Understanding spatial language in radiology: Representation framework, annotation, and spatial relation extraction from chest X-ray reports using deep learning.
Understanding spatial language in radiology: Representation framework, annotation, and spatial relation extraction from chest X-ray reports using deep learning.
复制标题
DOI：
10.1016/j.jbi.2020.103473
复制
发表时间：
2020-08
影响因子：
4.5
通讯作者：
Roberts K
中科院分区：
文献类型：
--
作者：
Datta S;Si Y;Rodriguez L;Shooshan SE;Demner-Fushman D;Roberts K
放射学报告包含放射科医师对图像的解释，并且这些图像经常描述空间关系。重要的影像学表现大多通过空间介词来描述解剖位置。这种空间关系也与各种鉴别诊断有关，并且经常通过不确定性短语来描述。这种临床上重要的空间信息的结构化表示有可能用于各种下游临床信息学应用。我们的重点是从报告中提取这些空间表示。为此，我们首先定义了一个表示框架的基础上的空间角色标签（SpRL）计划，我们称之为Rad-SpRL。在Rad-SpRL中，与空间关系相关的常见放射性实体通过四个空间角色进行编码：标记、地标、诊断和对冲，所有这些都与空间介词（或空间指示符）有关。我们共注释了2,000份Rad-SpRL后的胸部X线报告。然后，我们提出了一种基于深度学习的自然语言处理（NLP）方法，涉及单词和字符级编码，首先提取空间指示符，然后识别相应的空间角色。具体来说，我们使用双向长短期记忆（Bi-LSTM）条件随机场（CRF）神经网络作为基线模型。此外，我们还结合了来自预训练语言模型（BERT和XLNet）的上下文化单词表示来提取空间信息。我们评估黄金和预测的空间指标，以提取四种类型的空间角色。结果令人鼓舞，空间指标提取的最高平均F1度量为91.29（XLNet）;考虑所有四个空间角色的最高平均整体F1度量为92.9使用黄金指标（XLNet）;使用预测指标（BERT在MIMIC笔记上预训练）为85.6。该语料库可在Mendeley的http://dx.doi.org/10.17632/yhb26hfz8n.1和https://github.com/krobertslab/datasets/blob/master/Rad-SpRL.xml上获得。
Radiology reports contain a radiologist’s interpretations of images, and these images frequently describe spatial relations. Important radiographic findings are mostly described in reference to an anatomical location through spatial prepositions. Such spatial relationships are also linked to various differential diagnoses and often described through uncertainty phrases. Structured representation of this clinically significant spatial information has the potential to be used in a variety of downstream clinical informatics applications. Our focus is to extract these spatial representations from the reports. For this, we first define a representation framework based on the Spatial Role Labeling (SpRL) scheme, which we refer to as Rad-SpRL. In Rad-SpRL, common radiological entities tied to spatial relations are encoded through four spatial roles: trajector, landmark, diagnosis, and hedge, all identified in relation to a spatial preposition (or spatial indicator). We annotated a total of 2,000 chest X-ray reports following Rad-SpRL. We then propose a deep learning-based natural language processing (NLP) method involving word and character-level encodings to first extract the spatial indicators followed by identifying the corresponding spatial roles. Specifically, we use a bidirectional long short-term memory (Bi-LSTM) conditional random field (CRF) neural network as the baseline model. Additionally, we incorporate contextualized word representations from pre-trained language models (BERT and XLNet) for extracting the spatial information. We evaluate both gold and predicted spatial indicators to extract the four types of spatial roles. The results are promising, with the highest average F1 measure for spatial indicator extraction being 91.29 (XLNet); the highest average overall F1 measure considering all the four spatial roles being 92.9 using gold indicators (XLNet); and 85.6 using predicted indicators (BERT pre-trained on MIMIC notes). The corpus is available in Mendeley at http://dx.doi.org/10.17632/yhb26hfz8n.1 and https://github.com/krobertslab/datasets/blob/master/Rad-SpRL.xml.
登录
查看更多内容
DOI：
10.1136/jamia.1994.95236146
发表时间：
1994-03-01
影响因子：
6.4
作者：
FRIEDMAN, C;ALDERSON, PO;JOHNSON, SB
通讯作者：
JOHNSON, SB
通过自然语言处理描述放射学报告中临床结果的变化和意义
影响因子：
4.4
作者：
Hassanpour, Saeed;Bay, Graham;Langlotz, Curtis P.
通讯作者：
Langlotz, Curtis P.
影响因子：
3
作者：
Kordjamshidi P;Roth D;Moens MF
通讯作者：
Moens MF
DOI：
10.1093/jamia/ocv080
发表时间：
2016-03-01
影响因子：
6.4
作者：
Demner-Fushman, Dina;Kohli, Marc D.;McDonald, Clement J.
通讯作者：
McDonald, Clement J.
影响因子：
1.9
作者：
Alex, Beatrice;Grover, Claire;Whiteley, William
通讯作者：
Whiteley, William