Two-dimensional ultrasound results in underestimation of the ovarian follicle size compared to automated three-dimensional imaging in women undergoing IVF.

BACKGROUND: Traditionally, for the assessment of follicle growth during IVF, two-dimensional (2D) transvaginal ultrasound (US) is used. In the past few years three-dimensional (3D) US has also been introduced. OBJECTIVES: To compare follicular sizes between 2 and 3D ultrasound imaging on the final day of controlled ovarian stimulation. METHODS: A prospective observational cohort study including 121 women undergoing controlled ovarian stimulation (COS) between January 2017 and July 2018. All women were assessed by transvaginal 2D and 3D ultrasonography to measure ovarian follicle dimensions on the final day of COS. RESULTS: The mean difference in paired comparisons between the 3D and 2D US measurements in 25 women with monofollicular development was + 1.6 ± 2.5 mm for the x-dimension and + 1.7 ± 2.4 mm for the y-dimension; and in the total number of 1197 paired measurements of follicles the mean difference + 2.1 ± 3.3 mm and + 1.8 ± 3.9 mm for the x- and y-dimension respectively. In all cases the paired t-test showed that differences were statistically significant (p < 0.01). Further it was conjectured that the 2D underestimation results from the inherent difficulty to precisely place the US probe simultaneously on the perpendicular maximal of the x and y follicle diameters, leading to measurement errors that, by theory, are normally distributed. Running Monte-Carlo simulations based on these measurement errors it was found that both the mean difference and standard deviation are of the same magnitude as the ones found in real measurements, thus proving the conjecture. CONCLUSIONS: The utilisation of 3D US results in different measurements of the follicular dimensions, and volumes, when compared to conventional 2D US. The differences in the x- and y-dimensions may affect the outcome of an IVF cycle as they are used to define the day of triggering final oocyte maturation, which is associated with the yield of mature oocytes and the probability of live birth.

Evaluation of oocyte maturity using artificial intelligence quantification of follicle volume biomarker by three-dimensional ultrasound.

RESEARCH QUESTION: Can a novel deep learning-based follicle volume biomarker using three-dimensional ultrasound (3D-US) be established to aid in the assessment of oocyte maturity, timing of HCG administration and the individual prediction of ovarian hyper-response? DESIGN: A total of 515 IVF cases were enrolled, and 3D-US scanning was carried out on HCG administration day. A follicle volume biomarker established by means of a deep learning-based segmentation algorithm was used to calculate optimal leading follicle volume for predicting number of mature oocytes retrieved and optimizing HCG trigger timing. Performance of the novel biomarker cut-off value was compared with conventional two-dimensional ultrasound (2D-US) follicular diameter measurements in assessing oocyte retrieval outcome. Moreover, demographics, infertility work-up and ultrasound biomarkers were used to build models for predicting ovarian hyper-response. RESULTS: On the basis of the deep learning method, the optimal cut-off value of the follicle volume biomarker was determined to be 0.5 cm3 for predicting number of mature oocytes retrieved; its performance was significantly better than the conventional method (two-dimensional diameter measurement ≥10 mm). The cut-off value for leading follicle volume to optimize HCG trigger timing was determined to be 3.0 cm3 and was significantly associated with a higher number of mature oocytes retrieved (P = 0.01). Accuracy of the multi-layer perceptron model was better than two-dimensional diameter measurement (0.890 versus 0.785) and other multivariate classifiers in predicting ovarian hyper-response (P < 0.001). CONCLUSIONS: Deep learning segmentation methods and multivariate classifiers based on 3D-US were found to be potentially effective approaches for assessing mature oocyte retrieval outcome and individual prediction of ovarian hyper-response.

CR-Unet-Based Ultrasonic Follicle Monitoring to Reduce Diameter Variability and Generate Area Automatically as a Novel Biomarker for Follicular Maturity.

Follicle size is closely related to ovarian function and is an important biomarker in transvaginal ultrasound examinations for assessing follicular maturity during an assisted reproduction cycle. However, manual measurement is time consuming and subject to high inter- and intra- observer variability. Based on the deep learning model CR-Unet described in our previous study, the aim of our present study was to investigate further the feasibility of using this model in clinical practice by validating its performance in reducing the inter- and intra-observer variability of follicle diameter measurement. This study also investigated whether follicular area is a better biomarker than diameter in assessing follicular maturity. Data on 106 ovaries and 230 follicles collected from 80 cases of single follicular cycles and 26 cases of multiple follicular cycles constituted the validation set. Intra-observer variability was 0.973 and 0.982 for the senior sonographer and junior sonographer in single follicular cycles and 0.979 (0.971, 0.985) and 0.920 (0.892, 0.943) in multiple follicular cycles, respectively, while CR-Unet had no intra-group variation. Bland-Altman plot analysis indicated that the 95% limits of agreement between senior sonographer and CR-Unet (-2.1 to 1.1 mm, -2.02 to 0.75 mm) were smaller than those between senior sonographer and junior sonographer (-1.51 to 1.15 mm, -2.1 to 1.56 mm) in single and multiple follicular cycles. The average operating times of diameter measurement taken by the junior sonographer, senior sonographer and CR-Unet were 7.54 ± 1.8, 4.87 ± 0.84 and 1.66 ± 0.76 s, respectively (p < 0.001). Correlation analysis indicated that both manual and automated follicular area correlated better with follicular volume than diameter. The deep learning algorithm and the new biomarker of follicular area hold potential for clinical application of ultrasonic follicular monitoring.

Follicular Volume Predicts Oocyte Maturity: A Prospective Cohort Study Using Three-Dimensional Ultrasound and SonoAVC.

The aim of this study was to investigate whether the automatic measurement of follicular volume by three-dimensional (3D) ultrasound can predict the number of mature oocytes retrieved. A prospective cohort study including 47 women undergoing in vitro fertilization was conducted in a private fertility center. Follicular growth was monitored both manually and automatically using 3D scanning with SonoAVC on the day of human chorionic gonadotropin (hCG) administration. Regression analysis showed that under a standard protocol for hCG administration, the count of mature oocytes is well predicted by a multivariate model including the counts of follicles in the volume classes 2.00 to 5.00 cm3, 1.50 to 1.99 cm3, 1.00 to 1.49 cm3, and 0.60 to 0.99 cm3 In conclusion, this study shows that follicular volume as measured by SonoAVC on the day of hCG administration can be useful to predict oocyte maturity. Specifically, larger follicles and smaller size follicles (class 0.60-0.99 cm3) contribute to the mature oocyte count. This finding warrants the design of clinical trials to establish new criteria for hCG administration based on follicular volume.

FOLLICULAR MONITORING: COMPARISON OF TRANSABDOMINAL AND TRANSVAGINAL SONOGRAPHY.

Transabdominal sonography (TAS) and Transvaginal sonography (TVS) were compared for follicular monitoring in 73 patients of infertility. These patients were referred for follicular monitoring in normal and stimulated cycles from infertility clinic. Patient compliance and acceptance was excellent for TVS technique as compared to TAS technique. The overall resolution of ovarian and follicular anatomy was much better in TVS. With TAS only 35.6% had good visualisation of follicles as compared to 80.8% (p<0.05) in TVS. TVS offered advantage of much better detection rate of smaller follicles (<10mm) and higher accuracy in assessing number of follicles.