en
Scientific article
Open access
English

Automatic Annotation Tool to Support Supervised Machine Learning for Scaphoid Fracture Detection

Published inStudies in Health Technology and Informatics, vol. 255, p. 210-214
Publication date2018
Abstract

The aim of this work is to develop and validate an automatic annotation tool for the detection and bone localization of scaphoid fractures in radiology reports. To achieve this goal, a rule-based method using a Natural Language Processing (NLP) tool was applied. Finite state automata were constructed to detect, classify and annotate reports. An evaluation of the method on a manually annotated dataset has shown 96,8% of total match.

Keywords
  • Fractures
  • Bone/diagnosis
  • Humans
  • Natural Language Processing
  • Research Report
  • Scaphoid Bone/injuries
  • Supervised Machine Learning
Citation (ISO format)
FOUFI, Vasiliki et al. Automatic Annotation Tool to Support Supervised Machine Learning for Scaphoid Fracture Detection. In: Studies in Health Technology and Informatics, 2018, vol. 255, p. 210–214. doi: 10.3233/978-1-61499-921-8-210
Main files (1)
Article (Published version)
Identifiers
ISSN of the journal0926-9630
336views
64downloads

Technical informations

Creation11/03/2019 9:22:00 PM
First validation11/03/2019 9:22:00 PM
Update time03/15/2023 6:45:04 PM
Status update03/15/2023 6:45:04 PM
Last indexation05/05/2024 4:22:02 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack