Danardono, Gunawan Bondan and Erwin, Alva and Purnama, James (2021) Human Embryo Development Annotation for Cell Detection Using Convolutional Neural Network. Bachelor thesis, Swiss German University.

Preview	Text Gunawan Bondan Danardono 11902010 TOC.pdf Download (1MB) | Preview
	Text Gunawan Bondan Danardono 11902010 1.pdf Restricted to Registered users only Download (631kB)
	Text Gunawan Bondan Danardono 11902010 2.pdf Restricted to Registered users only Download (1MB)
	Text Gunawan Bondan Danardono 11902010 3.pdf Restricted to Registered users only Download (2MB)
	Text Gunawan Bondan Danardono 11902010 4.pdf Restricted to Registered users only Download (1MB)
	Text Gunawan Bondan Danardono 11902010 5.pdf Restricted to Registered users only Download (164kB)
Preview	Text Gunawan Bondan Danardono 11902010 Ref.pdf Download (629kB) | Preview

Abstract

In-vitro Fertilization (IVF) is a process that help couples who suffer from infertility and want to have a biological child. The process of IVF normally undergo external fertilization prior to embryo implantation to the mother's womb or uterus. Success rate of achieving clinical pregnancy after IVF program, however, remains lower in comparison to natural fertilization. Moreover, additional cost needed to undergo the IVF treatments is relatively expensive. One of the main problems contributing to the low IVF success rate is the lack of tools to precisely select the most viable embryo for transfer in embryology laboratory. Implementation of real-time embryo development monitoring through a time-lapse incubator is one of the promising technology to improve embryo selection. Utilizing a time-lapse incubator, embryologist allows to use several potential markers of embryo kinetics and its dynamic development obtained from time-lapse recording. Embryo annotation is one of the processes that need to be conducted to calculate the kinetics of embryo. This process remains conducted manually by the embryologist which potentially introduces bias that arises from individual subjective assessment. Part of the consideration is medical treatment of performing single elective embryo transfer is prioritized in IVF program, this research aims to do cell annotation for Hour 144 Embryo cells, starting from one-cell embryo (T1) to expanded blastocyst. Proof of concept from previous study has proven that cell annotation from T1-T4 is doable with the accuracy of 74%, this research will continue the annotation process of the previous study.

Item Type:	Thesis (Bachelor)
Uncontrolled Keywords:	Embryo Annotation, Convolutional Neural Network, Image Processing, In-Vitro Fertilization
Subjects:	Q Science > QA Mathematics > QA76 Computer software > QA76.87 Neural networks (Computer science) T Technology > T Technology (General) > T58.5 Information technology T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing
Divisions:	Faculty of Engineering and Information Technology > Department of Information Technology
Depositing User:	Faisal Ifzaldi
Date Deposited:	26 Dec 2021 16:19
Last Modified:	26 Dec 2021 16:19
URI:	http://repository.sgu.ac.id/id/eprint/2233

Actions (login required)

View Item