Using Deep Learning Algorithm: The Study Of Sperm Head Vacuoles And Its Correlation With Protamine MRNA Ratio

Document Type : Original Article


1 Department of Biology, Faculty of Science, University of Guilan, Rasht, Iran

2 Cellular and Molecular Research Center, Guilan University of Medical Sciences, Rasht, Iran

3 Reproductive Health Research Center (IVF Center), Alzahra Educational and Remedial Center, Guilan University of Medical Sciences, Rasht, Iran


Objective: It is necessary to evaluate fertility effective agents to predict assisted reproduction outcomes. This study was
designed to examine sperm vacuole characteristics, and its association with sperm chromatin status and protamine-1 (PRM1) to protamine-2 (PRM2) ratio, to predict assisted pregnancy outcomes.
Materials and Methods: In this experimental study, ninety eight semen samples from infertile men were classified based
on Vanderzwalmen’s criteria as follows: grade I: no vacuoles; grade II: ≤2 small vacuoles; grade III: ≥1 large vacuole and grade IV: large vacuole with other abnormalities. The location, frequency and size of vacuoles were assessed using high magnification, a deep learning algorithm, and scanning electron microscopy (SEM). The chromatin integrity, condensation, viability and acrosome integrity, and protamination status were evaluated for vacuolated samples by toluidine blue (TB) staining, aniline blue, triple staining, and CMA3 staining, respectively. Also, Protamine-1 and protamine-2 genes expression was analysed by reverse transcription-quantitative polymerase chain reaction (PCR).
The assisted reproduction outcomes were also followed for each cycle.
Results: The results show a significant correlation between the vacuole size (III and IV) and abnormal sperm chromatin
condensation (P=0.03 and P=0.02, respectively), and also, protamine-deficient (P=0.04 and P=0.03, respectively). The percentage of reacting acrosomes was significantly higher in the grades III and IV spermatozoa in comparison with normal group. The vacuolated spermatozoa with grade IV showed a high protamine mRNA ratio (PRM-2 was underexpressed, P=0.01). In the IVF cycles, we observed a negative association between sperm head vacuole and fertilization rate (P=0.01). This negative association was also significantly observed in pregnancy and live birth rate in the groups with grade III and IV (P=0.04 and P=0.03, respectively).
Conclusion: The results of our study highlight the importance sperm parameters such as sperm head vacuole characteristics, particularly those parameters with the potency of reflecting protamine-deficiency and in vitro fertilization/
intracytoplasmic sperm injection (IVF/ICSI) outcomes predicting.