EUVIMEDEUVIMED entdecken
Open Access

Deep Learning for Carotid Plaque Segmentation using a Dilated U-Net Architecture

Nirvedh H Meshram iD, Carol C Mitchell, Stephanie Wilbrand, Robert J Dempsey, Tomy Varghese iD

Ultrasonic Imaging · 2020-07 · 42 (4-5) · 221-230

DOI: 10.1177/0161734620951216 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ultrasonic Imaging, online erschienen am 04.09.2020. Verfasst von Nirvedh H Meshram und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Columbia University, New York, NY, USA. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 66-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, NHLBI NIH HHS, NINDS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Carotid plaque segmentation in ultrasound longitudinal B-mode images using deep learning is presented in this work. We report on 101 severely stenotic carotid plaque patients. A standard U-Net is compared with a dilated U-Net architecture in which the dilated convolution layers were used in the bottleneck. Both a fully automatic and a semi-automatic approach with a bounding box was implemented. The performance degradation in plaque segmentation due to errors in the bounding box is quantified. We found that the bounding box significantly improved the performance of the networks with U-Net Dice coefficients of 0.48 for automatic and 0.83 for semi-automatic segmentation of plaque. Similar results were also obtained for the dilated U-Net with Dice coefficients of 0.55 for automatic and 0.84 for semi-automatic when compared to manual segmentations of the same plaque by an experienced sonographer. A 5% error in the bounding box in both dimensions reduced the Dice coefficient to 0.79 and 0.80 for U-Net and dilated U-Net respectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCarotid ArteriesCarotid StenosisHumansImage Interpretation, Computer-AssistedPlaque, AtheroscleroticUltrasonography

Stichwörter der Autor:innen

carotid plaquedeep learningsegmentation

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Columbia University, New York, NY, USA.
  • Department of Medical Physics, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA.
  • Department of Electrical and Computer Engineering, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA.
  • Department of Medicine, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA.
  • Department of Neurological Surgery, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA.

ORCID-Profile: Nirvedh H Meshram, Tomy Varghese

Förderung

  • NCI NIH HHS
  • NHLBI NIH HHS
  • NINDS NIH HHS

Zitieren

APA

Meshram, N. H., Mitchell, C. C., Wilbrand, S., Dempsey, R. J., & Varghese, T. (2020). Deep Learning for Carotid Plaque Segmentation using a Dilated U-Net Architecture. Ultrasonic Imaging, 42(4-5), 221-230. https://doi.org/10.1177/0161734620951216

Vancouver

Meshram NH, Mitchell CC, Wilbrand S, Dempsey RJ, Varghese T. Deep Learning for Carotid Plaque Segmentation using a Dilated U-Net Architecture. Ultrasonic Imaging. 2020;42(4-5):221-230. doi:10.1177/0161734620951216

BibTeX
@article{Meshram2020,
  author = {Meshram, Nirvedh H and Mitchell, Carol C and Wilbrand, Stephanie and Dempsey, Robert J and Varghese, Tomy},
  title = {Deep Learning for Carotid Plaque Segmentation using a Dilated U-Net Architecture},
  journal = {Ultrasonic Imaging},
  year = {2020},
  volume = {42},
  number = {4-5},
  pages = {221--230},
  doi = {10.1177/0161734620951216}
}
Kostenlos starten →