Improved pregnancy prediction performance in an updated deep-learning embryo selection model: a retrospective independent validation study.

RESEARCH QUESTION: What is the effect of increasing training data on the performance of ongoing pregnancy prediction after single vitrified-warmed blastocyst transfer (SVBT) in a deep-learning model? DESIGN: A total of 3960 SVBT cycles were retrospectively analysed. Embryos were stratified according to the Society for Assisted Reproductive Technology age groups. Embryos were scored by deep-learning models iDAScore v1.0 (IDA-V1) and iDAScore v2.0 (IDA-V2) (15% more training data than v1.0) and by Gardner grading. The discriminative performance of the pregnancy prediction for each embryo scoring model was compared using the area under the curve (AUC) of the receiver operating characteristic curve for each maternal age group. RESULTS: The AUC of iDA-V2, iDA-V1 and Gardener grading in all cohort were 0.736, 0.720 and 0.702, respectively. iDA-V2 was significantly higher than iDA-V1 and Gardener grading (P < 0.0001). Group > 35 years (n = 757): the AUC of iDA-V2 was significantly higher than Gardener grading (0.718 versus 0.694, P = 0.015); group aged 35-37 years (n = 821), the AUC of iDA-V2 was significantly higher than iDA-V1 (0.712 versus 0.696, P = 0.035); group aged 41-42 years (n = 715, the AUC of iDA-V2 was significantly higher than Gardener grading (0.745 versus 0.696, P = 0.007); group > 42 years (n = 660) and group aged 38-40 years (n = 1007), no significant differences were found between the groups. CONCLUSION: The performance of deep learning models for pregnancy prediction will be improved by increasing the size of the training data.

Early transcriptomic changes in peripheral blood 7 days after embryo transfer in dairy cattle.

A common goal of the dairy industry is to shorten the calving interval to reap several benefits associated with improved fertility. Early pregnancy detection is crucial to shorten this interval, allowing for prompt re-insemination of cows that failed to conceive after the first service. Currently, the industry lacks a method to accurately predict pregnancy within the first 3 wk. The polypeptide cytokine IFN-tau (IFNT) is the primary signal for maternal recognition of pregnancy in ruminants. As IFNT is released from the early conceptus, it initiates a cascade of effects, including upregulation of IFN-stimulated genes (ISG). Expression of ISG can be detected in the peripheral blood. The present study aimed to characterize peripheral transcriptomic changes, including the ISG, as early as d 7 after embryo transfer. A total of 170 Holstein heifers received in vitro-produced embryos. Whole blood was collected from these heifers within 24 h of the embryo transfer (d 0), d 7, and d 14 after embryo transfer. The heifers were divided into 2 groups, pregnant and nonpregnant, based on pregnancy diagnosis on d 28 via ultrasound. Total RNA was extracted from the peripheral blood of pregnant and nonpregnant heifers, pooled and sequenced. Expression analysis on d 7 heifers resulted in 13 significantly differentially expressed genes mostly related to innate immunity. Differential expression analysis comparing pregnant heifers on d 0 to the same heifers on d 14 showed 51 significantly differentially expressed genes. Eight genes were further quantified through reverse-transcription quantitative real-time PCR for biological validation. On d 7 after embryo transfer, mRNA transcriptions of EDN1, CXCL3, CCL4, and IL1A were significantly upregulated in pregnant heifers (n = 14) compared with nonpregnant heifers (n = 14), with respective fold changes of 8.10, 18.12, 29.60, and 29.97. Although on d 14 after embryo transfer, mRNA transcriptions of ISG15, MX2, OASY1, and IFI6 were significantly upregulated in the blood of pregnant heifers (n = 14) compared with the same heifers on d 0, with respective fold changes of 5.09, 2.59, 3.89, and 3.08. These findings demonstrate that several immune-related genes and ISG are activated during the first 2 wk after embryo transfer, which may explain how the maternal immune system accommodates the allogenic conceptus. To further investigate the diagnostic potentials of these genes, future studies are warranted to analyze the specificity and sensitivity of these biomarkers to predict early pregnancy.

External validation of a model for selecting day 3 embryos for transfer based upon deep learning and time-lapse imaging.

RESEARCH QUESTION: Could objective embryo assessment using iDAScore Version 2.0 perform as well as conventional morphological assessment? DESIGN: A retrospective cohort study of fresh day 3 embryo transfer cycles was conducted at a large reproductive medicine centre. In total, 7786 embryos from 4328 cycles with known implantation data were cultured in a time-lapse incubator and included in the study. Fetal heartbeat (FHB) rate was analysed retrospectively using iDAScore Version 2.0 and conventional morphological assessment associated with the transferred embryos. The pregnancy-prediction performance of the two assessment methods was compared using area under the curve (AUC) values for predicting FHB. RESULTS: AUC values were significantly higher for iDAScore compared with morphological assessment for all cycles (0.62 versus 0.60; P = 0.005), single-embryo transfer cycles (0.63 versus 0.60; P = 0.043) and double-embryo transfer cycles (0.61 versus 0.59; P = 0.012). For the age subgroups, AUC values were significantly higher for iDAScore compared with morphological assessment in the <35 years subgroup (0.62 versus 0.60; P = 0.009); however, no significant difference was found in the ≥35 years subgroup. In terms of the number of blastomeres, AUC values were significantly higher for iDAScore compared with morphological assessment for both the <8c subgroup (0.67 versus 0.56; P < 0.001) and the ≥8c subgroup (0.58 versus 0.55; P = 0.012). CONCLUSIONS: iDAScore Version 2.0 performed as well as, or better than, conventional morphological assessment in fresh day 3 embryo transfer cycles. iDAScore Version 2.0 may therefore constitute a promising tool for selecting embryos with the highest likelihood of implantation.

Deep learning analysis of endometrial histology as a promising tool to predict the chance of pregnancy after frozen embryo transfers.

PURPOSE: Endometrial histology on hematoxylin and eosin (H&E)-stained preparations provides information associated with receptivity. However, traditional histological examination by Noyes' dating method is of limited value as it is prone to subjectivity and is not well correlated with fertility status or pregnancy outcome. This study aims to mitigate the weaknesses of Noyes' dating by analyzing endometrial histology through deep learning (DL) algorithm to predict the chance of pregnancy. METHODS: Endometrial biopsies were taken during the window of receptivity from healthy volunteers in natural menstrual cycles (group A) and infertile patients undergoing mock artificial cycles (group B). H&E staining was performed followed by whole slide image scanning for DL analysis. RESULTS: In a proof-of-concept trial to differentiate group A (n=24) vs. B (n=37), a DL-based binary classifier was trained, cross-validated, and achieved 100% for accuracy. Patients in group B underwent subsequent frozen-thawed embryo transfers (FETs) and were further categorized into "pregnant (n=15)" or "non-pregnant (n=18)" sub-groups based on the outcomes. In the following trial to predict pregnancy outcome in group B, the DL-based binary classifier yielded 77.8% for accuracy. Its performance was further validated by an accuracy of 75% in a "held-out" test set where patients had euploid embryo transfers. Furthermore, the DL model identified histo-characteristics including stromal edema, glandular secretion, and endometrial vascularity as important features related to pregnancy prediction. CONCLUSIONS: DL-based endometrial histology analysis demonstrated its feasibility and robustness in pregnancy prediction for patients undergoing FETs, indicating its value as a prognostic tool in fertility treatment.

Pregnancy status predicted using milk mid-infrared spectra from dairy cattle.

Accurate and timely pregnancy diagnosis is an important component of effective herd management in dairy cattle. Predicting pregnancy from Fourier-transform mid-infrared (FT-MIR) spectroscopy data is of particular interest because the data are often already available from routine milk testing. The purpose of this study was to evaluate how well pregnancy status could be predicted in a large data set of 1,161,436 FT-MIR milk spectra records from 863,982 mixed-breed pasture-based New Zealand dairy cattle managed within seasonal calving systems. Three strategies were assessed for defining the nonpregnant cows when partitioning the records according to pregnancy status in the training population. Two of these used records for cows with a subsequent calving only, whereas the third also included records for cows without a subsequent calving. For each partitioning strategy, partial least squares discriminant analysis models were developed, whereby spectra from all the cows in 80% of herds were used to train the models, and predictions on cows in the remaining herds were used for validation. A separate data set was also used as a secondary validation, whereby pregnancy diagnosis had been assigned according to the presence of pregnancy-associated glycoproteins (PAG) in the milk samples. We examined different ways of accounting for stage of lactation in the prediction models, either by including it as an effect in the prediction model, or by pre-adjusting spectra before fitting the model. For a subset of strategies, we also assessed prediction accuracies from deep learning approaches, utilizing either the raw spectra or images of spectra. Across all strategies, prediction accuracies were highest for models using the unadjusted spectra as model predictors. Strategies for cows with a subsequent calving performed well in herd-independent validation with sensitivities above 0.79, specificities above 0.91 and area under the receiver operating characteristic curve (AUC) values over 0.91. However, for these strategies, the specificity to predict nonpregnant cows in the external PAG data set was poor (0.002-0.04). The best performing models were those that included records for cows without a subsequent calving, and used unadjusted spectra and days in milk as predictors, with consistent results observed across the training, herd-independent validation and PAG data sets. For the partial least squares discriminant analysis model, sensitivity was 0.71, specificity was 0.54 and AUC values were 0.68 in the PAG data set; and for an image-based deep learning model, the sensitivity was 0.74, specificity was 0.52 and the AUC value was 0.69. Our results demonstrate that in pasture-based seasonal calving herds, confounding between pregnancy status and spectral changes associated with stage of lactation can inflate prediction accuracies. When the effect of this confounding was reduced, prediction accuracies were not sufficiently high enough to use as a sole indicator of pregnancy status.

Endometrial laminin subunit beta-3 expression associates with reproductive outcome in patients with repeated implantation failure.

PURPOSE: Endometrial laminin subunit beta-3 (LAMB3) is a candidate gene whose expression distinguishes the endometrial window of receptivity (WOR) in human. This study aims to examine endometrial LAMB3 levels in patients with repeated implantation failure (RIF), in order to assess the ability of LAMB3 to predict pregnancy outcome. METHODS: Endometrial biopsies were taken during the WOR from 21 healthy volunteers in natural menstrual cycles and from 50 RIF patients in mock cycles prior to frozen embryo transfer (FET) cycles. Immunohistochemistry (IHC) staining of LAMB3 was performed, and the H-score was correlated with the pregnancy outcome in subsequent FETs. RESULTS: In healthy volunteers, endometrial LAMB3 was demonstrated to be highly expressed during the WOR with the staining exclusively in the cytoplasm of the epithelial cells. In a discovery set of RIF patients, the LAMB3 expression level was found to be significantly higher in those who conceived compared to those who did not in subsequent FETs. A receiving operator characteristic (ROC) analysis revealed an area under the curve (AUC) of 0.7818 (95% confidence interval 59.92-96.44%) with an H-score cutoff of 4.129 to differentiate cases with positive or negative pregnancy outcomes. This cutoff achieved an accuracy of 75% in pregnancy prediction in a following validation set of RIF patients, in which the pregnancy rate in subsequent FETs was three-fold higher when the mock cycle LAMB3 H-score was ≥ 4.129 compared to < 4.129. CONCLUSIONS: IHC measurement of endometrial LAMB3 expression could be a promising prognostic method to predict pregnancy outcome for RIF patients undergoing FETs.

Specific gene expression differences in cumulus cells as potential biomarkers of pregnancy.

The development of an objective and accurate test that could help select embryos with the highest chance of achieving pregnancy in IVF procedures is an important goal of reproductive medicine. For this purpose, cumulus cell gene expression is being studied to find biomarkers of pregnancy. Several recent studies have proposed potential biomarkers of pregnancy expressed in cumulus cells; however, these have mostly not been validated on an independent set of samples. The aim of this study was to analyse the expression of EFNB2, RGS2 and VCAN genes proposed as biomarkers of pregnancy in cumulus cells by quantitative polymerase chain reaction. Gene expression was evaluated in 43 individual cumulus cell samples, derived from a highly homogenous group of 43 women. The same protocol for ovarian stimulation was used for all women, and elective single embryo transfer was performed. Expression levels of RGS2 and VCAN did not differ between cumulus cells of implanted and non-implanted embryos. EFNB2 showed borderline higher expression in cumulus cells of non-implanted embryos, which is contradictory to previous studies. Altogether, the results of previous studies in which EFNB2, RGS2 and VCAN were proposed as biomarkers of pregnancy could not be replicated in our set of cumulus cell samples.

Predicting Pregnancy Outcome in Dairy Cows: The Role of IGF-1 and Progesterone.

The purpose of this study was to determine the link between insulin-like growth factor 1 (IGF-1), progesterone (PROG), non-esterified fatty acids (NEFAs), ß-hydroxybutyrate (BHB), and glucose (GLU) and pregnancy probability after the first artificial insemination (AI) and during the first 100 days in milk (DIM), during the critical transition period. We determined levels of serum IGF-1, PROG, NEFA, BHB, and GLU in Holstein dairy cows via ELISA, using blood samples collected 7 days before parturition (DAP) until 21 days postparturition (DPP). The group was split into cows diagnosed pregnant at 100 DIM (PREG) and those that did not conceive at 100 and 150 DIM (NPREG). Serum IGF-1 and PROG median levels at 7 DAP were significantly higher in PREG vs. NPREG (p = 0.029), the only statistically significant differences across the subgroups. At 7 DAP, IGF-1 levels within the initial group showed a strong negative correlation with PROG (r = -0.693; p = 0.006), while for the PREG subgroup, the IGF-1 levels exhibited a very strong positive correlation with GLU (r = 0.860; p = 0.011) and NEFA (r = 0.872; p = 0.013). IGF-1 and PROG levels detected at 7 DAP may be useful to predict pregnancy at 100 DIM. The positive correlation of NEFA and GLU levels during the transition period demonstrates that the initial group is not in NEB; thus, the NEFA level was not a decisive factor for reproduction success.

Predicting the Outcome of Equine Artificial Inseminations Using Chilled Semen.

This study aimed to determine whether an analysis of stallion ejaculate could accurately predict the likelihood of pregnancy resulting from artificial insemination in mares. This study involved 46 inseminations of 41 mares, using 7 standardbred stallions over a 5-week period at an Australian pacing stud. Semen quality was assessed immediately after collection and again after chilling at ~5 °C for 24 h. The assessment involved evaluating ejaculate volume, sperm concentration, and motility parameters using an iSperm® Equine portable device. After the initial evaluation, a subpopulation of cells was subjected to a migration assay through a 5 µm polycarbonate filter within a Samson™ isolation chamber over a 15 min period. The cells were assessed for their concentration, motility parameters, and ability to reduce the membrane impermeant tetrazolium salt WST-1. The data, combined with the stallion and mare's ages, were used to predict the likelihood of pregnancy, as confirmed by rectal ultrasound sonography performed 14 days post ovulation. The criteria used to predict pregnancy were optimized for each individual stallion, resulting in an overall accuracy of 87.9% if analyzed pre-chilling and 95% if analyzed post-chilling. This study suggests that an analysis of stallion ejaculate can be used to predict the likelihood of pregnancy resulting from artificial insemination in mares with a high level of accuracy.

GVBD rate is an independent predictor for pregnancy in ICSI patients with surplus immature oocytes.

Introduction: It was reported that there were still up to 30% immature retrieved oocyte at germinal vesicle (GV) or metaphase I (MI) stage. Whether the spontaneous maturity competency of immature oocytes associated to the clinical outcome of in vitro fertilization (IVF) cycles remains unclear and unexplored. This study aimed to investigate how the oocyte developmental parameters in in vitro maturation (IVM) affect clinical outcomes of intracytoplasmic sperm injection (ICSI) cycles. Methods: This retrospective cohort study included couples undergoing ICSI in a university-affiliated hospital. Surplus immature oocytes during ICSI were collected and cultured in vitro. The numbers of germinal vesicle (GV) oocytes undergoing GV breakdown (GVBD) and polar body 1 extrusion within 24 h culture were recorded. The main outcome measurements were demographic baselines and oocyte developmental parameters in IVM associated with pregnancy outcomes. Results: A total of 191 couples were included with an overall GVBD rate of 63.7% (327/513) and oocyte maturation rate of 46.8% (240/513). 53.4% (102/191) of them had embryos transferred freshly, which originated from metaphase II oocytes that matured spontaneously in vivo, and 60.8% (62/102) got pregnant. Among factors with a P-value < 0.2 in univariate logistic regression analyses of pregnancy correlation, GVBD rate (OR 3.220, 95% CI 1.060-9.782, P=0.039) and progesterone level on human chorionic gonadotropin (HCG) day (OR 0.231, 95% CI 0.056-0.949, P=0.042) remained significant in the multivariate model. The area under the curve (AUC) of the predictive nomogram was 0.729 (95% CI 0.632-0.826) with an acceptable calibration. Moreover, decision curve analyses illustrated the superior overall net benefit of models that included the GVBD rate in clinical decisions within a wide range of threshold probabilities. Conclusion: In conclusion, GVBD rate and progesterone level on HCG day may be associated with pregnancy outcomes in infertile couples during the regular ICSI procedure. An elevated GVBD rate within 24 h may greatly increase the likelihood of pregnancy in infertile couples during ICSI. This preliminary study may optimize clinical pregnancy prediction, which provides support in decision-making in clinical practice.

Pregnancy prediction performance of an annotation-free embryo scoring system on the basis of deep learning after single vitrified-warmed blastocyst transfer: a single-center large cohort retrospective study.

OBJECTIVE: To analyze the performance of an annotation-free embryo scoring system on the basis of deep learning for pregnancy prediction after single vitrified blastocyst transfer (SVBT) compared with the performance of other blastocyst grading systems dependent on annotation or morphology scores. DESIGN: A single-center large cohort retrospective study from an independent validation test. SETTING: Infertility clinic. PATIENT(S): Patients who underwent SVBT cycles (3,018 cycles, mean ± SD patient age 39.3 ± 4.0 years). INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): The pregnancy prediction performances of each embryo scoring model were compared using the area under curve (AUC) for predicting the fetal heartbeat status for each maternal age group. RESULT(S): The AUCs of the <35 years age group (n = 389) for pregnancy prediction were 0.72 for iDAScore, 0.66 for KIDScore, and 0.64 for the Gardner criteria. The AUC of iDAScore was significantly greater than those of the other two models. For the 35-37 years age group (n = 514), the AUCs were 0.68, 0.68, and 0.65 for iDAScore, KIDScore, and the Gardner criteria, respectively, and were not significantly different. The AUCs of the 38-40 years age group (n = 796) were 0.67 for iDAScore, 0.65 for KIDScore, and 0.64 for the Gardner criteria, and there were no significant differences. The AUCs of the 41-42 years age group (n = 636) were 0.66, 0.66, and 0.63 for iDAScore, KIDScore, and the Gardner criteria, respectively, and there were no significant differences among the pregnancy prediction models. For the >42 years age group (n = 389), the AUCs were 0.76 for iDAScore, 0.75 for KIDScore, and 0.75 for the Gardner criteria, and there were no significant differences. Thus, iDAScore AUC was either the highest or equal to the highest AUC for all age groups, although a significant difference was observed only in the youngest age group. CONCLUSION(S): Our results showed that objective embryo assessment by a completely automatic and annotation-free model, iDAScore, performed as well as or even better than more traditional embryo assessment or annotation-dependent ranking tools. iDAScore could be an optimal pregnancy prediction model after SVBT, especially in young patients.

Predicting pregnancy using large-scale data from a women's health tracking mobile application.

Predicting pregnancy has been a fundamental problem in women's health for more than 50 years. Previous datasets have been collected via carefully curated medical studies, but the recent growth of women's health tracking mobile apps offers potential for reaching a much broader population. However, the feasibility of predicting pregnancy from mobile health tracking data is unclear. Here we develop four models - a logistic regression model, and 3 LSTM models - to predict a woman's probability of becoming pregnant using data from a women's health tracking app, Clue by BioWink GmbH. Evaluating our models on a dataset of 79 million logs from 65,276 women with ground truth pregnancy test data, we show that our predicted pregnancy probabilities meaningfully stratify women: women in the top 10% of predicted probabilities have a 89% chance of becoming pregnant over 6 menstrual cycles, as compared to a 27% chance for women in the bottom 10%. We develop a technique for extracting interpretable time trends from our deep learning models, and show these trends are consistent with previous fertility research. Our findings illustrate the potential that women's health tracking data offers for predicting pregnancy on a broader population; we conclude by discussing the steps needed to fulfill this potential.

Improved timed-mating, non-invasive method using fewer unproven female rats with pregnancy validation via early body mass increases.

For studies requiring accurate conception-timing, reliable, efficient methods of detecting oestrus reduce time and costs, whilst improving welfare. Standard methods use vaginal cytology to stage cycle, and breeders are paired-up using approximately five proven females with proven males to achieve at least one conception on a specific day. We describe an alternative, fast, consistent, non-invasive method of timed-mating using detection of lordosis behaviour in Wistar and Lister-Hooded rats that used unproven females with high success rates. Rats under reverse lighting had body masses recorded pre-mating, day (d) 3-4, d8, d10 and d18 of pregnancy. Using only the presence of the oestrus dance to time-mate females for 24 hours, 89% of Wistar and 88% of Lister-Hooded rats successfully conceived. We did not observe behavioural oestrus in Sprague-Dawleys without males being present. Significant body mass increases following mating distinguished pregnant from non-pregnant rats, as early as d4 of pregnancy (10% ± 1.0 increase cf. 3% ± 1.2). The pattern of increases throughout gestation was similar for all pregnant rats until late pregnancy, when there were smaller increases for primi- and multiparous rats (32% ± 2.5; 25% ± 2.4), whereas nulliparous rats had highest gains (38% ± 1.5). This method demonstrated a distinct refinement of the previous timed-mating common practice used, as disturbance of females was minimised. Only the number required of nulli-, primi- or multiparous rats were mated, and body mass increases validated pregnancy status. This new breeding management method is now established practice for two strains of rat and has resulted in a reduction in animal use.

Maternal weight as an alternative determinant of the gestational day of Wistar rats housed in individually-ventilated cages.

One of the commonly used animal models in fertility, developmental and neurobiological studies is the laboratory rat. The early recognition of rat pregnancy and confirmation of the exact embryonic day are vital. The aim of this study was to investigate the correlation of maternal weight at the time of conception to its increase throughout gestation, aiming to develop a mathematical model, which can be used for the determination of the exact day of pregnancy, set the threshold, and monitor pregnancy from the onset. We studied a total of 173 Wistar rats with a mean body weight of 238.22 ± 34.9 g. After 72 h at the male's cages, we considered as Day 0 (D0) the day in which a copulatory plug or sperm was found during the vaginal smear examination. After that period the female animals were transferred into their cages, and weight monitoring started 14 days (D14) after D0, until parturition. Based on the statistical analysis, there is a correlation between maternal body weight at D0 and maternal body weight from D14 to D19. Moreover, the average weight gain from D14 to D19 is positively correlated to initial female body weight, while there is no correlation between each pregnant animal's weight from D14 to D19 and litter size. A mathematical model was developed as a tool for the verification of the day of pregnancy. In conclusion, continuous monitoring of maternal weight after D14 can be a reliable method for the recognition of pregnancy and determination of the exact gestational day.

Nomogram to predict ongoing pregnancy using age of women and serum biomarkers after in vitro fertilization cycles.

OBJECTIVE: To develop a nomogram for prediction of ongoing pregnancy after in vitro fertilization (IVF)-embryo transfer (ET) using age of women and serum biomarkers. STUDY DESIGN: Prospective longitudinal study of 103 patients undergoing IVF-ET at a university-based hospital. Serum HCG and progesterone levels were measured at the time of the pregnancy test (14 days after oocyte retrieval) and pregnancy outcomes were followed. The main outcome was ongoing pregnancy prediction. RESULTS: For the prediction of ongoing pregnancy, a combination of serum HCG, progesterone and age of the woman shows the best predictive accuracy (AUC 0.912 [95% CI 0.815-1.000], sensitivity 89.3%, specificity 80.0%, positive predictive value 89.3%, negative predictive value 80.0%). On the basis of these variables, we developed a nomogram to predict ongoing pregnancy. CONCLUSION: A nomogram could help to predict ongoing pregnancy after IVF-ET. The nomogram needs further validation to improve individualized prediction of ongoing pregnancy.

Avaliação morfofuncional do corpo lúteo para diagnóstico precoce de gestação 20 dias após IATF em vacas mestiças leiteiras / Morphological evaluation of corpus luteum for the diagnosis of 20-day pregnancy after IATF in crossbred cows

A detecção superprecoce de gestação é de grande relevância quando se trata do aumento da produtividade dos rebanhos, na tentativa de redução do tempo de serviço desses animais. Por tal relevância, objetivou-se utilizar a ultrassonografia (US) Doppler como ferramenta para predição de gestação, avaliando a irrigação do corpo lúteo (CL), vinte dias após IATF. Setenta e três vacas mestiças foram avaliadas 20 dias após IATF por US transretal. Para obtenção do diâmetro do CL (DCL) e sua área (ACL) utilizou-se o modo B, na mensuração da área de vascularização (VCL) e seu percentual no CL (VCL%) empregou-se o Doppler Colorido. As imagens foram classificadas com base na quantidade de pixels coloridos e sua distribuição no CL, em dois grupos: diagnóstico preditivo negativo de gestação (DPN) e preditivo positivo (DPP). No mesmo dia, a funcionalidade do CL foi determinada pela concentração plasmática de P4. O diagnóstico de gestação definitivo foi realizado por US 35 dias após as IATFs. Utilizou-se o teste t de Student (com P<0,05) na avaliação das variáveis. Grupo gestantes apresentou médias superiores (P<0,05) para todas as variáveis ao Grupo Não Gestantes. O diagnóstico preditivo demonstrou 83,33% de especificidade, sensibilidade de 100% e acurácia de 91,79%. Conclui-se que a US doppler do CL aos 20 dias pós IATF é um método confiável no diagnóstico precoce de gestação.(AU)

The super early gestation detection is of great relevance considering the increase of the herds' productivity, in an attempt to reduce the time of service of these animals. Due to this relevance, this study aimed to use Doppler ultrasonography as a tool for gestation prediction, evaluating the luteal body (CL) irrigation twenty days after FTAI. 73 crossbred cows were evaluated 20 days after FTAI through trans rectal US. In order to obtain the diameter of the CL (DCL) and its area (ACL), B mode was used. The Color Doppler was applied to measure the vascularization area (CLV) and its percentage in the CL (VCL %). The images were classified, based on the number of colored pixels and their distribution in CL, in two groups: negative predictive diagnosis of gestation (NPD) and positive predictive value (PPV). On the same day, LC functionality was determined based on P4 plasma concentration. The definitive gestation diagnosis was confirmed through US 35 days after the FTAIs. Student's T test (with P<0.05) was used to evaluate the variables. Pregnant group presented higher averages (P<0.05) for all variables compared to the Non-Pregnant Group. The predictive diagnosis showed 83.33% of specificity, 100% of sensitivity and 91.79% of accuracy. The conclusion is that the US Doppler at 20 days post FTAI is a reliable method for early gestation diagnosis.(AU)