Effectiveness of neural language models for word prediction of textual mammography reports

Mihai David Marin, Elena Mocanu, Christin Seifert

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

136 Downloads (Pure)

Abstract

Radiologists are required to write free paper text reports for breast screenings in order to assign cancer diagnoses in a later step. The current procedure requires considerable time and needs efficiency. In this paper, to streamline the writing process and keep up with the specific vocabulary, a word prediction tool using neural language models was developed. Consequently, challenges as different languages (English, Dutch), small data sizes and low computational power have been overcome by introducing a novel English-Dutch Radiology Language Modelling process. After defining model architectures, the process involves data preparation, bilevel hyperparameters optimization, configuration transfer and evaluation. The model is able to improve the current workflow and successfully meet the computational constraints, based on both an intrinsic and extrinsic evaluation. Given its flexibility, the model opens the door for future research involving other languages and also an extensive set of real-world applications.
Original languageEnglish
Title of host publication2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
PublisherIEEE SMC
ISBN (Electronic)978-1-7281-8526-2
DOIs
Publication statusPublished - 14 Dec 2020
EventIEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 - Virtual Conference
Duration: 11 Oct 202014 Oct 2020

Conference

ConferenceIEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
Period11/10/2014/10/20

Fingerprint

Dive into the research topics of 'Effectiveness of neural language models for word prediction of textual mammography reports'. Together they form a unique fingerprint.

Cite this