Please use this identifier to cite or link to this item:
Publisher DOI: 10.1515/cdbme-2021-1021
Title: Deep learning for calcium segmentation in intravascular ultrasound images
Language: English
Authors: Holstein, Lennart 
Riedl, Katharina Alina 
Wissel, Tobias 
Brunner, Fabian J. 
Schaefers, Klaus 
Graß, Michael 
Blankenberg, Stefan 
Seiffert, Moritz 
Schlaefer, Alexander 
Keywords: Convolutional neural network; Coronary artery; Multi-task learning; Small dataset; Vessel
Issue Date: 1-Aug-2021
Publisher: De Gruyter
Source: Current Directions in Biomedical Engineering 7 (1): 20211123 (2021-08-01)
Abstract (english): 
Knowing the shape of vascular calcifications is crucial for appropriate planning and conductance of percutaneous coronary interventions. The clinical workflow can therefore benefit from automatic segmentation of calcified plaques in intravascular ultrasound (IVUS) images. To solve segmentation problems with convolutional neural networks (CNNs), large datasets are usually required. However, datasets are often rather small in the medical domain. Hence, developing and investigating methods for increasing CNN performance on small datasets can help on the way towards clinically relevant results. We compared two state-of-the-art CNN architectures for segmentation, U-Net and DeepLabV3, and investigated how incorporating auxiliary image data with vessel wall and lumen annotations improves the calcium segmentation performance by using these either for pretraining or multi-task training. DeepLabV3 outperforms U-Net with up to 6.3 % by means of the Dice coefficient and 36.5 % by means of the average Hausdorff distance. Using auxiliary data improves the segmentation performance in both cases, whereas the multi-task approach outperforms the pre-training approach. The improvements of the multi-task approach in contrast to not using auxiliary data at all is 5.7 % for the Dice coefficient and 42.9 % for the average Hausdorff distance. Automatic segmentation of calcified plaques in IVUS images is a demanding task due to their relatively small size compared to the image dimensions and due to visual ambiguities with other image structures. We showed that this problem can generally be tackled by CNNs. Furthermore, we were able to improve the performance by a multi-task learning approach with auxiliary segmentation data.
DOI: 10.15480/882.3824
ISSN: 2364-5504
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 
License: CC BY 4.0 (Attribution) CC BY 4.0 (Attribution)
Appears in Collections:Publications with fulltext

Files in This Item:
File Description SizeFormat
10.1515_cdbme-2021-1021.pdfVerlags-PDF1,37 MBAdobe PDFView/Open
Show full item record

Page view(s)

Last Week
Last month
checked on May 29, 2023


checked on May 29, 2023

Google ScholarTM


Note about this record

Cite this record


This item is licensed under a Creative Commons License Creative Commons