NEWS
Backed by proven science
A prospective cohort of 116 IVF/ICSI cycles compared a 25-point clinical/laboratory KPI score with an AI blastocyst-image algorithm (Embryo/Aid-MIM Fertility) for predicting implantation and live birth. AI outperformed the KPI score (AUC 0.80 vs 0.66; accuracy 73% vs 63%), though the single-centre design and small sample limit the conclusions.
A prospective study of 334 IVF cycles at CEGYR (Argentina) compared automated AFC with manual AFC and AMH for predicting poor (<4 oocytes) and high (>15 oocytes) response. Automated AFC performed at least as well as the conventional markers – ROC AUC ~0.84 for low response (vs 0.80 AMH, 0.72 manual AFC) – while high-response […]
An AI system (FOLLISCAN) counted follicles on 212 ovarian ultrasound cine-loops from 79 patients across five Polish clinics and was compared with routine clinical assessment for the ESHRE FNPO ≥20 PCOM criterion. Precision was similar (96% vs 93%), but AI sensitivity was far higher (79% vs 39%; McNemar p = 0.00097), with the biggest gains […]
Real-world implementation of AI-based follicular monitoring (FOLLISCAN) in the Adora clinic network was assessed via blinded review of 100 ultrasound scans plus two months of laboratory KPIs. Clinical decisions and trigger timing were unchanged, measurement variability dropped, lab KPIs stayed within competency thresholds, and ultrasound assessment time fell by up to 50%.
A deep learning model was trained on 6,299 blastocyst images from four IVF centres in Europe and Latin America to automate full Gardner grading (expansion, ICM, TE). It reached a multiclass AUROC of 0.913 and 83.7% top-5 accuracy, with performance holding steady across centres despite equipment and protocol differences.
Our recent multicentre study across six IVF centres in five countries demonstrates the potential of artificial intelligence to support embryo selection in IVF. An AI-based embryo scoring algorithm was evaluated against 20 embryologists using 1,681 embryo pairs with known clinical outcomes. The model achieved an accuracy of 70.1%, outperforming most individual embryologists and exceeding the […]
This multicenter study evaluated the analytical performance of an AI-based platform for automated ovarian follicle measurement and count estimation during ovarian stimulation in IVF cycles. Follicle diameters and counts derived from two-dimensional ultrasound images were compared with assessments performed by certified sonographers. The results demonstrated high agreement between the AI platform and expert clinicians, supporting […]
The Folliscan AI model’s ability to measure ovarian follicle diameters was assessed and its performance was compared with expert sonographers across four international IVF clinics. The study showed exceptionally high agreement between AI and clinicians, with ICC values consistently above 0.95 and error levels comparable to, and in some cases lower than inter-physician variability. Folliscan […]
An AI system was designed to measure endometrial thickness and its performance was compared with expert clinicians across multicenter IVF ultrasound datasets. The study demonstrated that AI achieved accuracy and consistency on par with experienced sonographers, with variability nearly identical to clinician-to-clinician differences. In clinically relevant decision-making, such as determining whether thickness exceeds the 7 […]
In this study a deep learning method was developed that automatically segments and estimates endometrial volume from 3D ultrasound scans, addressing a key bottleneck in current IVF monitoring workflows. Trained on a large, diverse, multicenter dataset, the model achieves accuracy comparable to manual VOCAL measurements while reducing analysis time from several minutes to under two […]
This study evaluated how AI can assist embryologists in predicting embryo implantation success in IVF. Using 2,075 embryo pairs from six international centres, the AI model showed consistently high accuracy and generalizability. It outperformed most individual embryologists and closely aligned with expert consensus, suggesting it can enhance decision-making consistency. AI’s performance was independent of clinical […]
This study investigated whether IVF lab workload can be optimized without compromising clinical outcomes. Using simulations based on 774 real IVF cycles, various scheduling strategies were tested by adjusting trigger days. The balanced optimization approach reduced weekend workload by 20% while maintaining a high yield of mature (M2) oocytes. Unlike pure workload or M2-focused strategies, […]
This research opens exciting possibilities for more standardized, efficient, and accessible embryo selection in clinics worldwide — especially where experienced embryologists may be limited. Additional poster description for MIM website:This ongoing prospective, multicenter study explores how AI can support embryologists in selecting embryos for transfer during IVF. Early results from 221 transfers show that clinical […]
This study compared AI-based ultrasound assessment with expert ultrasonographers in predicting ovarian response and estimating MII oocyte numbers. AI measured antral follicle count consistently and predicted low ovarian response nearly as accurately as human experts. However, during ovulation trigger monitoring, AI tended to detect fewer large follicles and slightly underestimated MII oocyte numbers. These findings […]
This study compared the AI follicle tracking tool Folliscan with manual measurements for assessing ovarian follicles. Folliscan showed high accuracy and strong correlation with manual methods, confirming its reliability. It significantly reduced scan time, improving workflow and patient satisfaction. The AI tool performed equally well in supporting clinical decisions about treatment timing. Although the study […]
This content is intended exclusively for qualified medical professionals and may include specialized information that should not be interpreted by individuals without appropriate medical training.
