D. Dirvanauskas “Algorithm for live cell classification and monitoring based on deep neural networks” doctoral dissertation defence

Thesis Defense

Author, Institution: Darius Dirvanauskas, Kaunas University of Technology

Science area, field of science: Technological Sciences, Informatics Engineering, T007

Scientific supervisor: Prof. Dr. Rytis Maskeliūnas (Kaunas University of Technology, Technological Sciences, Informatics Engineering – T007).

Dissertation Defence Board of Informatics Engineering Science Field:
Prof. Dr. Rimvydas Simutis (Kaunas University of Technology, Technological Sciences, Informatics Engineering – T007) – pirmininkas
Prof. Dr. Habil. Romualdas Baušys (Vilnius Gediminas Technical University, Technological Sciences, Informatics Engineering – T007)
Prof. Dr. Giacomo Capizzi (University of Catania, Italy, Natural Sciences, Informatics – N009)
Prof. Dr. Arnas Kačeniauskas (Vilnius Gediminas Technical University, Technological Sciences, Informatics Engineering – T007)
Prof. Dr. Olga Kurasova (Vilnius University, Technological Sciences, Informatics Engineering – T007)

The dissertation defence takes place online.

The doctoral dissertation is available on the internet and at the library of Kaunas University of Technology (K. Donelaičio g. 20, Kaunas).

Annotation:

Every sixth couple in the world has difficulty having children. There are about 50 thousand such families in Lithuania and their number is growing every year. Some of these families are treated with an in vitro method for growing an embryo. Time-lapse microscopy has provided new tools for embryo image inspection. These machines are used for continuous monitoring of embryos in different layers and capturing images of embryo evolution, measuring embryo’s development stage duration and inspecting embryo cell shape without removing embryos from their growth environment. The aim of dissertation is to develop a computerized method, which would predict the embryo growth stage and reconstruct its spatial model from the layer images. We propose a hybrid embryo classification model which is applicable for constant embryo monitoring and stage prediction. Our offered deep learning method can be used for embryo spatial model reconstruction from different layer images. The created tool for embryo spatial image visual evaluation gives embryologists new possibilities for embryo analysis.

We are using cookies to provide statistics that help us give you the best experience of our site. You can find out more or switch them off if you prefer. However, by continuing to use the site without changing settings, you are agreeing to our use of cookies.
I agree