A Homogeneous Ensemble of Robust Pre-defined Neural Network Enables Automated Annotation of Human Embryo Morphokinetics

Gunawan B.  Danardono; Alva  Erwin; James  Purnama; Nining  Handayani; Arie A.  Polim; Arief   Boediono; Ivan  Sini

doi:10.18502/jri.v23i4.10809

Gunawan B. Danardono IRSI Research and Training Center, Jakarta, Indonesia
Alva Erwin IRSI Research and Training Center, Jakarta, Indonesia
James Purnama Faculty of Engineering and Information Technology, Swiss German University, Tangerang, Indonesia
Nining Handayani IRSI Research and Training Center, Jakarta, Indonesia
Arie A. Polim IRSI Research and Training Center, Jakarta, Indonesia
Arief Boediono IRSI Research and Training Center, Jakarta, Indonesia
Ivan Sini IRSI Research and Training Center, Jakarta, Indonesia

DOI: https://doi.org/10.18502/jri.v23i4.10809

Keywords: Artificial intelligence, Automation, Computer-assisted image processing, Embryonic development, In vitro fertilization, Machine learning, Neural networks.

Abstract

Background: The purpose of the current study was to reduce the risk of human bias in assessing embryos by automatically annotating embryonic development based on their morphological changes at specified time-points with convolutional neural network (CNN) and artificial intelligence (AI).

Methods: Time-lapse videos of embryo development were manually annotated by the embryologist and extracted for use as a supervised dataset, where the data were split into 14 unique classifications based on morphological differences. A compilation of homogeneous pre-trained CNN models obtained via TensorFlow Hub was tested with various hyperparameters on a controlled environment using transfer learning to create a new model. Subsequently, the performances of the AI models in correctly annotating embryo morphologies within the 14 designated classifications were compared with a collection of AI models with different built-in configurations so as to derive a model with the highest accuracy.

Results: Eventually, an AI model with a specific configuration and an accuracy score of 67.68% was obtained, capable of predicting the embryo developmental stages (t1, t2, t3, t4, t5, t6, t7, t8, t9+, tCompaction, tM, tSB, tB, tEB).

Conclusion: Currently, the technology and research of artificial intelligence and machine learning in the medical field have significantly and continuingly progressed in an effort to develop computer-assisted technology which could potentially increase the efficiency and accuracy of medical personnel’s performance. Nonetheless, building AI models with larger data is required to properly increase AI model reliability.