Please use this identifier to cite or link to this item:
Title: Deep Learning-Based Brain Hemorrhage Detection in CT Reports
Authors: Bayrak, Gıyaseddin
Toprak, M. Şakir
Ganiz, Murat Can
Kodaz, Halife
Koç, Ural
Keywords: Brain Hemorrhage
Deep Learning
Computational linguistics
Computerized tomography
Deep learning
Medical informatics
Natural language processing systems
Brain hemorrhage
Critical case
Deep learning
Domain specific
Fine tuning
Hemorrhage detection
Language model
Learning classifiers
Radiology reports
brain hemorrhage
natural language processing
x-ray computed tomography
Deep Learning
Intracranial Hemorrhages
Natural Language Processing
Research Report
Tomography, X-Ray Computed
Issue Date: 2022
Publisher: IOS Press BV
Abstract: Radiology reports can potentially be used to detect critical cases that need immediate attention from physicians. We focus on detecting Brain Hemorrhage from Computed Tomography (CT) reports. We train a deep learning classifier and observe the effect of using different pre-trained word representations along with domain-specific fine-tuning. We have several contributions. Firstly, we report the results of a large-scale classification model for brain hemorrhage detection from Turkish radiology reports. Second, we show the effect of fine-tuning pre-trained language models using domain-specific data on the performance. We conclude that deep learning models can be used for detecting brain Hemorrhage with reasonable accuracy and fine-tuning language models using domain-specific data to improve classification performance. © 2022 European Federation for Medical Informatics (EFMI) and IOS Press.
Description: Norwegian Centre for E-health Research
32nd Medical Informatics Europe Conference, MIE 2022 -- 27 May 2022 through 30 May 2022 -- 179490
ISBN: 9781643682846
ISSN: 0926-9630
Appears in Collections:Mühendislik ve Doğa Bilimleri Fakültesi Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu / PubMed Indexed Publications Collections
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections

Show full item record

CORE Recommender


checked on Mar 18, 2023

Page view(s)

checked on Mar 20, 2023

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.