Self-supervised Representation Learning for Ultrasound Video

TL;DR

This paper introduces a self-supervised learning method for ultrasound videos that learns meaningful representations without annotations by solving anatomy-aware tasks, improving performance on downstream medical imaging tasks.

Contribution

It presents a novel self-supervised approach that leverages anatomy-aware tasks to learn transferable representations from unlabeled ultrasound videos.

Findings

Effective learning of representations from unlabeled ultrasound videos.

Strong transferability to downstream tasks like plane detection and saliency prediction.

Improved performance over baseline methods.

Abstract

Recent advances in deep learning have achieved promising performance for medical image analysis, while in most cases ground-truth annotations from human experts are necessary to train the deep model. In practice, such annotations are expensive to collect and can be scarce for medical imaging applications. Therefore, there is significant interest in learning representations from unlabelled raw data. In this paper, we propose a self-supervised learning approach to learn meaningful and transferable representations from medical imaging video without any type of human annotation. We assume that in order to learn such a representation, the model should identify anatomical structures from the unlabelled data. Therefore we force the model to address anatomy-aware tasks with free supervision from the data itself. Specifically, the model is designed to correct the order of a reshuffled video clip and at the same time predict the geometric transformation applied to the video clip. Experiments on fetal ultrasound video show that the proposed approach can effectively learn meaningful and strong representations, which transfer well to downstream tasks like standard plane detection and saliency prediction.