kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Classifying and Explaining Hypertrophic Cardiomyopathy with Deep Learning Methods
KTH, School of Electrical Engineering and Computer Science (EECS).
2023 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Klassificering och Förklaring av Hypertrofisk Kardiomyopati med Djupinlärningsmetoder (Swedish)
Abstract [en]

The introduction of Deep Learning methods for Ultrasound applications is more relevant than ever in the context of Echocardiography. In this thesis we worked on a small echocardiographic dataset with 70 patients and proved that an adapted scale and the alignment to end diastolic heart cycle frames can be beneficial for classifying Hypertrophic Cardiomyopathy. Furthermore, we investigated three Explainable Artificial Intelligence Methods and showed that our model focused on more than the clinically prevalent indicators.

Abstract [sv]

Införandet av metoder för djupinlärning inom ultraljudstillämpningar är mer relevant än någonsin inom ekokardiografi. I detta examensarbete arbetade vi med en liten ekokardiografisk datauppsättning med 70 patienter och visade att en anpassad skala och anpassning till slutdiastoliska hjärtcykelramar kan vara fördelaktigt för att klassificera hypertrofisk kardiomyopati. Dessutom undersökte vi tre förklarbara artificiell intelligensmetoder och visade att vår modell fokuserade på mer än de kliniskt vanliga indikatorerna.

Place, publisher, year, edition, pages
2023. , p. 70
Series
TRITA-EECS-EX ; 2023:911
Keywords [en]
Medical Imaging, Hypertrophic Cardiomyopathy, XAI
Keywords [sv]
Medical Imaging, Hypertrofisk Kardiomyopati, XAI
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-344044OAI: oai:DiVA.org:kth-344044DiVA, id: diva2:1841564
Educational program
Master of Science - Machine Learning
Supervisors
Examiners
Available from: 2024-03-14 Created: 2024-02-29 Last updated: 2024-03-14Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 163 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf