Analiza medicinskih slika prikupljenih pomoću CT-a

undergraduate thesis

• Title (english): Analysis of CT Medical Images
• Author: Josip Skender
• Mentor: Mislav Grgić (mentor)
• Committee member: Mislav Grgić (predsjednik povjerenstva)
• Committee member: Sonja Grgić (član povjerenstva)
• Committee member: Tomislav Kos (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu opisan je pojam računalnog vida i njegov povijesni razvoj s naglaskom na njegovoj primjeni u području medicine. Navedene su metode medicinskog snimanja i objašnjen je proces njihove analize pomoću raznih algoritama strojnog učenja. Među metodama medicinskog snimanja objašnjena je kompjutorizirana tomografija (CT), središnja metoda ovog rada. Opisan je širok spektar online baza medicinskih slika raznih namjera i naveden njihov sadržaj s istaknutim prednostima i nedostacima. U suradnji sa specijalnom privatnom bolnicom prikupljeni su DICOM podaci snimanja kompjutoriziranom tomografijom, izvršenom na 20 pacijenata, s toraksom (prsnim košem) kao regijom interesa. Programski jezik Python korišten je kao alat za obradu slika (eng. image processing) kompjutorizirane tomografije. Nad ulaznim podacima provedena su dva različita algoritma segmentacije plućnog tkiva te je generiran 3D model pluća pacijenata.

Abstract (english)

This thesis follows computer vision and its methods throughout modern history, with focus towards medical image analysis. Various methods of medical imaging have been listed and their processing using machine learning has been explained. One of the methods, computerized tomography (CT) is the focal point of this thesis. Some of the most popular online databases of medical images have also been listed. In cooperation with a private hospital, DICOM images of 20 patients have been gathered using CT scans of the thorax region. All image processing in this thesis has been coded in Python. Two different lung segmentation algorithms were applied on the gathered CT scans. As a result a 3D model of isolated lungs has been generated using segmented lung scans.

• Keywords: računalni vid; medicinsko snimanje; kompjutorizirana tomografija (CT); DICOM; toraks; pluća; Python; segmentacija; 3D model
• Keywords (english): computer vision; medical imaging; computerized tomography (CT); DICOM; thorax; lungs; Python; segmentation; 3D model
• Language: croatian
• URN:NBN: urn:nbn:hr:168:923196
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 21:38:20