liu.seSearch for publications in DiVA
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Managing imbalanced training data by sequential segmentation in machine learning
Linköpings universitet, Institutionen för medicinsk teknik, Avdelningen för medicinsk teknik.
2019 (engelsk)Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
Abstract [en]

Imbalanced training data is a common problem in machine learning applications. Thisproblem refers to datasets in which the foreground pixels are significantly fewer thanthe background pixels. By training a machine learning model with imbalanced data, theresult is typically a model that classifies all pixels as the background class. A result thatindicates no presence of a specific condition when it is actually present is particularlyundesired in medical imaging applications. This project proposes a sequential system oftwo fully convolutional neural networks to tackle the problem. Semantic segmentation oflung nodules in thoracic computed tomography images has been performed to evaluate theperformance of the system. The imbalanced data problem is present in the training datasetused in this project, where the average percentage of pixels belonging to the foregroundclass is 0.0038 %. The sequential system achieved a sensitivity of 83.1 % representing anincrease of 34 % compared to the single system. The system only missed 16.83% of thenodules but had a Dice score of 21.6 % due to the detection of multiple false positives. Thismethod shows considerable potential to be a solution to the imbalanced data problem withcontinued development.

sted, utgiver, år, opplag, sider
2019. , s. 68
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-155091ISRN: LIU-IMT-TFK-A–19/560–SEOAI: oai:DiVA.org:liu-155091DiVA, id: diva2:1296713
Fag / kurs
Biomedical Laboratory Science
Tilgjengelig fra: 2019-03-19 Laget: 2019-03-17 Sist oppdatert: 2019-03-19bibliografisk kontrollert

Open Access i DiVA

fulltext(9398 kB)131 nedlastinger
Filinformasjon
Fil FULLTEXT02.pdfFilstørrelse 9398 kBChecksum SHA-512
0f3ddbb0aa72607ac4ec0405a9416555d1f1ff4a5a7c332fb17c355ebaa6e4461860031246d347cb081afcc88ce6fba64032980039369c0fb1a6a82764ecbeed
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 131 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 1243 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf