University of Twente Student Theses

Login

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

Marin, Mihai David (2019) Effectiveness of neural language models for word prediction of textual mammography reports.

[img] PDF
9MB
Abstract:Radiologists are required to write free paper paper text reports for breast screenings in order to assign cancer diagnoses in a later step. The current procedure requires a lot of time and needs efficiency. To streamline the writing process and keep up with the specific vocabulary, a word prediction tool using neural language models was developed. Challenges as different languages (English,Dutch), small data sizes and low computational power have been overcome by introducing EnDuRLM process, able to improve by 25\% the current workflow according to RPE measurement. After defining model architectures, EnDuRLM process involves data preparation, hyperparameters optimization, configuration transfer and evaluation. This work supports future research involving other languages and also an extensive set of real-world applications.
Item Type:Essay (Bachelor)
Clients:
ZGT, Hengelo, Netherlands
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Awards:Best Paper in Data Science Track
Keywords:Mammography, Medical reports, Neural language model, Text generation, Natural language processing
Link to this item:http://purl.utwente.nl/essays/78779
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page