2022 Fiscal Year Final Research Report
Noninvasive embryo selection by time-lapse imaging of an embryo using artificial intelligence
Project/Area Number |
20K18195
|
Research Category |
Grant-in-Aid for Early-Career Scientists
|
Allocation Type | Multi-year Fund |
Review Section |
Basic Section 56040:Obstetrics and gynecology-related
|
Research Institution | Nagoya City University |
Principal Investigator |
Sawada Yuki 名古屋市立大学, 医薬学総合研究院(医学), 助教 (90793589)
|
Project Period (FY) |
2020-04-01 – 2023-03-31
|
Keywords | 人工知能 / ディープラーニング / 生殖補助医療 / 胚染色体異数性 / タイムラプスイメージング |
Outline of Final Research Achievements |
First, an AI system was created by using the Attention Branch Network associated with deep learning to predict the probability of live birth from images recorded by time-lapse imaging of transferred embryos. We have created the AI system with a confidence score that is useful for non-invasive selection of embryos that could result in live birth. Based on this method, an AI was created to classify aneuploidy from images of embryos that had been identified as euploidy or aneuploid by chromosomal analysis. We tried to improve the accuracy of this AI by selecting datasets and expanding the data, but we could not develop a practical model of the AI. At present, it was found to be difficult to identify aneuploidy in embryos from images of embryos.
|
Free Research Field |
生殖医療
|
Academic Significance and Societal Importance of the Research Achievements |
移植する胚を選択する方法の一つとして、人工知能のディープラーニングの技術を用いることは、非侵襲的に生殖補助医療の治療成績を向上させることができる可能性があると考えられた。しかし胚の染色体異数性の有無を高い精度で識別するまでには至っておらず、非侵襲的な着床前胚染色体異数性検査として、実際の臨床で用いることはできない。 現時点では、従来から用いられてる胚の形態学的及び動態学的評価に、人工知能による胚評価を併用して胚を選択することが、より生児獲得に至る可能性が高い胚を選択するための有用な方法であると考える。
|