Development of an automated two pronuclei detection system on time‐lapse embryo images using deep learning techniques

Fukunaga, Noritaka; Sanami, Sho; Kitasaka, Hiroya; Tsuzuki, Yuji; Watanabe, Hiroyuki; Kida, Yutaka; Takeda, Seiji; Asada, Yoshimasa

doi:10.1002/rmb2.12331

Cited by 13 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of developments in embryo evaluation include the assessment of pronuclear stage embryos to differentiate between 2PN and non-2PN zygotes 81,82 . Morphokinetic data such as cytoplasmic movements have also shown potential to predict blastocyst formation at early cleavage stages in a time seriesbased ANN model 83 .…”

Section: Morphokinetics and Morphologymentioning

confidence: 99%

The prospect of artificial intelligence to personalize assisted reproductive technology

Hanassab,

Abbara,

Yeung

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

Infertility affects 1-in-6 couples, with repeated intensive cycles of assisted reproductive technology (ART) required by many to achieve a desired live birth. In ART, typically, clinicians and laboratory staff consider patient characteristics, previous treatment responses, and ongoing monitoring to determine treatment decisions. However, the reproducibility, weighting, and interpretation of these characteristics are contentious, and highly operator-dependent, resulting in considerable reliance on clinical experience. Artificial intelligence (AI) is ideally suited to handle, process, and analyze large, dynamic, temporal datasets with multiple intermediary outcomes that are generated during an ART cycle. Here, we review how AI has demonstrated potential for optimization and personalization of key steps in a reproducible manner, including: drug selection and dosing, cycle monitoring, induction of oocyte maturation, and selection of the most competent gametes and embryos, to improve the overall efficacy and safety of ART.

show abstract

Section: Morphokinetics and Morphologymentioning

confidence: 99%

The prospect of artificial intelligence to personalize assisted reproductive technology

Hanassab,

Abbara,

Yeung

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

show abstract

“…These include the automated segmentation of the ICM ( Kheradmand et al , 2017 ; Rad et al , 2017 ), TE ( Rad et al , 2020 ), zona pellucida thickness ( Yee et al , 2013 ; Rad et al , 2018 ) or a combination of the three in a blastocyst ( Filho et al , 2012 ; Farias et al , 2023 ). The use of TLV further boosted advancements in automated detection of pronuclei ( Fukunaga et al , 2020 ) and subsequent embryo cleavage stages ( Dirvanauskas et al , 2019 ; Raudonis et al , 2019 ). An important milestone study was reported by Feyeux et al (2020) , which automated the annotation of morphokinetic parameters ranging from early cleavage stages to the expanded blastocyst stage.…”

Section: Ai-driven Dsssmentioning

confidence: 99%

A brief history of artificial intelligence embryo selection: from black-box to glass-box

Lee,

Natalwala,

Chapple

et al. 2023

Human Reproduction

View full text Add to dashboard Cite

With the exponential growth of computing power and accumulation of embryo image data in recent years, artificial intelligence (AI) is starting to be utilized in embryo selection in IVF. Amongst different AI technologies, machine learning (ML) has the potential to reduce operator-related subjectivity in embryo selection while saving labor time on this task. However, as modern deep learning (DL) techniques, a subcategory of ML, are increasingly used, its integrated black-box attracts growing concern owing to the well-recognized issues regarding lack of interpretability. Currently, there is a lack of randomized controlled trials to confirm the effectiveness of such black-box models. Recently, emerging evidence has shown underperformance of black-box models compared to the more interpretable traditional ML models in embryo selection. Meanwhile, glass-box AI, such as interpretable ML, is being increasingly promoted across a wide range of fields and is supported by its ethical advantages and technical feasibility. In this review, we propose a novel classification system for traditional and AI-driven systems from an embryology standpoint, defining different morphology-based selection approaches with an emphasis on subjectivity, explainability, and interpretability.

show abstract

“…The main focus is on early-stage human embryo development to characterize morphological characteristics. Fukunaga et al [5] developed a system of automating the detection of pronuclei on 900 embryos. Khan et al [6] and Leahy et al [7] applied segmentation techniques for counting the number of cells, while there are works (Dirvanauskas et al [8], Liu et al [9], Malmsten et al [10][11][12], Lau et al [13], Gingold et al [14], Meseguer et al [15]) on identifying the development stage.…”

Section: Introductionmentioning

confidence: 99%

Detecting the Area of Bovine Cumulus Oocyte Complexes Using Deep Learning and Semantic Segmentation

Athanasiou

Cerquides

Raes

et al. 2022

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

The cumulus-oocyte complex (COC) is an oocyte surrounded by specialized granulosa cells, called cumulus cells. The cumulus cells surrounding the oocyte ensure healthy oocyte and embryo development. The maturity of COCs at oocyte retrieval may be used as an indicator to predict outcome of assisted reproductive technology (ART). Segmenting COCs is a preliminary step in many image processing pipelines to evaluate maturity. However, acquiring well-annotated bright-field microscopy image datasets remains a time-consuming and inaccurate procedure, for most biological domains. Additionally, specialists often partially disagree on their annotations, not only among each other, but also among their own annotations, leading to an inconsistent outcome. Despite the recent advancements in deep learning and image segmentation tools for biological and biomedical images, there is limited usage of them for having more accurate and automated procedures. In this work, we propose an automated pipeline to segment bovine COCs in bright-field microscopy images. The results of our evaluation show that our pipeline is able to segment COCs with the same level of quality as provided by human experts.

show abstract

Development of an automated two pronuclei detection system on time‐lapse embryo images using deep learning techniques

Cited by 13 publications

References 7 publications

The prospect of artificial intelligence to personalize assisted reproductive technology

The prospect of artificial intelligence to personalize assisted reproductive technology

A brief history of artificial intelligence embryo selection: from black-box to glass-box

Detecting the Area of Bovine Cumulus Oocyte Complexes Using Deep Learning and Semantic Segmentation

Contact Info

Product

Resources

About