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
Implementation, Modification and Evaluation of Deep Learning Algorithm for Olfactory Bulb Segmentation
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematics (Div.).
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Implementering, modifiering och utvärdering av djupinlärningsalgoritm för segmentering av luktbulben (Swedish)
Abstract [en]

This thesis explores the generalizability of an automated deep learning algorithm with a U-Net architecture specifically tailored for human olfactory bulb (OB) segmentation. The study focuses on enhancing the performance of the segmentation tool through the implementation of targeted modifications, which are threshold adjustment and designing postprocessing constraints with the aim to successfully annotate the entire Human Connectome Project Young Adult (HCP-YA) dataset (n=1101, age 22-35 years). Extensive validation was conducted using multiple datasets to assess the algorithm's performance and its ability to generalize across different datasets with different scanning parameters. The results show a remarkably low percentage (5.8%) of missegmentations within the HCP-YA dataset and improvements in segmentation performance by reduction of over-segmentation. These enhancements do not only streamline the segmentation process but also increase the potential for using OB volume as a biomarker for neurodegenerative diseases. This thesis contributes to the field of medical image analysis by improving the performance and efficiency of OB segmentation tools, with strong implications for both research and clinical applications in diagnosing neurodegenerative disease.

Abstract [sv]

Detta examensarbete utreder generaliserbarheten hos en automatiserad djupinlärningsalgoritm med en U-Net-arkitektur, speciellt anpassad för segmentering av den mänskliga luktbulben. Studien fokuserar på att förbättra segmenteringsnoggrannheten genom implementering av riktade modifieringar, såsom tröskeljustering och utformning av efterbehandlingsrestriktioner i syfte att framgångsrikt annotera hela Human Connectome Project Young Adult (HCP-YA) datasetet (n=1101, ålder 22-35 år). Omfattande validering genomfördes med flera dataset för att bedöma algoritmens prestanda och dess förmåga att generalisera över olika dataset med olika skanings parametrar. Resultaten visar en anmärkningsvärt låg andel (5,8%) av felaktiga segmenteringar inom HCP-YA-datasetet samt förbättringar i segmenteringsnoggrannhet genom minskning av översegmentering. Dessa förbättringar strömlinjeformar inte bara segmenteringsprocessen utan ökar också potentialen att använda volymen av luktbulben som biomarkör för neurodegenerativa sjukdomar. Detta arbete bidrar till området medicinsk bildanalys genom att förbättra noggrannheten och effektiviteten hos verktyg för segmentering av luktbulben, med starka implikationer för både forskningsmässiga och kliniska tillämpningar vid diagnostisering av neurodegenerativa sjukdomar.

Place, publisher, year, edition, pages
2024. , p. 49
Series
TRITA-SCI-GRU ; 2024:282
Keywords [en]
Deep Learning, U-Net, Image Segmentation, Olfactory Bulb, Neuroimaging
Keywords [sv]
Djupinlärning, U-Net, bildsegmentering, luktbulb, neuroavbildning
National Category
Other Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-361491OAI: oai:DiVA.org:kth-361491DiVA, id: diva2:1946052
External cooperation
Karolinska Institutet
Subject / course
Mathematical Statistics
Educational program
Master of Science - Applied and Computational Mathematics
Supervisors
Examiners
Available from: 2025-03-20 Created: 2025-03-20 Last updated: 2025-03-20Bibliographically approved

Open Access in DiVA

fulltext(4067 kB)28 downloads
File information
File name FULLTEXT01.pdfFile size 4067 kBChecksum SHA-512
933598ee06cc8127bbc2cbdefba2b734ec6eb4dd8708ecd80bc28b2041a6997b24fca7d5e9cb9468d2b14f1f75825be4d2f2964b4401e34dd68e629910864c96
Type fulltextMimetype application/pdf

By organisation
Mathematics (Div.)
Other Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 28 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 380 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