In this study, we investigated whether self-supervised pretraining could
produce a neural network feature extractor applicable to multiple
classification tasks in B-mode lung ultrasound analysis. When fine-tuning on
three lung ultrasound tasks, pretrained models resulted in an improvement of
the average across-task area under the receiver operating curve (AUC) by 0.032
and 0.061 on local and external test sets respectively. Compact nonlinear
classifiers trained on features outputted by a single pretrained model did not
improve performance across all tasks; however, they did reduce inference time
by 49% compared to serial execution of separate fine-tuned models. When
training using 1% of the available labels, pretrained models consistently
outperformed fully supervised models, with a maximum observed test AUC increase
of 0.396 for the task of view classification. Overall, the results indicate
that self-supervised pretraining is useful for producing initial weights for
lung ultrasound classifiers.

通过自监督预训练可以生成适用于多种 B 模式肺部超声分析分类任务的神经网络特征提取器，经预训练模型在三项肺部超声任务的微调后，平均跨任务下的受试者工作特性曲线（AUC）面积分别提高了 0.032 和 0.061， 紧凑非线性分类器在单个预训练模型输出的特征上训练并不能提高所有任务的性能，但比起独立微调模型的串行执行，推理时间缩短了 49%；在仅使用 1％的标签进行训练时，预训练模型始终优于全监督模型，对于视图分类任务，最大观察到的测试 AUC 提高了 0.396。总体而言，结果表明自监督预训练有助于生成用于肺部超声分类器的初始权重。