registry of IVF outcomes.Reprod Biomed Online. 2019; 38: 133-137Abstract Full Text Full Text PDF PubMed Google Scholar). Despite >200,000 ART cycles being reported annually nationwide (10Sunderam S. Kissin D.M. Zhang Y. Jewett A. Boulet S.L. Warner L. et al.Assisted reproductive technology surveillance - United States, 2018.MMWR Surveill Summ. 2022; 71: 1-19Crossref PubMed Google Scholar), success rates have remained relatively constant over the past few years (9Fauser B.C. Towards the global coverage of a unified registry of IVF outcomes.Reprod Biomed Online. 2019; 38: 133-137Abstract Full Text Full Text PDF PubMed Google Scholar), with sperm selection being a key determining factor (11Oseguera-López I. Ruiz-Díaz S. Ramos-Ibeas P. Pérez-Cerezales S. Novel techniques of sperm selection for improving IVF and ICSI outcomes.Front Cell Dev Biol. 2019; 7: 298Crossref PubMed Scopus (55) Google Scholar). There is a spectrum of laboratory procedures currently available for sperm selection. These include multiple steps and methods, alone or in combination, with the common goal of removing dead cells and debris (e.g., density gradient) and separating highly motile sperm (e.g., swim-up) (12Rappa K.L. Rodriguez H.F. Hakkarainen G.C. Anchan R.M. Mutter G.L. Asghar W. Sperm processing for advanced reproductive technologies: where are we today?.Biotechnol Adv. 2016; 34: 578-587Crossref PubMed Scopus (84) Google Scholar, 13Jayaraman V. Upadhya D. Narayan P.K. Adiga S.K. Sperm processing by swim-up and density gradient is effective in elimination of sperm with DNA damage.J Assist Reprod Genet. 2012; 29: 557-563Crossref PubMed Scopus (0) Google Scholar). Another metric that has been found to have an impact on embryo development and pregnancy success is sperm DNA fragmentation (14Lewis S.E.M. John Aitken R. Conner S.J. Iuliis G.D. Evenson D.P. Henkel R. et al.The impact of sperm DNA damage in assisted conception and beyond: recent advances in diagnosis and treatment.Reprod Biomed Online. 2013; 27: 325-337Abstract Full Text Full Text PDF PubMed Scopus (190) Google Scholar), which is not evaluated by the above-mentioned techniques (15Esteves S.C. Roque M. Bedoschi G. Haahr T. Humaidan P. Intracytoplasmic sperm injection for male infertility and consequences for offspring.Nat Rev Urol. 2018; 15: 535-562Crossref PubMed Scopus (111) Google Scholar). Although techniques, such as microfluidics and hyaluronic acid binding have been found to lower DNA fragmentation of a sperm sample, they have not proved their value to improve clinical outcomes yet (16Miller D. Pavitt S. Sharma V. Forbes G. Hooper R. Bhattacharya S. et al.Physiological, hyaluronan-selected intracytoplasmic sperm injection for infertility treatment (HABSelect): a parallel, two-group, randomised trial.Lancet. 2019; 393: 416-422Abstract Full Text Full Text PDF PubMed Scopus (50) Google Scholar). Despite the technological advancements and the variety of available sperm selection techniques, the final sperm selection is largely performed manually by an embryologist based on the World Health Organization (WHO) criteria (7Björndahl L. Kirkman Brown J. other Editorial Board Members of the WHO Laboratory Manual for the Examination and Processing of Human Semen. The sixth edition of the WHO laboratory manual for the examination and processing of human semen: ensuring quality and standardization in basic examination of human ejaculates.Fertil Steril. 2022; 117: 246-251Abstract Full Text Full Text PDF PubMed Scopus (0) Google Scholar). The embryologist is assigned with the enormous task of selecting only a few sperm from hundreds of thousands that are being present in a patient’s sample (17Nasr-Esfahani M.H. Deemeh M.R. Tavalaee M. New era in sperm selection for ICSI.Int J Androl. 2012; 35: 475-484Crossref PubMed Scopus (35) Google Scholar). This process becomes even more important in cases such that a single sperm needs to be selected for intracytoplasmic sperm injection (ICSI). The WHO currently provides some guidance regarding sperm morphologic selection, including head length, circularity, and presence or absence of vacuoles (7Björndahl L. Kirkman Brown J. other Editorial Board Members of the WHO Laboratory Manual for the Examination and Processing of Human Semen. The sixth edition of the WHO laboratory manual for the examination and processing of human semen: ensuring quality and standardization in basic examination of human ejaculates.Fertil Steril. 2022; 117: 246-251Abstract Full Text Full Text PDF PubMed Scopus (0) Google Scholar), while motility is also assessed visually by the embryologist (18Amann R.P. Waberski D. Computer-assisted sperm analysis (CASA): capabilities and potential developments.Theriogenology. 2014; 81: 5-17.e1Crossref PubMed Scopus (288) Google Scholar). However, embryologists do not have enough time to holistically assess an entire sperm sample. Additionally, sperm assessment largely depends on the operator, making the whole process highly subjective and staff specific (19Barroso G. Mercan R. Ozgur K. Morshedi M. Kolm P. Coetzee K. et al.Intra- and inter-laboratory variability in the assessment of sperm morphology by strict criteria: impact of semen preparation, staining techniques and manual versus computerized analysis.Hum Reprod. 1999; 14: 2036-2040Crossref PubMed Scopus (0) Google Scholar), with obvious repercussions on ART success. Artificial intelligence (AI) could potentially provide the solution to the subjectivity and efficiency challenge of sperm selection (20Bormann C.L. Thirumalaraju P. Kanakasabapathy M.K. Kandula H. Souter I. Dimitriadis I. et al.Consistency and objectivity of automated embryo assessments using deep neural networks.Fertil Steril. 2020; 113: 781-787.e1Abstract Full Text Full Text PDF PubMed Google Scholar, 21Bormann C.L. Curchoe C.L. Thirumalaraju P. Kanakasabapathy M.K. Gupta R. Pooniwala R. et al.Deep learning early warning system for embryo culture conditions and embryologist performance in the ART laboratory.J Assist Reprod Genet. 2021; 38: 1641-1646Crossref PubMed Scopus (13) Google Scholar). The picture analysis capabilities of AI are unparallel and recognizes patterns that are unperceivable to the human eye (22Stockman G. Shapiro L.G. Computer vision. Prentice Hall PTR, 2001Google Scholar). This ability makes AI systems uniquely applicable in the fertility setting among other health care fields (23Esteva A. Kuprel B. Novoa R.A. Ko J. Swetter S.M. Blau H.M. et al.Dermatologist-level classification of skin cancer with deep neural networks.Nature. 2017; 542: 115-118Crossref PubMed Scopus (54) Google Scholar, 24Dimitriadis I. Zaninovic N. Badiola A.C. Bormann C.L. Artificial intelligence in the embryology laboratory: a review.Reprod Biomed Online. 2022; 44: 435-448Abstract Full Text Full Text PDF PubMed Scopus (15) Google Scholar, 25Hosny A. Parmar C. Quackenbush J. Schwartz L.H. Aerts H.J.W.L. Artificial intelligence in radiology.Nat Rev Cancer. 2018; 18: 500-510Crossref PubMed Scopus (1297) Google Scholar). Furthermore, AI algorithms have proven their efficacy and consistency in embryo grading as well as predicting which embryos had the best developmental and implantation potential (26Bortoletto P. Kanakasabapathy M.K. Thirumalaraju P. Gupta R. Pooniwala R. Souter I. et al.Predicting blastocyst formation of day 3 embryos using a convolutional neural network (CNN): a machine learning approach.Fertil Steril. 2019; 112: e272-e273Abstract Full Text Full Text PDF Google Scholar, 27Dimitriadis I. Christou G. Dickinson K. McLellan S. Brock M. Souter I. et al.Cohort embryo selection (CES): a quick and simple method for selecting cleavage stage embryos that will become high quality blastocysts (HQB).Fertil Steril. 2017; 108: e162-e163Abstract Full Text Full Text PDF Google Scholar, 28Fitz V.W. Kanakasabapathy M.K. Thirumalaraju P. Kandula H. Ramirez L.B. Boehnlein L. et al.Should there be an “AI” in TEAM? Embryologists selection of high implantation potential embryos improves with the aid of an artificial intelligence algorithm.J Assist Reprod Genet. 2021; 38: 2663-2670Crossref PubMed Scopus (7) Google Scholar, 29Thirumalaraju P. Hsu J.Y. Bormann C.L. Kanakasabapathy M. Souter I. Dimitriadis I. et al.Deep learning-enabled blastocyst prediction system for cleavage stage embryo selection.Fertil Steril. 2019; 111: e29Abstract Full Text Full Text PDF Google Scholar). Additionally, AI could provide a logistical edge for the ART laboratory by reducing the embryologist’s time, effort, and subjectivity related to visual assessment and manual embryo grading (30Khosravi P. Kazemi E. Zhan Q. Malmsten J.E. Toschi M. Zisimopoulos P. et al.Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization.NPJ Digit Med. 2019; 2: 21Crossref PubMed Google Scholar). Machine learning algorithms have a tremendous capability to process large amounts of data and, similarly to embryo assessment, can be applied to automate the sperm selection process by combining visual and genetic data. Implementing these algorithms in the ART laboratory could minimize the innate subjectivity of manual assessment and enhance the embryologist’s sperm selection capabilities. Finally, embryo and clinical outcome data (fertilization, blastocyst formation, and clinical pregnancy rates) could be incorporated in the machine learning algorithms to further improve their applicability and predictive value. Consequently, our review aims to summarize the current evidence of AI and machine learning applications for sperm selection. Furthermore, we will investigate their performance to assess sperm parameters that are traditionally assessed by embryologists (e.g., morphology, DNA fragmentation, and motility). In this systematic review, we aimed to investigate the utilization of AI for selecting sperm in ART. A comprehensive search was conducted in Web of Science, ProQuest Central, PubMed Central, and MEDLINE-Academic databases to identify relevant articles. The search terms included “Intracytoplasmic Sperm Injection,” “Sperm,” “Artificial Intelligence,” “Deep Learning,” “Neural Networks,” “Machine Learning,” and “Human Infertility.” We limited our search to peer-reviewed articles published in English between 2010 and 2023. The initial search yielded a total of 261 articles. After a thorough review of the search results, 34 articles were selected based on their relevance and adherence to the inclusion criteria. Spermatogenesis involves a series of morphological changes from a round to a more elongated shape. Normal transition from spermatid to spermatozoa leads to normal sperm morphology and good fertilization potential. Currently sperm morphology serves as the main selection metric across ART practices, as evidence suggests that sperm morphology is also associated with normal fertilization and optimal pregnancy outcomes (31Bartoov B. Berkovitz A. Eltes F. Kogosowski A. Menezo Y. Barak Y. Real-time fine morphology of motile human sperm cells is associated with IVF-ICSI outcome.J Androl. 2002; 23: 1-8Crossref PubMed Google Scholar, 32De Vos A. Van De Velde H. Joris H. Verheyen G. Devroey P. Van Steirteghem A. Influence of individual sperm morphology on fertilization, embryo morphology, and pregnancy outcome of intracytoplasmic sperm injection.Fertil Steril. 2003; 79: 42-48Abstract Full Text Full Text PDF PubMed Scopus (211) Google Scholar). Sperm morphology is assessed based on the WHO criteria, with samples containing ≥4% morphologically normal sperms considered normal (7Björndahl L. Kirkman Brown J. other Editorial Board Members of the WHO Laboratory Manual for the Examination and Processing of Human Semen. The sixth edition of the WHO laboratory manual for the examination and processing of human semen: ensuring quality and standardization in basic examination of human ejaculates.Fertil Steril. 2022; 117: 246-251Abstract Full Text Full Text PDF PubMed Scopus (0) Google Scholar). Normal sperm morphology is defined based on sperm retrieved from the female reproductive tract and the oocyte zona pellucida after coitus because it is considered that sperm present there has better fertilization potential. Despite that, there is considerable variability in samples labeled as normal, which mainly poses an issue in cases of ICSI where the natural egg-sperm selection does not exist as does for cases of in vitro fertilization (IVF) or intrauterine insemination. Morphology assessment criteria became increasingly stricter because the initial imprecise criteria exhibited poor association with clinical outcomes (33Gatimel N. Moreau J. Parinaud J. Léandri R.D. Sperm morphology: assessment, pathophysiology, clinical relevance, and state of the art in 2017.Andrology. 2017; 5: 845-862Crossref PubMed Scopus (64) Google Scholar). Favorable sperm morphology characteristics include smooth and oval shaped head, acrosome covering 40%–70% of the head, absence of large or multiple small vacuoles, slenderness of the midpiece and equal length compared with the head, residual cytoplasm up to one third of the size of the head shape and surface texture of the head, acrosome area percentage, presence or absence of vacuoles (7Björndahl L. Kirkman Brown J. other Editorial Board Members of the WHO Laboratory Manual for the Examination and Processing of Human Semen. The sixth edition of the WHO laboratory manual for the examination and processing of human semen: ensuring quality and standardization in basic examination of human ejaculates.Fertil Steril. 2022; 117: 246-251Abstract Full Text Full Text PDF PubMed Scopus (0) Google Scholar, 34Menkveld R. Wong W.Y. Lombard C.J. Wetzels A.M. Thomas C.M. Merkus H.M. et al.Semen parameters, including WHO and strict criteria morphology, in a fertile and subfertile population: an effort towards standardization of in-vivo thresholds.Hum Reprod. 2001; 16: 1165-1171Crossref PubMed Google Scholar). However, assessing and interpreting these criteria by embryologists has an innate subjective nature leading to sperm selection interobserver and interlaboratory variability and inconsistency (19Barroso G. Mercan R. Ozgur K. Morshedi M. Kolm P. Coetzee K. et al.Intra- and inter-laboratory variability in the assessment of sperm morphology by strict criteria: impact of semen preparation, staining techniques and manual versus computerized analysis.Hum Reprod. 1999; 14: 2036-2040Crossref PubMed Scopus (0) Google Scholar, 33Gatimel N. Moreau J. Parinaud J. Léandri R.D. Sperm morphology: assessment, pathophysiology, clinical relevance, and state of the art in 2017.Andrology. 2017; 5: 845-862Crossref PubMed Scopus (64) Google Scholar, 35Eustache F. Auger J. Inter-individual variability in the morphological assessment of human sperm: effect of the level of experience and the use of standard methods.Hum Reprod. 2003; 18: 1018-1022Crossref PubMed Scopus (40) Google Scholar). Morphology assessment is performed utilizing different staining methods on a fixated sperm sample (36Bijar A. Mikaeili M. Khayati R. Fully automatic identification and discrimination of sperm’s parts in microscopic images of stained human semen smear.J Biomed Sci Eng. 2012; 5Crossref PubMed Google Scholar). There have been several methods described for sperm staining (e.g., Rapi-Diff, SpermBlue, Testimplets, and Papanicolaou) (37Singh S. Sharma S. Jain M. Chauhan R. Importance of papanicolaou staining for sperm morphologic analysis: comparison with an automated sperm quality analyzer.Am J Clin Pathol. 2011; 136: 247-251Crossref PubMed Scopus (0) Google Scholar, 38Schirren C. Eckhardt U. Jachczik R. Carstensen C.A. Morphological differentiation of human spermatozoa with Testsimplets slides.Andrologia. 1977; 9: 191-192Crossref PubMed Google Scholar, 39van der Horst G. Maree L. SpermBlue: a new universal stain for human and animal sperm which is also amenable to automated sperm morphology analysis.Biotech Histochem. 2009; 84: 299-308Crossref PubMed Scopus (0) Google Scholar). The aim of these methods is to enhance sperm visualization by increasing sperm contrast; however, significant differences have been described in the measured sperm dimensions among these methods (40Henkel R. Schreiber G. Sturmhoefel A. Hipler U.C. Zermann D.H. Menkveld R. Comparison of three staining methods for the morphological evaluation of human spermatozoa.Fertil Steril. 2008; 89: 449-455Abstract Full Text Full Text PDF PubMed Scopus (40) Google Scholar, 41Maree L. du Plessis S.S. Menkveld R. van der Horst G. Morphometric dimensions of the human sperm head depend on the staining method used.Hum Reprod. 2010; 25: 1369-1382Crossref PubMed Scopus (104) Google Scholar, 42Natali I. Muratori M. Sarli V. Vannuccini M. Cipriani S. Niccoli L. et al.Scoring human sperm morphology using Testsimplets and Diff-Quik slides.Fertil Steril. 2013; 99: 1227-1232.e2Abstract Full Text Full Text PDF PubMed Google Scholar, 43Czubaszek M. Andraszek K. Banaszewska D. Walczak-Jędrzejowska R. The effect of the staining technique on morphological and morphometric parameters of boar sperm.PLoS One. 2019; 14e0214243Crossref PubMed Scopus (24) Google Scholar). Depending on the osmolality of the stains and fixatives, there is either swelling or shrinking of the sperm head affecting sperm’s morphometric dimensions (41Maree L. du Plessis S.S. Menkveld R. van der Horst G. Morphometric dimensions of the human sperm head depend on the staining method used.Hum Reprod. 2010; 25: 1369-1382Crossref PubMed Scopus (104) Google Scholar). Additionally, the staining process, commonly involving drying and fixation has a significant impact on sperm’s vitality and motility, deeming it practically unusable for fertility treatments. To overcome these challenges there has been a number of noninvasive methods developed to assess the morphology of live sperm, including differential interference contrast and phase contrast microscopy (44Dai C. Zhang Z. Huang J. Wang X. Ru C. Pu H. et al.Automated non-invasive measurement of single sperm’s motility and morphology.IEEE Trans Med Imaging. 2018; 37: 2257-2265Crossref PubMed Scopus (17) Google Scholar). Evidence in the literature is conflicting when it comes to clinical outcomes with morphologically selected sperm for utilization in ICSI, with some studies showing better outcomes (45Hammoud I. Boitrelle F. Ferfouri F. Vialard F. Bergere M. Wainer B. et al.Selection of normal spermatozoa with a vacuole-free head (x6300) improves selection of spermatozoa with intact DNA in patients with high sperm DNA fragmentation rates.Andrologia. 2013; 45: 163-170Crossref PubMed Scopus (0) Google Scholar, 46Balaban B. Yakin K. Alatas C. Oktem O. Isiklar A. Urman B. Clinical outcome of intracytoplasmic injection of spermatozoa morphologically selected under high magnification: a prospective randomized study.Reprod Biomed Online. 2011; 22: 472-476Abstract Full Text Full Text PDF PubMed Scopus (100) Google Scholar), whereas others not showing significant differences (47Ebner T. Shebl O. Oppelt P. Mayer R.B. Some reflections on intracytoplasmic morphologically selected sperm injection.Int J Fertil Steril. 2014; 8: 105-112PubMed Google Scholar, 48De Vos A. Van de Velde H. Bocken G. Eylenbosch G. Franceus N. Meersdom G. et al.Does intracytoplasmic morphologically selected sperm injection improve embryo development? A randomized sibling-oocyte study.Hum Reprod. 2013; 28: 617-626Crossref PubMed Scopus (47) Google Scholar). Additionally, manual sperm selection based on morphology is a highly subjective, inconsistent, and time-consuming process (∼2.5 hours to select sperm to inject 10 oocytes under 100× magnification) (49Berkovitz A. Eltes F. Yaari S. Katz N. Barr I. Fishman A. et al.The morphological normalcy of the sperm nucleus and pregnancy rate of intracytoplasmic injection with morphologically selected sperm.Hum Reprod. 2005; 20: 185-190Crossref PubMed Scopus (246) Google Scholar, 50Vingris L. Setti A.S. De Almeida Ferreira Braga D.P. De Cassia Savio Figueira R. Iaconelli A. Borges E. Sperm morphological normality under high magnification predicts laboratory and clinical outcomes in couples undergoing ICSI.Hum Fertil (Camb). 2015; 18: 81-86Crossref PubMed Scopus (8) Google Scholar). Polyvinylpyrrolidone is a substance commonly used in ICSI and has been found to increase sperm DNA fragmentation after prolonged exposure (51Rougier N. Uriondo H. Papier S. Checa M.A. Sueldo C. Alvarez Sedó C. Changes in DNA fragmentation during sperm preparation for intracytoplasmic sperm injection over time.Fertil Steril. 2013; 100: 69-74Abstract Full Text Full Text PDF PubMed Scopus (0) Google Scholar). Consequently, there is a need to standardize these processes with the goal to minimize subjectivity, as well as time required to assess sperm morphology. AI and machine learning algorithms have shown a great potential to address and help overcome this challenge. The WHO delineates specific criteria to assess sperm morphology, which can be used to train the above-mentioned algorithms (52Riordon J. McCallum C. Sinton D. Deep learning for the classification of human sperm.Comput Biol Med. 2019; 111103342Crossref PubMed Scopus (51) Google Scholar, 53Chang V. Heutte L. Petitjean C. Härtel S. Hitschfeld N. Automatic classification of human sperm head morphology.Comput Biol Med. 2017; 84: 205-216Crossref PubMed Scopus (0) Google Scholar, 54Shaker F. Monadjemi S.A. Alirezaie J. Naghsh-Nilchi A.R. A dictionary learning approach for human sperm heads classification.Comput Biol Med. 2017; 91: 181-190Crossref PubMed Scopus (35) Google Scholar). A summary of the AI algorithms assessing sperm morphology is presented in Table 1 (55Butola A. Popova D. Prasad D.K. Ahmad A. Habib A. Tinguely J.C. et al.High spatially sensitive quantitative phase imaging assisted with deep neural network for classification of human spermatozoa under stressed condition.Sci Rep. 2020; 1013118Crossref PubMed Scopus (20) Google Scholar, 56Javadi S. Mirroshandel S.A. A novel deep learning method for automatic assessment of human sperm images.Comput Biol Med. 2019; 109: 182-194Crossref PubMed Scopus (40) Google Scholar, 57Kandel M.E. Rubessa M. He Y.R. Schreiber S. Meyers S. Matter Naves L. et al.Reproductive outcomes predicted by phase imaging with computational specificity of spermatozoon ultrastructure.Proc Natl Acad Sci U S A. 2020; 117: 18302-18309Crossref PubMed Scopus (12) Google Scholar, 58Liu G. Shi H. Zhang H. Zhou Y. Sun Y. Li W. et al.Fast noninvasive morphometric characterization of free human sperms using deep learning.Microsc Microanal. 2022; : 1-13Google Scholar, 59Chang V. Saavedra J.M. Castañeda V. Sarabia L. Hitschfeld N. Härtel S. Gold-standard and improved framework for sperm head segmentation.Comput Methods Programs Biomed. 2014; 117: 225-237Crossref PubMed Google Scholar, 60Hook K.A. Yang Q. Campanello L. Losert W. Fisher H.S. The social shape of sperm: using an integrative machine-learning approach to examine sperm ultrastructure and collective motility.Proc Biol Sci. 2021; 28820211553PubMed Google Scholar, 61Mirsky S.K. Barnea I. Levi M. Greenspan H. Shaked N.T. Automated analysis of individual sperm cells using stain-free interferometric phase microscopy and machine learning.Cytometry A. 2017; 91: 893-900Crossref PubMed Scopus (0) Google Scholar, 62Tseng K.K. Li Y. Hsu C.Y. Huang H.N. Zhao M. Ding M. Computer-assisted system with multiple feature fused support vector machine for sperm morphology diagnosis.Biomed Res Int. 2013; 2013687607Crossref Scopus (12) Google Scholar, 63Yüzkat M. Ilhan H.O. Aydin N. Multi-model CNN fusion for sperm morphology analysis.Comput Biol Med. 2021; 137104790Crossref PubMed Scopus (8) Google Scholar, 64Mirroshandel S.A. Ghasemian F. Monji-Azad S. Applying data mining techniques for increasing implantation rate by selecting best sperms for intra-cytoplasmic sperm injection treatment.Comput Methods Programs Biomed. 2016; 137: 215-229Crossref PubMed Google Scholar, 65Thirumalaraju P. Bormann C.L. Kanakasabapathy M. Doshi F. Souter I. Dimitriadis I. et al.Automated sperm morpshology testing using artificial intelligence.Fertil Steril. 2018; 110: e432Abstract Full Text Full Text PDF Google Scholar). Deep neural network (52Riordon J. McCallum C. Sinton D. Deep learning for the classification of human sperm.Comput Biol Med. 2019; 111103342Crossref PubMed Scopus (51) Google Scholar, 55Butola A. Popova D. Prasad D.K. Ahmad A. Habib A. Tinguely J.C. et al.High spatially sensitive quantitative phase imaging assisted with deep neural network for classification of human sperm