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.

翻译：本研究探究了自监督预训练能否为B模式肺部超声分析中的多项分类任务生成通用的神经网络特征提取器。在三项肺部超声任务的微调过程中，预训练模型使本地测试集和外部测试集的平均跨任务受试者工作特征曲线下面积（AUC）分别提升了0.032和0.061。基于单一预训练模型输出特征训练的紧凑型非线性分类器虽未能在所有任务上提高性能，但与串行执行多个独立微调模型相比，其推理时间减少了49%。当仅使用1%的可用标签进行训练时，预训练模型始终优于全监督模型，在视图分类任务中观测到的最大测试集AUC提升达0.396。总体结果表明，自监督预训练对生成肺部超声分类器的初始权重具有重要价值。