In tasks involving the interpretation of medical images, suitably trained machine-learning models often exceed the performance of medical experts. Yet such a high-level of performance typically requires that the models be trained with relevant datasets that have been painstakingly annotated by experts. Here we show that a self-supervised model trained on chest X-ray images that lack explicit annotations performs pathology-classification tasks with accuracies comparable to those of radiologists. On an external validation dataset of chest X-rays, the self-supervised model outperformed a fully supervised model in the detection of three pathologies (out of eight), and the performance generalized to pathologies that were not explicitly annotated for model training, to multiple image-interpretation tasks and to datasets from multiple institutions.

Ekin Tiu

Ellie Talius

Pujan Patel

Curtis P. Langlotz

Andrew Y. Ng

Pranav Rajpurkar

Nature Biomedical Engineering

NATURE BIOMEDICAL ENGINEERING 于 2017 年 1 月启动，将发表对生物医学工程界具有重要意义的原创研究、评论和评论，包括对设计材料、方法、技术或疗法以了解或对抗疾病感兴趣的实验室科学家；设计或优化医疗设备和程序的工程师；和临床医生利用生物医学工程的研究成果来评估患者健康或在各种临床环境和医疗保健环境中提供治疗。

Nature Biomedical Engineering was launched in January 2017 and aims to publish original research, reviews, and commentaries that are of significant importance to the field of biomedical engineering. The journal focuses on topics such as laboratory research aimed at designing materials, methods, technologies, or therapies to understand or combat diseases; the work of engineers designing or optimizing medical devices and procedures; and how clinicians utilize the findings of biomedical engineering research to assess patient health or provide treatment in various clinical and healthcare settings.

《Nature Biomedical Engineering》于2017年1月创刊，旨在发表对生物医学工程领域具有重要意义的原创研究、评论和综述。期刊关注的主题包括设计材料、方法、技术或疗法，以理解或对抗疾病的实验室科学研究；设计或优化医疗设备和程序的工程师的工作；以及临床医生如何利用生物医学工程的研究成果来评估患者健康，或在各种临床和医疗保健环境中提供治疗。

Category	Quartile
医学	1
医学, 工程生物医学	1

Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info