arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.05995cs.CLcs.AIcs.LG
收藏

一种基于协同训练的双视图放射学报告分类方法

A Dual-View Approach to Classifying Radiology Reports by Co-Training

University of Alberta(阿尔伯塔大学);Alberta Machine Intelligence Institute (Amii)(阿尔伯塔机器智能研究所(Amii));School of Public Health, University of Alberta(阿尔伯塔大学公共卫生学院);Amii(Amii(阿尔伯塔机器智能研究所))

Yutong Han, Yan Yuan, Lili Mou

AI总结:

本文提出利用放射学报告的“发现”和“印象”两部分作为双视图进行协同训练,通过半监督方式利用未标注数据提升分类性能,并在公共卫生监测实验中超越现有监督与半监督方法。

摘要:

放射学报告分析能够提供有价值的信息,有助于公共卫生举措,并已引起研究界越来越多的关注。在本工作中,我们提出一种新颖的见解:放射学报告的结构(即“发现”和“印象”部分)提供了对放射扫描的不同视图。基于这一直觉,我们进一步提出一种协同训练方法,其中两个机器学习模型分别构建在“发现”和“印象”部分之上,并以半监督方式利用海量未标注数据,借助彼此的信息来提升性能。我们在一项公共卫生监测研究中进行了实验,结果表明,我们的协同训练方法能够利用双视图提升性能,并超越竞争性的监督和半监督方法。

英文摘要:

Radiology report analysis provides valuable information that can aid with public health initiatives, and has been attracting increasing attention from the research community. In this work, we present a novel insight that the structure of a radiology report (namely, the Findings and Impression sections) offers different views of a radiology scan. Based on this intuition, we further propose a co-training approach, where two machine learning models are built upon the Findings and Impression sections, respectively, and use each other's information to boost performance with massive unlabeled data in a semi-supervised manner. We conducted experiments in a public health surveillance study, and results show that our co-training approach is able to improve performance using the dual views and surpass competing supervised and semi-supervised methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑