ECR 2018 / C-2810
Multimedia structured reporting employing natural language processing to improve the efficiency of data entry
Congress: ECR 2018
Poster No.: C-2810
Type: Scientific Exhibit
Keywords: Computer applications, RIS, PACS, Structured reporting, Computer Applications-General, Quality assurance, Workforce
Authors: D. J. Vining, A. Pitici, C. Popovici, A. Prisacariu, M. Kontak; Houston, TX/US
DOI:10.1594/ecr2018/C-2810

Methods and materials

Our initial development of a multimedia structured reporting system, as presented at the ECR 2013, utilized a system of pull-down menus, check boxes and data entry fields to create structured data (figures 1-4) [9].

 

The system operated as follows:

  1. Records key images and voice descriptions that are transcribed to text
  2. Tags images with metadata referenced to the SNOMED-CT ontology
  3. Assembles a multimedia report with related information from serial exams arranged in timelines.

During the past year we have integrated an open-source NLP engine (Apache cTAKES) with the structured reporting system to automate the labeling of image findings with metadata that is referenced to the SNOMED-CT ontology [10]. The system labels each finding with its anatomical location, radiologic observation/diagnosis, and secondary descriptors (also known as common data elements) if those elements are contained in the verbal description provided by the radiologist (figures 5-8) [11].

SHARE THIS POSTER
2 clicks for more privacy: On the first click the button will be activated and you can then share the poster with a second click.

This website uses cookies. Learn more