Rad-SpatialNet: A Frame-based Resource for Fine-Grained Spatial Relations in Radiology Reports

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 2251–2260 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 2251 Rad-SpatialNet: A Frame-based Resource for Fine-Grained Spatial Relations in Radiology Reports Surabhi Datta1, Morgan Ulinski2, Jordan Godfrey-Stovall1, Shekhar Khanpara3, Roy F. Riascos-Castaneda3, Kirk Roberts1 1School of Biomedical Informatics, The University of Texas Health Science Center at Houston 2Department of Computer Science, Columbia University 3McGovern Medical School, The University of Texas Health Science Center at Houston {surabhi.datta,kirk.roberts}@uth.tmc.edu Abstract This paper proposes a representation framework for encoding spatial language in radiology based on frame semantics. The framework is adopted from the existing SpatialNet representation in the general domain with the aim to generate more accurate representations of spatial language used by radiologists. We describe Rad-SpatialNet in detail along with illustrating the importance of incorporating domain knowledge in understanding the varied linguistic expressions involved in different radiological spatial relations. This work also constructs a corpus of 400 radiology reports of three examination types (chest X-rays, brain MRIs, and babygrams) annotated with fine-grained contextual information according to this schema. Spatial trigger expressions and elements corresponding to a spatial frame are annotated. We apply BERT-based models (BERTBASE and BERTLARGE) to first extract the trigger terms (lexical units for a spatial frame) and then to identify the related frame elements. The results of BERTLARGE are decent, with F1 of 77.89 for spatial trigger extraction and an overall F1 of 81.61 and 66.25 across all frame elements using gold and predicted spatial triggers respectively. This frame-based resource can be used to develop and evaluate more advanced natural language processing (NLP) methods for extracting fine-grained spatial information from radiology text in the future. Keywords: spatial relations, radiology, frame semantics 1. Introduction Radiology reports are one of the most important sources of medical information about a patient and are thus one of the most-targeted data sources for natural language process- ing (NLP) in medicine (Pons et al., 2016). These reports describe a radiologist’s interpretation of one or more two- or three-dimensional images (e.g., X-ray, computed tomog- raphy, magnetic resonance imaging, ultrasound, positron emission tomography). As a consequence, these reports are filled with spatial relationships between medical findings (e.g., tumor, pneumonia, inflammation) or devices (e.g., tube, stent, pacemaker) and some anatomical location (e.g., right ventricle, chest cavity, T4, femur). These relations de- scribe complex three-dimensional interactions, requiring a combination of rich linguistic representation and medical knowledge in order to process. Table 1 shows an example radiology report.1 The ex- ample demonstrates the large number of medical findings and the relationships with various anatomical entities often found within radiology reports. A flexible way of incorporating fine-grained linguis- tic representations with knowledge is through the use of frames for spatial relations (Petruck and Ellsworth, 2018). Notably, SpatialNet (Ulinski et al., 2019) extends the use of FrameNet-style frames with enabling the connection of these frames to background knowledge about how entities may interact in spatial relationships. In this paper, we propose an extension of SpatialNet …

Content truncated to 500 words