Attention via Scattering Transforms for Segmentation of Small Intravascular Ultrasound Data Sets

Publikationstyp
Conference Paper
Date Issued
2021-07
Sprache
English
Author(s)
Holstein, Lennart 
Riedl, Katharina Alina  
Wissel, Tobias  
Brunner, Fabian J.  
Schaefers, Klaus  
Grass, Michael  
Blankenberg, Stefan  
Seiffert, Moritz  
Schlaefer, Alexander  
Herausgeber*innen
Heinrich, Mattias
Dou, Qi
Bruijne, Marleen de
Lellmann, Jan
Schlaefer, Alexander  
Ernst, Floris
Institut
Medizintechnische und Intelligente Systeme E-1  
TORE-URI
http://hdl.handle.net/11420/11559
First published in
Proceedings of machine learning research  
Number in series
143
Start Page
34
End Page
47
Citation
Proceedings of Machine Learning Research 143: 34-47 (2021)
Contribution to Conference
4th Conference on Medical Imaging with Deep Learning, MIDL 2021  
Publisher Link
https://proceedings.mlr.press/v143/bargsten21a.html
Scopus ID
2-s2.0-85160313021
Publisher
Microtome Publishing
Using intracoronary imaging modalities like intravascular ultrasound (IVUS) has a positive impact on the results of percutaneous coronary interventions. Efficient extraction of important vessel metrics like lumen diameter, vessel wall thickness or plaque burden via automatic segmentation of IVUS images can improve the clinical workflow. State-of-the-art segmentation results are usually achieved by data-driven methods like convolutional neural networks (CNNs). However, clinical data sets are often rather small leading to extraction of image features which are not very meaningful and thus decreasing performance. This is also the case for some applications which inherently allow for only small amounts of available data, e.g., detection of diseases with extremely small prevalence or online-adaptation of an existing algorithm to individual patients. In this work we investigate how integrating scattering transformations - as special forms of wavelet transformations - into CNNs could improve the extraction of meaningful features. To this end, we developed a novel network module which uses features of a scattering transform for an attention mechanism. We observed that this approach improves the results of calcium segmentation up to 8.2% (relatively) in terms of the Dice coefficient and 24.8% in terms of the modified Hausdorff distance. In the case of lumen and vessel wall segmentation, the improvements are up to 2.3% (relatively) in terms of the Dice coefficient and 30.8% in terms of the modified Hausdorff distance.Incorporating scattering transformations as a component of an attention block into CNNs improves the segmentation results on small IVUS segmentation data sets. In general, scattering transformations can help in situations where efficient feature extractors can not be learned via the training data. This makes our attention module an interesting candidate for applications like few-shot learning for patient adaptation or detection of rare diseases.
DDC Class
600: Technology