期刊
NATURE BIOMEDICAL ENGINEERING
卷 6, 期 12, 页码 1399-1406出版社
NATURE PORTFOLIO
DOI: 10.1038/s41551-022-00936-9
关键词
-
A self-supervised model trained on chest X-ray images without explicit annotations achieves comparable accuracy to radiologists in pathology-classification tasks, demonstrating generalization to multiple pathologies, image-interpretation tasks, and datasets from different institutions.
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. 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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据