Background: The most common Assisted Reproductive Technology is Fertilization (IVF). During IVF, embryologists commonly perform a morphological assessment to evaluate embryo quality and choose the best embryo for transferring to the uterus. However, embryo selection through morphological assessment is subjective, so various embryologists obtain different conclusions. Furthermore, humans can consider only a limited number of visual parameters resulting in a poor IVF success rate. Artificial intelligence (AI) for embryo selection is objective and can include many parameters, leading to better IVF outcomes.
Objectives: This study sought to use AI to (1) predict pregnancy results based on embryo images, (2) assess using more than one image of the embryo in the prediction of pregnancy but based on the current process in IVF labs, and (3) compare results of AI-Based methods and embryologist experts in predicting pregnancy.
Methods: A data set including 252 Time-lapse Videos of embryos related to IVF performed between 2017 and 2020 was collected. Frames related to 19 ± 1, 43 ± 1, and 67 ± 1 h post-insemination were extracted. Well-Known CNN architectures with transfer learning have been applied to these images. The results have been compared with an algorithm that only uses the final image of embryos. Furthermore, the results have been compared with five experienced embryologists.
Results: To predict the pregnancy outcome, we applied five well-known CNN architectures (AlexNet, ResNet18, ResNet34, Inception V3, and DenseNet121). DeepEmbryo, using three images, predicts pregnancy better than the algorithm that only uses one final image. It also can predict pregnancy better than all embryologists. Different well-known architectures can successfully predict pregnancy chances with up to 75.0% accuracy using Transfer Learning.
Conclusion: We have developed DeepEmbryo, an AI-based tool that uses three static images to predict pregnancy. Additionally, DeepEmbryo uses images that can be obtained in the current IVF process in almost all IVF labs. AI-based tools have great potential for predicting pregnancy and can be used as a proper tool in the future.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11177761 | PMC |
| http://dx.doi.org/10.3389/frai.2024.1375474 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Deep cascaded registration and weakly-supervised segmentation of fetal brain MRI.
Heliyon
January 2025
BCN MedTech, Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain.
Deformable image registration is a cornerstone of many medical image analysis applications, particularly in the context of fetal brain magnetic resonance imaging (MRI), where precise registration is essential for studying the rapidly evolving fetal brain during pregnancy and potentially identifying neurodevelopmental abnormalities. While deep learning has become the leading approach for medical image registration, traditional convolutional neural networks (CNNs) often fall short in capturing fine image details due to their bias toward low spatial frequencies. To address this challenge, we introduce a deep learning registration framework comprising multiple cascaded convolutional networks.
View Article and Find Full Text PDFTesticular mapping-guided sperm retrieval upfront microTESE in non-obstructive azoospermia: a comparison of sperm retrieval, pregnancy and live-birth rates.
Transl Androl Urol
December 2024
University of Washington, Seattle, WA, USA.
Background: Sperm extraction by Microscopic Testicular Sperm Extraction (microTESE) has become the standard of care for sperm retrieval (SR) in men with non-obstructive azoospermia (NOA) but is costly and has a 40-50% chance of failure. Fine needle aspiration mapping (FNAM) can be performed prior to microTESE as a predictor of success to reduce the likelihood of failure to retrieve sperm but there is limited evidence that directly compares these methods. The objective of this study was to compare success rate of SR, pregnancy, and live birth rates in men who underwent upfront microTESE versus FNAM.
View Article and Find Full Text PDFMeasuring psychological well-being in a danish pregnancy cohort using the self-reported WHO-5 index.
BMC Psychol
January 2025
Department of Obstetrics, The Juliane Marie Centre, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark.
Background: Reduced well-being and depressive episodes frequently complicate pregnancy and can result in serious adverse outcomes for both mother and infant if left untreated. This study aimed to assess the psychometric validity of the 5-item World Health Organization index (WHO-5), and to evaluate if the WHO-5 index can serve as a proxy for two items of core depressive symptoms from the Major Depression Inventory (MDI), identified as MDI-2. Additionally, the paper aimed to assess well-being and detect risk factors of reduced well-being using the WHO-5 index.
View Article and Find Full Text PDFPrediction and unsupervised clustering of fertility intention among migrant workers based on machine learning: a cross-sectional survey from Henan, China.
BMC Public Health
January 2025
Department of Health Management of Public Health, College of Public Health, Zhengzhou University, 100 Kexue Road, Gaoxin district, Zhengzhou, Henan, 450001, China.
Background: Although China has implemented multiple policies to encourage childbirth, the results have been underwhelming. Migrant workers account for a considerable proportion of China's population, most of whom are of childbearing age. However, few articles focus on their fertility intentions.
View Article and Find Full Text PDFDevelopment of immune-derived molecular markers for preeclampsia based on multiple machine learning algorithms.
Sci Rep
January 2025
Department of Gynecology and Obstetrics, First Hospital of Jilin University, Changchun, 130031, Jilin, China.
Preeclampsia (PE) is a major pregnancy-specific cardiovascular complication posing latent life-threatening risks to mothers and neonates. The contribution of immune dysregulation to PE is not fully understood, highlighting the need to explore molecular markers and their relationship with immune infiltration to potentially inform therapeutic strategies. We used bioinformatics tools to analyze gene expression data from the Gene Expression Omnibus (GEO) database using the GEOquery package in R.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!