Oct 29, 2020   3:53 p.m. Klára, pamätný deň - Deň narodenia Ľudovíta Štúra
Academic information system

Persons at STU

This page displays all publicly accessible information about the desired person. Some information about the person's occupation and offices may be hidden.

Ing. Marek Jakab
Identification number: 5669
University e-mail: marek.jakab [at] stuba.sk
2511V00  Applied Informatics D-AI
FIIT D-AI den [interrupted]
Doctoral type of study, full-time, attendance method form
interrupted study

Graduate     Lesson
Projects     Publications
Supervised theses

Basic information

Basic information about a final thesis

Type of thesis:
Diploma thesis
Thesis title:
Semantic image segmentation utilizing convolutional neural networks
Written by (author): Ing. Marek Števuliak
Institute of Computer Engineering and Applied Informatics (FIIT)
Thesis supervisor:
Ing. Marek Jakab
Ing. Lukáš Hudec
Final thesis progress:
Final thesis was successfully defended.

Additional information

Additional information about the final thesis follows. Click on the language link to display the information in the desired language.

Language of final thesis:

Slovak        English

Title of the thesis:
Semantic image segmentation utilizing convolutional neural networks
Image segmentation as one of the computer vision methods is increasingly used in the medical domain. With deep learning introduction, techniques utilizing convolutional neural networks come to attention. In this work, we deal with brain tumor segmentation problem from magnetic resonance imaging (MRI), considered financially and time demanding when carried out manually. To tackle this specific and complex domain problem, the mentioned convolutional networks have proved competent due to significantly better performance than standard segmentation approaches. Therefore, within our research, we dedicate our time to analysis and design of fully-automatic method based on aforementioned networks, yielding the output in form of segmentation mask which captures a tumor classified into 4 sub-tumoral regions. We analyze pros and cons of the state of the art brain tumor segmentation techniques. During elaboration, we propose multiple architectures, training phases, and evaluation metrics based on the analysis. Our goal is reliable automatic method, specialized on helping the experts with delineation of tumorous tissues.
Key words:
brain tumor segmentation, deep learning, computer vision, segmentation of medical data, convolutional neural networks

Display and download files

To display the final thesis assignment form click on the Display the final thesis assignment form icon. The following icons - Final thesis, Thesis appendices, Supervisor's review, Opponent's review - relate to the final thesis and can be downloaded. They could be displayed on condition they have been inserted and are available publicly.

Display the assignment form

Parts of thesis with postponed release:

Final thesis (final thesis appendices) unlimited
Reviews for final thesis unlimited