Cristin-resultat-ID: 1775259
Sist endret: 3. mars 2020, 14:14
NVI-rapporteringsår: 2019
Resultat
Vitenskapelig artikkel
2019

Segmentation of apical long axis, four- and two-chamber views using deep neural networks

Bidragsytere:
  • Erik Smistad
  • Ivar Mjåland Salte
  • Andreas Østvik
  • Sarah Leclerc
  • Olivier Bernard og
  • Lasse Løvstakken

Tidsskrift

Proceedings - IEEE Ultrasonics Symposium
ISSN 1948-5719
e-ISSN 1948-5727
NVI-nivå 1

Om resultatet

Vitenskapelig artikkel
Publiseringsår: 2019
Volum: 2019-October
Sider: 8 - 11

Importkilder

Scopus-ID: 2-s2.0-85077578645

Beskrivelse Beskrivelse

Tittel

Segmentation of apical long axis, four- and two-chamber views using deep neural networks

Sammendrag

It has been shown that deep neural networks can accuratly segment the left ventricle (LV), myocardium and left atrium in apical two and four chamber (A2C and A4C) views. While segmentation of apical long-axis (ALAX) views is quite similar to A2C and A4C, there is one major difference; the left ventricular outflow tract (LVOT) which restricts the myocardium. The objectives of this work were to accurately segment ALAX views, investigate if transfer learning from A2C/A4C improves accuracy, and study how a single network can learn to segment all three views.The CAMUS dataset of 500 patients together with an additional dataset of 106 patients with ALAX views were used for training and testing using 10-fold cross-validation. The results showed that by training from scratch the neural network was able to segment ALAX views, but with a lower accuracy to that of A2C/A4C views. Transfer learning only slightly improved mycoardium accuracy (0.77 to 0.78), but was statistically significant (p-value 0.001). Multi-view segmentation with the baseline network showed a reduction in accuracy, resulting in 38 cases of incorrect segmentations in terms of LVOT. The proposed network reduced the number of incorrect segmentations to 8, and achieved the best overall accuracy in terms of dice score where the improvement in myocardium segmentation accuracy (0.776 to 0.786) was statistically significant (p-value 0.005).

Bidragsytere

Erik Smistad

  • Tilknyttet:
    Forfatter
    ved Institutt for sirkulasjon og bildediagnostikk ved Norges teknisk-naturvitenskapelige universitet
  • Tilknyttet:
    Forfatter
    ved Helse ved SINTEF AS

Ivar Mjåland Salte

  • Tilknyttet:
    Forfatter
    ved Fakultet for medisin og helsevitenskap ved Norges teknisk-naturvitenskapelige universitet
  • Tilknyttet:
    Forfatter
    ved Medisinsk klinikk ved Sørlandet sykehus HF

Andreas Østvik

  • Tilknyttet:
    Forfatter
    ved Institutt for sirkulasjon og bildediagnostikk ved Norges teknisk-naturvitenskapelige universitet
  • Tilknyttet:
    Forfatter
    ved Helse ved SINTEF AS

Sarah Leclerc

  • Tilknyttet:
    Forfatter
    ved INSA Institut National des Sciences Appliquées Centre Val de Loire

Olivier Bernard

  • Tilknyttet:
    Forfatter
    ved INSA Institut National des Sciences Appliquées Centre Val de Loire
1 - 5 av 6 | Neste | Siste »