Thesis Details

Detection of Pathological Findings in Videos from Bronchial Pathways

Bachelor's Thesis Student: Novotný Mlinárcsik Martin Academic Year: 2021/2022 Supervisor: Drahanský Martin, prof. Ing., Dipl.-Ing., Ph.D.
Czech title
Detection of pathological findings in videos from bronchial pathways
Language
English
Abstract

The aim of this work is a detection of lung pathologies in videos from bronchial airways. Videos of bronchial passages, created by inserting a bronchoscope into a patient, are used as an input. Afterwards, individual frames are processed in a way, that pathologies are color separated from non-pathological background as dark spots. These dark spots are then analyzed by a Blob Detector, which will mark these as pathological and highlight them in the output image.

Keywords

image processing, object detection, lung pathologies, Blob Detector, OpenCV

Department
Department of Intelligent Systems FIT BUT
Degree Programme
Information Technology
Files
Status
defended, grade E
Date
14 June 2022
Reviewer
Goldmann Tomáš, Ing.
Committee
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT), předseda
Bařina David, Ing., Ph.D. (DCGM FIT BUT), člen
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Češka Milan, doc. RNDr., Ph.D. (DITS FIT BUT), člen
Mrázek Vojtěch, Ing., Ph.D. (DCSY FIT BUT), člen
Citation
NOVOTNÝ, Mlinárcsik. Detection of Pathological Findings in Videos from Bronchial Pathways. Brno, 2022. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2022-06-14. Supervised by Drahanský Martin. Available from: https://www.fit.vut.cz/study/thesis/24849/
BibTeX 
@bachelorsthesis{FITBT24849,
    author = "Martin Mlin\'{a}rcsik Novotn\'{y}",
    type = "Bachelor's thesis",
    title = "Detection of Pathological Findings in Videos from Bronchial Pathways",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2022,
    location = "Brno, CZ",
    language = "english",
    url = "https://www.fit.vut.cz/study/thesis/24849/"
}

Theses

Back to top