Please use this identifier to cite or link to this item: https://doi.org/10.15480/882.3821
Publisher DOI: 10.1007/s11548-021-02417-x
Title: Capsule networks for segmentation of small intravascular ultrasound image datasets
Language: English
Authors: Bargsten, Lennart 
Raschka, Silas 
Schlaefer, Alexander 
Keywords: Capsule networks; Deep learning; Image segmentation; Intravascular ultrasound; Small datasets
Issue Date: 14-Jun-2021
Publisher: Springer
Source: International Journal of Computer Assisted Radiology and Surgery 16 (8): 1243–1254 (2021)
Abstract (english): 
Purpose: Intravascular ultrasound (IVUS) imaging is crucial for planning and performing percutaneous coronary interventions. Automatic segmentation of lumen and vessel wall in IVUS images can thus help streamlining the clinical workflow. State-of-the-art results in image segmentation are achieved with data-driven methods like convolutional neural networks (CNNs). These need large amounts of training data to perform sufficiently well but medical image datasets are often rather small. A possibility to overcome this problem is exploiting alternative network architectures like capsule networks. Methods: We systematically investigated different capsule network architecture variants and optimized the performance on IVUS image segmentation. We then compared our capsule network with corresponding CNNs under varying amounts of training images and network parameters. Results: Contrary to previous works, our capsule network performs best when doubling the number of capsule types after each downsampling stage, analogous to typical increase rates of feature maps in CNNs. Maximum improvements compared to the baseline CNNs are 20.6% in terms of the Dice coefficient and 87.2% in terms of the average Hausdorff distance. Conclusion: Capsule networks are promising candidates when it comes to segmentation of small IVUS image datasets. We therefore assume that this also holds for ultrasound images in general. A reasonable next step would be the investigation of capsule networks for few- or even single-shot learning tasks.
URI: http://hdl.handle.net/11420/9828
DOI: 10.15480/882.3821
ISSN: 1861-6429
Journal: International journal of computer assisted radiology and surgery 
Institute: Medizintechnische und Intelligente Systeme E-1 
Document Type: Article
Project: MALEKA: Maschinelle Lernverfahren für die kardiovaskuläre Bildgebung auf der Grundlage des Programms für Innovation (PROFI) - Modul PROFI Transfer Plus 
Projekt DEAL 
License: CC BY 4.0 (Attribution) CC BY 4.0 (Attribution)
Appears in Collections:Publications with fulltext

Files in This Item:
File Description SizeFormat
Bargsten2021_Article_CapsuleNetworksForSegmentation.pdfVerlags-PDF1,34 MBAdobe PDFView/Open
Thumbnail
Show full item record

Google ScholarTM

Check

Note about this record

Cite this record

Export

This item is licensed under a Creative Commons License Creative Commons