Are we ready to inject? Individualized LC-CUSUM training in ICSI

Advancements in the future of automating micromanipulation techniques in the IVF laboratory using deep convolutional neural networks

PURPOSE

To determine if deep learning artificial intelligence algorithms can be used to accurately identify key morphologic landmarks on oocytes and cleavage stage embryo images for micromanipulation procedures such as intracytoplasmic sperm injection (ICSI) or assisted hatching (AH).

METHODS

Two convolutional neural network (CNN) models were trained, validated, and tested over three replicates to identify key morphologic landmarks used to guide embryologists when performing micromanipulation procedures. The first model (CNN-ICSI) was trained (n = 13,992), validated (n = 1920), and tested (n = 3900) to identify the optimal location for ICSI through polar body identification. The second model (CNN-AH) was trained (n = 13,908), validated (n = 1908), and tested (n = 3888) to identify the optimal location for AH on the zona pellucida that maximizes distance from healthy blastomeres.

RESULTS

The CNN-ICSI model accurately identified the polar body and corresponding optimal ICSI location with 98.9% accuracy (95% CI 98.5-99.2%) with a receiver operator characteristic (ROC) with micro and macro area under the curves (AUC) of 1. The CNN-AH model accurately identified the optimal AH location with 99.41% accuracy (95% CI 99.11-99.62%) with a ROC with micro and macro AUCs of 1.

CONCLUSION

Deep CNN models demonstrate powerful potential in accurately identifying key landmarks on oocytes and cleavage stage embryos for micromanipulation. These findings are novel, essential stepping stones in the automation of micromanipulation procedures.

Fabrication on the microscale: a two-photon polymerized device for oocyte microinjection

Purpose

Intracytoplasmic sperm injection (ICSI) addresses male sub-fertility by injecting a spermatozoon into the oocyte. This challenging procedure requires the use of dual micromanipulators, with success influenced by inter-operator expertise. We hypothesized that minimizing oocyte handling during ICSI will simplify the procedure. To address this, we designed and fabricated a micrometer scale device that houses the oocyte and requires only one micromanipulator for microinjection.

Methods

The device consisted of 2 components, each of sub-cubic millimeter volume: a Pod and a Garage. These were fabricated using 2-photon polymerization. Toxicity was evaluated by culturing single-mouse presumptive zygotes (PZs) to the blastocyst stage within a Pod, with several Pods (and embryos) docked in a Garage. The development was compared to standard culture. The level of DNA damage/repair in resultant blastocysts was quantified (γH2A.X immunohistochemistry). To demonstrate the capability to carry out ICSI within the device, PZs were microinjected with 4-μm fluorescent microspheres and cultured to the blastocyst stage. Finally, the device was assessed for oocyte traceability and high-throughput microinjection capabilities and compared to standard microinjection practice using key parameters (pipette setup, holding then injecting oocytes).

Results

Compared to standard culture, embryo culture within Pods and a Garage showed no differences in development to the blastocyst stage or levels of DNA damage in resultant blastocysts. Furthermore, microinjection within our device removes the need for a holding pipette, improves traceability, and facilitates high-throughput microinjection.

Conclusion

This novel device could improve embryo production following ICSI by simplifying the procedure and thus decreasing inter-operator variability.

Supplementary information

The online version contains supplementary material available at 10.1007/s10815-022-02485-1.

Semi-automated versus manual embryo vitrification: inter-operator variability, time-saving, and clinical outcomes

PURPOSE

Does semi-automated vitrification have lower inter-operator variability and better clinical outcomes than manual vitrification?

METHODS

Retrospective analyses of 282 patients whose embryos had been cryopreserved, manually with Irvine®-CBS® (MV) or semi-automatically vitrified with the GAVI® method (AV) (from November 2017 to September 2020). Both techniques were performed during the same period by 5 operators. Inter-operator variability was statistically analyzed between operators who performed the vitrification and those who performed the warming process to compare the intact survival rate (% embryos with 100% intact blastomeres) and the positive survival rate (at least 50% intact blastomeres). Additionally, the complete vitrification time was assessed for the 2 techniques according to the number of vitrified embryos.

RESULTS

Manual vitrification involved warming 338 embryos in 266 cycles for 181 couples compared to 212 embryos in 162 AV cycles for 101 patients. The positive survival rate was higher (p < 0.05) after MV (96%; 323/338) than after AV (90%; 191/212). The intact survival rate (86 vs 84%) and the clinical pregnancy rate (27 vs 22%) were not significantly different between MV and AV. Regarding the inter-operator variability, no significant difference in positive and intact survival rate was evident between the 5 technicians, neither by vitrification nor by warming steps with MV and AV. Concerning time-saving, the MV technique proved to be quicker than AV (minus 11 ± 9 min).

CONCLUSIONS

Manual vitrification exhibited favorable total survival rates and was more time efficient, while both MV and AV cooling and warming treatments showed little operator variability.

The value of the modern embryologist to a successful IVF system: revisiting an age-old question

Background

The embryology laboratory remains one of the primary factors influencing the overall performance of the IVF clinic. Clinical embryology, however, has undergone remarkable advancements over the last decade. These developments in both practice and education have been driven together by science and technology.

Main body

The changes in clinical embryology practice have created a significant challenge for both the profession and the embryologist. New competencies for embryologists have subsequently emerged to provide and manage high-quality services for their patients and clinics. Embryologists’ efficacy behind the scenes reflects positively on the success of the fertility clinic. This framework will serve as the flagship document to shed light on the often-overlooked value of the embryologist as an intellectual and intangible asset for the clinic.

Conclusion

To fully leverage a modern embryologist’s skill set, significant investment is required from the IVF clinics’ leadership, which is associated with a substantial return on the IVF clinic’s success. From their side, embryologists should be up to date on further developments and innovations. On the other hand, mentors need to mend the curriculum to allow for better training of high-caliber embryologists.

Evaluation of the effect of piezo-intracytoplasmic sperm injection on the laboratory, clinical, and neonatal outcomes

PURPOSE

Limited research has been published on the effect of piezo-assisted intracytoplasmic sperm injection (P-ICSI). We evaluated the effect of P-ICSI on the laboratory, clinical, and neonatal outcomes.

METHODS

This retrospective study was based on the data collected between April 2011 and October 2016. Total 1348 mature oocytes from 145 patients were analyzed. Laboratory, clinical, and neonatal outcomes of those given conventional intracytoplasmic sperm injection (C-ICSI) and those administered P-ICSI were examined.

RESULTS

P-ICSI showed significantly more favorable results, with a survival rate of 97.0% (C-ICSI: 94.1%, P < .010) and a fertilization rate of 83.5% (C-ICSI: 70.6%, P < .001). There were no differences in the blastocyst development rate, implantation rate, miscarriage rate, live birth rate, gestational age, birth weight, proportion of male neonates, cesarean section rate, and congenital abnormalities between the two patient groups.

CONCLUSIONS

Our comparison of P-ICSI with C-ICSI showed that P-ICSI significantly improved the survival and fertilization.

Learning Curve for Percutaneous Endoscopic Lumbar Diskectomy in Bi-needle Technique Using Cumulative Summation Test for Learning Curve

BACKGROUND

The purpose of this study was to determine the number of cases needed to achieve the level of competence for percutaneous endoscopic lumbar diskectomy (PELD) via the bi-needle technique using the cumulative summation test for learning curve (LC-CUSUM).

METHODS

A retrospective design was used. We included 60 patients who underwent a single-level PELD via the bi-needle technique performed by a single surgeon. The surgeon had 5 years of experience in open surgery including the transforaminal endoscopic spine system and Yeung endoscopic spine system but no experience in the bi-needle technique. Surgery success was defined as an operative time <60 minutes, and the acceptable procedure was completed within 3 times of C-arm fluoroscopies. The LC-CUSUM was used to analyze the data.

RESULTS

The average operative time for PELD via the bi-needle technique was 58.3 ± 12.4 minutes. The mean operative time was 65.7 ± 12.1 minutes in the early learning period (30 cases) and 51.0 ± 7.5 minutes in the late learning period (30 cases) (P < 0.05). On the basis of the evaluation indexes of the operative time and radioactive exposure, the LC-CUSUM signaled proficiency for the bi-needle technique at the 50th-54th operation. Seven cases of complications were observed during the whole learning process, with 6 in the early period and 1 in the late period (P < 0.05).

CONCLUSIONS

The novel bi-needle technique is safe and effective for PELD with appropriate patients, and the learning curve is acceptable. A substantial learning period (50-54 cases) is needed before a spine surgeon can master the bi-needle technique.