An enhanced CRFs-based system for information extraction from radiology reports

We discuss the problem of performing information extraction from free-text radiology reports via supervised learning. In this task, segments of text (not necessarily coinciding with entire sentences, and possibly crossing sentence boundaries) need to be annotated with tags representing concepts of interest in the radiological domain. In this paper we present two novel approaches to IE for radiology reports: (i) a cascaded, two-stage method based on pipelining two taggers generated via the well known linear-chain conditional random fields (LC-CRFs) learner and (ii) a confidence-weighted ensemble method that combines standard LC-CRFs and the proposed two-stage method. We also report on the use of “positional features”, a novel type of feature intended to aid in the automatic annotation of texts in which the instances of a given concept may be hypothesized to systematically occur in specific areas of the text. We present experiments on a dataset of mammography reports in which the proposed ensemble is shown to outperform a traditional, single-stage CRFs system in two different, applicatively interesting scenarios.

A screenshot displaying a mammographic report automatically annotated according to the nine concepts of interest. The screenshot depicts the interface of the GATE system, which the two human annotators have used for manually annotating the reports.Figure optionsDownload high-quality image (338 K)Download as PowerPoint slideHighlights
► Automated information extraction from radiology reports is studied.
► Two new methods based on linear-chain conditional random fields are presented.
► A new feature representation, based on positional information, is presented.
► Experiments are run on a dataset of radiological reports.
► The experiments simulate two different, interesting applicative scenarios.