Most deep neural networks (DNNs) based ultrasound (US) medical image analysis
models use pretrained backbones (e.g., ImageNet) for better model
generalization. However, the domain gap between natural and medical images
causes an inevitable performance bottleneck. To alleviate this problem, an US
dataset named US-4 is constructed for direct pretraining on the same domain. It
contains over 23,000 images from four US video sub-datasets. To learn robust
features from US-4, we propose an US semi-supervised contrastive learning
method, named USCL, for pretraining. In order to avoid high similarities
between negative pairs as well as mine abundant visual features from limited US
videos, USCL adopts a sample pair generation method to enrich the feature
involved in a single step of contrastive optimization. Extensive experiments on
several downstream tasks show the superiority of USCL pretraining against
ImageNet pretraining and other state-of-the-art (SOTA) pretraining approaches.
In particular, USCL pretrained backbone achieves fine-tuning accuracy of over
94% on POCUS dataset, which is 10% higher than 84% of the ImageNet pretrained
model. The source codes of this work are available at
this https URL

通过使用 US-4 数据集进行直接预训练，提出了一种名为 USCL 的 US 半监督对比学习方法，以学习来自 US-4 的功能强大的特征，并在多项下游任务中取得超越 ImageNet 预训练和其他 SOTA 预训练方法的结果。