May 20, 2019   4:29 a.m. Bernard
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
 
Výskumný pracovník s VŠ vzdelaním - Institute of Computer Engineering and Applied Informatics (FIIT)
 
2511V00  Applied Informatics D-AI
FIIT D-AI den [year 3]
Doctoral type of study, full-time, attendance method form
3rd year of study

Contacts     Graduate     Lesson     Final thesis     
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): Bc. Marek Števuliak
Department: Institute of Computer Engineering and Applied Informatics (FIIT)
Thesis supervisor: Ing. Marek Jakab
Opponent:Ing. Lukáš Hudec
Final thesis progress:Final thesis is in progress


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:English

Slovak        English

Title of the thesis:Semantic image segmentation utilizing convolutional neural networks
Summary: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