An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization.

Medical Assisted Reproduction proved its efficacy to treat the vast majority forms of infertility. One of the key procedures in this treatment is the selection and transfer of the embryo with the highest developmental potential. To assess this potential, clinical embryologists routinely work with static images (morphological assessment) or short video sequences (time-lapse annotation). Recently, Artificial Intelligence models were utilized to support the embryo selection procedure. Even though they have proven their great potential in different in vitro fertilization settings, there is still considerable room for improvement. To support the advancement of algorithms in this research field, we built a dataset consisting of static blastocyst images and additional annotations. As such, Gardner criteria annotations, depicting a morphological blastocyst rating scheme, and collected clinical parameters are provided. The presented dataset is intended to be used to train deep learning models on static morphological images to predict Gardner's criteria and clinical outcomes such as live birth. A benchmark of human expert's performance in annotating Gardner criteria is provided.

MiR-182-5p and miR-375-3p Have Higher Performance Than PSA in Discriminating Prostate Cancer from Benign Prostate Hyperplasia.

Prostate cancer (PCa) is the most commonly diagnosed neoplasm among men. Since it often resembles benign prostate hyperplasia (BPH), biomarkers with a higher differential value than PSA are required. Epigenetic biomarkers in liquid biopsies, especially miRNA, could address this challenge. The absolute expression of miR-375-3p, miR-182-5p, miR-21-5p, and miR-148a-3p were quantified in blood plasma and seminal plasma of 65 PCa and 58 BPH patients by digital droplet PCR. The sensitivity and specificity of these microRNAs were determined using ROC curve analysis. The higher expression of miR-182-5p and miR-375-3p in the blood plasma of PCa patients was statistically significant as compared to BPH (p = 0.0363 and 0.0226, respectively). Their combination achieved a specificity of 90.2% for predicting positive or negative biopsy results, while PSA cut-off of 4 µg/L performed with only 1.7% specificity. In seminal plasma, miR-375-3p, miR-182-5p, and miR-21-5p showed a statistically significantly higher expression in PCa patients with PSA >10 µg/L compared to ones with PSA ≤10 µg/L. MiR-182-5p and miR-375-3p in blood plasma show higher performance than PSA in discriminating PCa from BPH. Seminal plasma requires further investigation as it represents an obvious source for PCa biomarker identification.

Undetectable Serum Levels of Anti-Müllerian Hormone in Women with Ovarian Hyperstimulation Syndrome During In Vitro Fertilization and Successful Pregnancy Outcome: Case Report.

We report a unique case of undetectable serum levels of anti-müllerian hormone (AMH) in women with polycystic ovary syndrome (PCOS) who developed ovarian hyperstimulation syndrome (OHSS) during in vitro fertilization (IVF). A case is described of a 28-year-old woman with clinical symptoms of PCOS and AMH serum level below analytical sensitivity (<1.0 pmol/L). After undergoing controlled ovarian stimulation, the patient developed OHSS. After follicle aspiration, seven oocytes were recovered. Three of them were used for intracytoplasmic sperm injection (ICSI) and fertilized, but with unsuccessful pregnancy outcome. A successful pregnancy was achieved in the second IVF/ICSI cycle with six oocytes retrieved and three embryos transferred. At 39 weeks of gestation, the patient delivered a healthy baby weighing 3930 g and 50 cm long. In conclusion, although AMH is considered a useful tool in ovarian reserve assessment and in predicting response to controlled ovarian hyperstimulation, the case presented shows that AMH should not be used as an independent ovarian marker.

Synergetic Effects of K, Ca, Cu and Zn in Human Semen in Relation to Parameters Indicative of Spontaneous Hyperactivation of Spermatozoa.

We have observed that sperm quality parameters indicative of spermatozoa hyperactivation such are lower "linearity" and "straightness", and as showed by this research "elongation", were more pronounced in patients with normal spermiogram compared to the group of men with reduced sperm motility who were undergoing routine in vitro fertilisation. The research encompassed 97 men diagnosed with normozoospermia (n = 20), asthenozoospermia (n = 54) and oligoasthenozoospermia (n = 23). The findings indicate that sperm quality of patients with normal spermiogram diagnosed according to WHO criteria, may be compromised by showing premature spontaneous hyperactivation which can decrease the chances of natural conception. We assessed synergistic effects of multiple chemical elements in ejaculated semen to find if premature spontaneous hyperactivation of spermatozoa can be a sign of imbalanced semen composition especially of elements K, Ca, Cu and Zn. Human semen samples showing low or high baseline status of chemical elements concentrations were found in samples from all three diagnostic groups. However, correlation of K/Ca and Cu/Zn ratios, taking into account samples from all three groups of men, were negative at statistical significance level p = 0.01. We tested if the negative correlation between K/Ca and Cu/Zn ratio works for greater number of semen samples. We found the negative correlation to be valid for 175 semen samples at statistical significance of p = 0.00002. The ratio of K/Ca and Cu/Zn, i.e. increased concentrations of K and Zn in comparison to concentrations of Ca and Cu, were associated with a decrease of "straightness" in the group of men with normal spermiogram and pronounced spontaneous hyperactivation of spermatozoa, implying that these elements act in synergy and that the balance of elements and not their absolute concentrations plays the major role in premature spermatozoa hyperactivation in ejaculated semen.

Follicular fluid anti-Müllerian hormone: a predictive marker of fertilization capacity of MII oocytes.

PURPOSE: The present study aimed to correlate anti-Müllerian hormone (AMH) levels in follicular fluid (FF) with oocyte maturity stages, morphological quality of metaphase II (MII) oocyte and fertilization capacity of MII oocytes. METHODS: A total of 92 infertile women undergoing controlled ovarian stimulation and intracytoplasmic sperm injection were analyzed. Patients were divided into two groups according to age: <35 years (n = 43) and ≥35 years (n = 49). An FF sample was obtained from a single dominant follicle in each patient for a total of 92 follicular fluid samples analyzed. AMH levels in serum and follicular fluid were measured by enzyme-linked immunosorbent assay. Mature MII oocytes, zygotes, and embryos were assessed for morphological quality. RESULTS: Serum AMH levels were significantly higher in patients aged <35 years. No correlation was observed between FF AMH level and oocyte maturation stages or morphological quality of MII oocyte. Significantly lower FF AMH levels were observed in fertilized MII oocytes than in non-fertilized MII oocytes in patients aged <35 years (2.56 ± 2.0 ng/ml vs. 4.81 ± 4.14 ng/ml; p = 0.032). CONCLUSIONS: The present study revealed no correlation between FF AMH and oocyte maturity stage or morphological quality of MII oocyte. However, FF AMH might be a predictive marker for fertilization capacity of MII oocytes.