scholarly journals Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Pegah Khosravi ◽  
Ehsan Kazemi ◽  
Qiansheng Zhan ◽  
Jonas E. Malmsten ◽  
Marco Toschi ◽  
...  
2021 ◽  
Author(s):  
Itay Erlich ◽  
Assaf Ben-Meir ◽  
Iris Har-Vardi ◽  
James A Grifo ◽  
Assaf Zaritsky

Automated live embryo imaging has transformed in-vitro fertilization (IVF) into a data-intensive field. Unlike clinicians who rank embryos from the same IVF cycle cohort based on the embryos visual quality and determine how many embryos to transfer based on clinical factors, machine learning solutions usually combine these steps by optimizing for implantation prediction and using the same model for ranking the embryos within a cohort. Here we establish that this strategy can lead to sub-optimal selection of embryos. We reveal that despite enhancing implantation prediction, inclusion of clinical properties hampers ranking. Moreover, we find that ambiguous labels of failed implantations, due to either low quality embryos or poor clinical factors, confound both the optimal ranking and even implantation prediction. To overcome these limitations, we propose conceptual and practical steps to enhance machine-learning driven IVF solutions. These consist of separating the optimizing of implantation from ranking by focusing on visual properties for ranking, and reducing label ambiguity.


2019 ◽  
Vol 21 (4) ◽  
pp. 200-209 ◽  
Author(s):  
Swati Viviyan Lagah ◽  
Tanushri Jerath Sood ◽  
Prabhat Palta ◽  
Manishi Mukesh ◽  
Manmohan Singh Chauhan ◽  
...  

2007 ◽  
Vol 88 ◽  
pp. S152
Author(s):  
E.B. Johnston-MacAnanny ◽  
A.J. DiLuigi ◽  
L.L. Engmann ◽  
D.B. Maier ◽  
C.A. Benadiva ◽  
...  

1985 ◽  
Vol 43 (2) ◽  
pp. 251-254 ◽  
Author(s):  
Michael P. Diamond ◽  
Bobby W. Webster ◽  
Catherine H. Garner ◽  
William K. Vaughn ◽  
Wayne S. Maxson ◽  
...  

Author(s):  
Helena Bleeker

Pre-implantation genetic diagnosis (PGD) follows in vitro fertilization (IVF) of several ova. Negative selection (NS), or the discarding of embryos containing undesirable alleles, is currently being performed in IVF clinics. Conversely, positive selection (PS) is the discarding of embryos that do not contain a desirable allele. In other words, PS keeps an embryo because it contains a desirable genetic profile. There are many groups that support NS but there are far fewer who support PS. The bioconservative philosophy, led by philosophers such as Leon Kass, opposes PS and bioliberalism in general. Conversely, NS (and PS) of embryos resonates best of all with the bioliberalism philosophy. More specifically, a subset of bioliberalism, called transhumanism. In order to find NS morally permissible and PS morally unacceptable, one must support one’s position by making a moral distinction between the two types of selection. The major claims against PS include that it is not medically serious, that it propagates eugenics, that it propagates sex selection and that it elicits a moral repugnance which proves its immorality. In analyzing these arguments, I hope to show that none of them are consistent in their application, and that their inability to be applied universally significantly weakens their case. 


2018 ◽  
Vol 42 (1) ◽  
pp. 79-86
Author(s):  
Ihsan H. S. Al-Timimi

     The main objectives of this study is the separation of X from Y bearing epididymal spermatozoa of local buck by swim-up, and the use of this spermatozoa for in vitro fertilization to determine the percentage of produced male and female embryos. The sex of produced embryo was identified by polymerase chain reaction. Testis of the local buck were obtained from Al-Shu'alah abattoir and the epididymal spermatozoa were harvested from the cauda by and submitted to in vitro maturation prior to separation of X from Y bearing spermatozoa and prior to their use for in vitro fertilization. For the separation of epididymal spermatozoa, swim-up technique was used with centrifugation at 200×g or 300×g. The centrifugation at 200×g showed that 41.84±1.39 % of spermatozoa were detected in the supernatant while the precipitate contained 50.69±0.71 and the mean of the sperm lost was 7.65±0.93. After centrifugation, spermatozoa in the supernatant were used for in vitro fertilization of matured oocytes. The sex of in vitro produced goat embryos was determined by polymerase chain reaction using specific primers to detect of SRY gene. The percentage of total goat embryos obtained after in vitro fertilization by sperms selected using swim-up at centrifugation force of 200×g recorded 79.66 % male embryos while female embryos recorded only 20.33 %. At the end, the results showed the ability of selection male embryos in caprine by application of swim-up technique on epididymal spermatozoa with centrifugation at 200×g.


2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
X Zhang

Abstract Abstract text Some studies have discussed the use of artificial intelligence and machine learning in the assessment and selection of embryos for in vitro fertilization. Complete artificial intelligence acquired using CNN’s dark box algorithm could be highly useful in assessing in embryos, though it could be difficult to perform the external validation necessary to confirm its value. But due to the inherent drawbacks in complete artificial intelligence assessing in vitro developmental embryos, such as lacking results of discard embryos, dislocations between computer scientist and embryologist, low explanatory values in dark box algorithm, here, we suggest training computers to recognize the target region (internal pellucid zone region) and the features of embryos, then continuously score the embryos starting at in vitro fertilization through the zygote to the blastocyst stage. Parameters suitable for use with various endpoints in treatment sequence could be found by AI. Further clinical studies should be performed to validate the parameters and AI needed. Trial registration number: Study funding: Funding source:


Sign in / Sign up

Export Citation Format

Share Document