prikaz prve stranice dokumenta Duboko učenje za detekciju upale pluća iz X-ray slika prsnog koša
  Download
PDF 1.16 MB
undergraduate thesis
Duboko učenje za detekciju upale pluća iz X-ray slika prsnog koša
2023. urn:nbn:hr:200:609131
Ribičić, Ivana
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Cite this document

Ribičić, I. (2023). Duboko učenje za detekciju upale pluća iz X-ray slika prsnog koša (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:609131

Ribičić, Ivana. "Duboko učenje za detekciju upale pluća iz X-ray slika prsnog koša." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:609131

Ribičić, Ivana. "Duboko učenje za detekciju upale pluća iz X-ray slika prsnog koša." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:609131

Ribičić, I. (2023). 'Duboko učenje za detekciju upale pluća iz X-ray slika prsnog koša', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 09 May 2024, https://urn.nsk.hr/urn:nbn:hr:200:609131

Ribičić I. Duboko učenje za detekciju upale pluća iz X-ray slika prsnog koša [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 May 09] Available at: https://urn.nsk.hr/urn:nbn:hr:200:609131

I. Ribičić, "Duboko učenje za detekciju upale pluća iz X-ray slika prsnog koša", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:609131

Please login to the repository to save this object to your list.
Metadata
TitleDuboko učenje za detekciju upale pluća iz X-ray slika prsnog koša
Title (english)Deep learning for pneumonia detection from X-ray chest images
AuthorIvana Ribičić
MentorIrena Galić (mentor)
MentorMarija Habijan (sumentor)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2023, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
X-ray slike prsnog koša dobivaju se medicinskim uređajima za radiografiju, računalnu tomografiju (CT), ultrazvuk te magnetsku rezonancu (MR). Na osnovu medicinskih slika otkrivaju se i potvrđuje različite bolesti. Jedna od tih bolesti je upala pluća (pneumonija), česta akutna upalna bolest plućnog parenhima. S razvojem tehnologije sve su češći sustavi koji se koriste za detekciju upale pluća iz X-ray slika prsnog koša. Takvi sustavi temeljeni su na metodama dubokog učenja, od kojih su najčešće konvolucijske neuronske mreže koje daju jako dobre rezultate i kada se radi s manjim skupovima podataka. Za potrebe ovog rada kreiran je sustav dubokog učenja koji koristi konvolucijsku neuronsku mrežu kako bi detektirao upalu pluća na skupu podataka sastavljenom od X-ray slika prsnog koša. Za klasifikaciju podataka korišten je binarni klasifikator te su prikazani rezultati dobiveni klasifikacijom.
Abstract (english)
Chest X-ray images are obtained using devices for radiography, computerized tomography (CT), ultrasound and magnetic resonance imaging (MRI). Medical images are used for detection and confirmation of various diseases. One of these diseases is pneumonia which is an inflammation of the lungs, usually caused by an infection. Systems that are used to detect pneumonia from X-ray images are becoming more and more common since thanks to the constant development of technology. Such systems are based on deep learning methods and the most common methods are convolutional neural networks that can be used even on smaller datasets and still achieve good results. For the purposes of this paper, a deep learning system based on a convolutional neural network was created with a goal to detect pneumonia from a data set composed of a chest X-ray images. A binary classifier was used to classify the data, and the results obtained by the classification were presented.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:609131
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
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 resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-10-20 11:36:21