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
Signal Extraction from Scans of Electrocardiograms
KTH, School of Electrical Engineering and Computer Science (EECS).
2018 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Signalextraheringar från skanningar av elektrokardiogram (Swedish)
Abstract [en]

In this thesis, we propose a Deep Learning method for fully automated digitization of ECG (Electrocardiogram) sheets. We perform the digitization of ECG sheets in three steps: layout detection, column-wise signal segmentation, and finally signal retrieval - each of them performed by a Convolutional Neural Network. These steps leverage advances in the fields of object detection and pixel-wise segmentation due to the rise of CNNs in image processing. We train each network on synthetic images that reect the challenges of real-world data. The use of these realistic synthetic images aims at making our models robust to the variability of real-world ECG sheets. Compared with computer vision benchmarks, our networks show promising results. Our signal retrieval network significantly outperforms our implementation of the benchmark. Our column segmentation model shows robustness to overlapping signals, an issue of signal segmentation that computer vision methods are not equipped to deal with. Overall, this fully automated pipeline provides a gain in time and precision for physicians willing to digitize their ECG database.

Abstract [sv]

I detta examensarbete föreslår vi en Deep Learning-metod för fullständig automatiserad digitalisering av EKG-grafer. Vi utför digitaliseringen av EKG-graferna i tre steg: layoutdetektering, kolumnvis signalsegmentering och slutligen signalhämtning. Var och en av dem utförs av ett faltningsnätverk. Dessa nätverk är inspirerade av nätverk som används för objektdetektering och pixelvis segmentering. Vi tränar varje nätverk på syntetiska bilder som återspeglar utmaningarna i den verkliga datan. Användningen av dessa realistiska syntetiska bilder syftar till att göra våra modeller robusta mot variationer av EKG-graferna i den riktiga världen. Jämfört med riktmärkning från datorseende visar våra nätverk lovande resultat. Vårt signalhämtningsnätverk överträffar avsevärt vår implementering av riktmärket. Vår kolumnsegmenteringsmodell visar robusthet mot överlappande signaler, en fråga om signalsegmentering som metoder i datorseende inte kan hantera. Sammantaget ger denna helautomatiska pipeline en förbättring i tid och precision för läkare som är villiga att digitalisera sina EKG-databaser.

Place, publisher, year, edition, pages
2018.
Series
TRITA-EECS-EX ; 2018:777
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-248430OAI: oai:DiVA.org:kth-248430DiVA, id: diva2:1305213
External cooperation
Cardiologs
Educational program
Master of Science in Engineering - Computer Science and Technology
Supervisors
Examiners
Available from: 2019-04-30 Created: 2019-04-16 Last updated: 2019-04-30Bibliographically approved

Open Access in DiVA

fulltext(23941 kB)32 downloads
File information
File name FULLTEXT01.pdfFile size 23941 kBChecksum SHA-512
041a57a4d823599f77df17b0ce4b35321ae692345c6aa9b9efc1213353635740f6390a9babc1c2452963e0ee335c2e52bd579fb2cee11651b7299ec034eb5aed
Type fulltextMimetype application/pdf

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

Search outside of DiVA

GoogleGoogle Scholar
Total: 32 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: 50 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