Self-supervised pretraining has been observed to improve performance in
supervised learning tasks in medical imaging. This study investigates the
utility of self-supervised pretraining prior to conducting supervised
fine-tuning for the downstream task of lung sliding classification in M-mode
lung ultrasound images. We propose a novel pairwise relationship that couples
M-mode images constructed from the same B-mode image and investigate the
utility of data augmentation procedure specific to M-mode lung ultrasound. The
results indicate that self-supervised pretraining yields better performance
than full supervision, most notably for feature extractors not initialized with
ImageNet-pretrained weights. Moreover, we observe that including a vast volume
of unlabelled data results in improved performance on external validation
datasets, underscoring the value of self-supervision for improving
generalizability in automatic ultrasound interpretation. To the authors' best
knowledge, this study is the first to characterize the influence of
self-supervised pretraining for M-mode ultrasound.

本研究探讨了在 M 模式肺超声图像的肺滑动分类任务中，进行自监督预训练对于监督微调的实用性，结果表明，相对于完全监督，自监督预训练表现更好，特别是对于未使用 ImageNet 预训练权重来初始化特征提取器的情况下。此外，包含大量未标记数据可提高外部验证集上的表现，突显了自我监督在提高自动超声识别的泛化能力方面的价值。

自监督预训练策略在 M 型肺部超声中发现无肺滑动的实用性探索

Exploring the Utility of Self-Supervised Pretraining Strategies for the  Detection of Absent Lung Sliding in M-Mode Lung Ultrasound

Contemporary artificial neural networks (ANN) are trained end-to-end, jointly
learning both features and classifiers for the task of interest. Though
enormously effective, this paradigm imposes significant costs in assembling
annotated task-specific datasets and training large-scale networks. We propose
to decouple feature learning from downstream lung ultrasound tasks by
introducing an auxiliary pre-task of visual biomarker classification. We
demonstrate that one can learn an informative, concise, and interpretable
feature space from ultrasound videos by training models for predicting
biomarker labels. Notably, biomarker feature extractors can be trained from
data annotated with weak video-scale supervision. These features can be used by
a variety of downstream Expert models targeted for diverse clinical tasks
(Diagnosis, lung severity, S/F ratio). Crucially, task-specific expert models
are comparable in accuracy to end-to-end models directly trained for such
target tasks, while being significantly lower cost to train.

该研究提出了一种通过引入辅助的预任务 (视觉生物标志分类) 来将特征学习与下游肺部超声任务分离的方法；通过为预测生物标志标签训练模型，可以学习到一种信息丰富、简洁和可解释的超声视频特征空间。这些特征可以被用于各种下游临床任务的专家模型中，这些任务包括诊断、肺部严重程度以及 S/F 比；与直接针对这些任务进行训练的端到端模型相比，这些任务特定的专家模型具有可比的准确度，同时成本显著降低。

学习通用肺部超声生物标志物以解耦特征提取与下游任务

Learning Generic Lung Ultrasound Biomarkers for Decoupling Feature Extraction from Downstream Tasks

The new coronavirus 2019 (COVID-2019) has rapidly become a pandemic and has
had a devastating effect on both everyday life, public health and the global
economy. It is critical to detect positive cases as early as possible to
prevent the further spread of this epidemic and to treat affected patients
quickly. The need for auxiliary diagnostic tools has increased as accurate
automated tool kits are not available. This paper presents a work in progress
that proposes the analysis of images of lung ultrasound scans using a
convolutional neural network. The trained model will be used on a Raspberry Pi
to predict on new images.

该论文提出利用卷积神经网络分析肺部超声扫描图像，以检测 COVID-19 病例，成为辅助诊断工具的一种尝试。