Intra-video positive pairs in self-supervised learning for ultrasound
Frontiers in Imaging · 2024
DOI: 10.3389/fimag.2024.1416114 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Imaging, 2024. Verfasst von Blake VanBerlo und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Introduction
Self-supervised learning (SSL) is a strategy for addressing the paucity of labelled data in medical imaging by learning representations from unlabelled images. Contrastive and non-contrastive SSL methods produce learned representations that are similar for pairs of related images. Such pairs are commonly constructed by randomly distorting the same image twice. The videographic nature of ultrasound offers flexibility for defining the similarity relationship between pairs of images.
Methods
We investigated the effect of utilizing proximal, distinct images from the same B-mode ultrasound video as pairs for SSL. Additionally, we introduced a sample weighting scheme that increases the weight of closer image pairs and demonstrated how it can be integrated into SSL objectives.
Results
Named Intra-Video Positive Pairs (IVPP), the method surpassed previous ultrasound-specific contrastive learning methods' average test accuracy on COVID-19 classification with the POCUS dataset by ≥ 1.3%. Detailed investigations of IVPP's hyperparameters revealed that some combinations of IVPP hyperparameters can lead to improved or worsened performance, depending on the downstream task.
Discussion
Guidelines for practitioners were synthesized based on the results, such as the merit of IVPP with task-specific hyperparameters, and the improved performance of contrastive methods for ultrasound compared to non-contrastive counterparts.
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
VanBerlo, B., Wong, A., Hoey, J., & Arntfield, R. (2024). Intra-video positive pairs in self-supervised learning for ultrasound. Frontiers in Imaging. https://doi.org/10.3389/fimag.2024.1416114
Vancouver
VanBerlo B, Wong A, Hoey J, Arntfield R. Intra-video positive pairs in self-supervised learning for ultrasound. Frontiers in Imaging. 2024. doi:10.3389/fimag.2024.1416114
BibTeX
@article{VanBerlo2024,
author = {VanBerlo, Blake and Wong, Alexander and Hoey, Jesse and Arntfield, Robert},
title = {Intra-video positive pairs in self-supervised learning for ultrasound},
journal = {Frontiers in Imaging},
year = {2024},
doi = {10.3389/fimag.2024.1416114}
}
EUVIMED