Performance of a deep learning based neural network in the selection of human blastocysts for implantation
- Massachusetts General Hospital, Harvard Medical School, United States
- Brigham and Women's Hospital, Harvard Medical School, United States
- Extend Fertility, United States
- San Diego Fertility Center, United States
- Colorado Center for Reproductive Medicine IVF Laboratory Network, United States
- University of Wisconsin, United States
Abstract
Deep learning in in-vitro fertilization is currently being evaluated in the development of assistive tools for the determination of transfer order and implantation potential using time-lapse data collected through expensive imaging hardware. Assistive tools and algorithms that can work with static images, however, can help in improving the access to care by enabling their use with images acquired from traditional microscopes that are available to virtually all fertility centers. Here, we evaluated the use of a deep convolutional neural network (CNN), trained using single timepoint images of embryos collected at 113 hours post-insemination, in embryo selection amongst 97 clinical patient cohorts (742 embryos) and observed an accuracy of 90% in choosing the highest quality embryo available. Furthermore, a CNN trained to assess an embryo’s implantation potential directly using a set of 97 euploid embryos capable of implantation outperformed 15 trained embryologists (75.26% vs. 67.35%, P<0.0001) from 5 different fertility centers.
Data availability
Patients did not explicitly consent to their data being made public and access is therefore restricted. Requests for the anonymized data should be made to Charles Bormann (cbormann@partners.org) and Hadi Shafiee (hshafiee@bwh.harvard.edu). Requests will be reviewed by a data access committee, taking into account the research proposal and intended use of the data. Requestors are required to sign a data-sharing agreement to ensure patients' confidentiality is maintained prior to the release of any data.
Article and author information
Author details
Funding
National Institutes of Health (R01AI138800)
- Hadi Shafiee
Brigham and Women's Hospital (Precision Medicine Program)
- Hadi Shafiee
Partners Healthcare (Innovation Discovery Grant)
- Charles L Bormann
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Ethics
Human subjects: Embryo image/video data collected from patients were used in this study with an institutional review board approval (IRB#2017P001339) We used 3,469 recorded videos of embryos collected from patients with informed consent for research and publication, under an institutional review board approval for secondary research use.
Copyright
© 2020, Bormann et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 5,025
- views
-
- 840
- downloads
-
- 91
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
A two-part list of links to download the article, or parts of the article, in various formats.
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Performance of a deep learning based neural network in the selection of human blastocysts for implantation
eLife 9:e55301.
https://doi.org/10.7554/eLife.55301
Further reading
-
- Medicine
- Neuroscience
Background:
Subarachnoid hemorrhage (SAH) is characterized by intense central inflammation, leading to substantial post-hemorrhagic complications such as vasospasm and delayed cerebral ischemia. Given the anti-inflammatory effect of transcutaneous auricular vagus nerve stimulation (taVNS) and its ability to promote brain plasticity, taVNS has emerged as a promising therapeutic option for SAH patients. However, the effects of taVNS on cardiovascular dynamics in critically ill patients, like those with SAH, have not yet been investigated. Given the association between cardiac complications and elevated risk of poor clinical outcomes after SAH, it is essential to characterize the cardiovascular effects of taVNS to ensure this approach is safe in this fragile population. Therefore, this study assessed the impact of both acute and repetitive taVNS on cardiovascular function.
Methods:
In this randomized clinical trial, 24 SAH patients were assigned to either a taVNS treatment or a sham treatment group. During their stay in the intensive care unit, we monitored patient electrocardiogram readings and vital signs. We compared long-term changes in heart rate, heart rate variability (HRV), QT interval, and blood pressure between the two groups. Additionally, we assessed the effects of acute taVNS by comparing cardiovascular metrics before, during, and after the intervention. We also explored acute cardiovascular biomarkers in patients exhibiting clinical improvement.
Results:
We found that repetitive taVNS did not significantly alter heart rate, QT interval, blood pressure, or intracranial pressure (ICP). However, repetitive taVNS increased overall HRV and parasympathetic activity compared to the sham treatment. The increase in parasympathetic activity was most pronounced from 2 to 4 days after initial treatment (Cohen’s d = 0.50). Acutely, taVNS increased heart rate, blood pressure, and peripheral perfusion index without affecting the corrected QT interval, ICP, or HRV. The acute post-treatment elevation in heart rate was more pronounced in patients who experienced a decrease of more than one point in their modified Rankin Score at the time of discharge.
Conclusions:
Our study found that taVNS treatment did not induce adverse cardiovascular effects, such as bradycardia or QT prolongation, supporting its development as a safe immunomodulatory treatment approach for SAH patients. The observed acute increase in heart rate after taVNS treatment may serve as a biomarker for SAH patients who could derive greater benefit from this treatment.
Funding:
The American Association of Neurological Surgeons (ALH), The Aneurysm and AVM Foundation (ALH), The National Institutes of Health R01-EB026439, P41-EB018783, U24-NS109103, R21-NS128307 (ECL, PB), McDonnell Center for Systems Neuroscience (ECL, PB), and Fondazione Neurone (PB).
Clinical trial number:
-
- Immunology and Inflammation
- Medicine
Together with obesity and type 2 diabetes, metabolic dysfunction-associated steatotic liver disease (MASLD) is a growing global epidemic. Activation of the complement system and infiltration of macrophages has been linked to progression of metabolic liver disease. The role of complement receptors in macrophage activation and recruitment in MASLD remains poorly understood. In human and mouse, C3AR1 in the liver is expressed primarily in Kupffer cells, but is downregulated in humans with MASLD compared to obese controls. To test the role of complement 3a receptor (C3aR1) on macrophages and liver resident macrophages in MASLD, we generated mice deficient in C3aR1 on all macrophages (C3aR1-MφKO) or specifically in liver Kupffer cells (C3aR1-KpKO) and subjected them to a model of metabolic steatotic liver disease. We show that macrophages account for the vast majority of C3ar1 expression in the liver. Overall, C3aR1-MφKO and C3aR1-KpKO mice have similar body weight gain without significant alterations in glucose homeostasis, hepatic steatosis and fibrosis, compared to controls on a MASLD-inducing diet. This study demonstrates that C3aR1 deletion in macrophages or Kupffer cells, the predominant liver cell type expressing C3ar1, has no significant effect on liver steatosis, inflammation or fibrosis in a dietary MASLD model.
