Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/105923
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKer, Justinen
dc.contributor.authorBai, Yeqien
dc.contributor.authorRao, Jaien
dc.contributor.authorLim, Tchoyosonen
dc.contributor.authorSingh, Satya Prakashen
dc.contributor.authorWang, Lipoen
dc.date.accessioned2019-06-18T04:35:37Zen
dc.date.accessioned2019-12-06T22:00:44Z-
dc.date.available2019-06-18T04:35:37Zen
dc.date.available2019-12-06T22:00:44Z-
dc.date.issued2019en
dc.identifier.citationKer, J., Singh, S. P., Bai, Y., Rao, J., Lim, T., & Wang, L. (2019). Image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans. Sensors, 19(9), 2167-. doi:10.3390/s19092167en
dc.identifier.issn1424-8220en
dc.identifier.urihttps://hdl.handle.net/10356/105923-
dc.description.abstractIntracranial hemorrhage is a medical emergency that requires urgent diagnosis and immediate treatment to improve patient outcome. Machine learning algorithms can be used to perform medical image classification and assist clinicians in diagnosing radiological scans. In this paper, we apply 3-dimensional convolutional neural networks (3D CNN) to classify computed tomography (CT) brain scans into normal scans (N) and abnormal scans containing subarachnoid hemorrhage (SAH), intraparenchymal hemorrhage (IPH), acute subdural hemorrhage (ASDH) and brain polytrauma hemorrhage (BPH). The dataset used consists of 399 volumetric CT brain images representing approximately 12,000 images from the National Neuroscience Institute, Singapore. We used a 3D CNN to perform both 2-class (normal versus a specific abnormal class) and 4-class classification (between normal, SAH, IPH, ASDH). We apply image thresholding at the image pre-processing step, that improves 3D CNN classification accuracy and performance by accentuating the pixel intensities that contribute most to feature discrimination. For 2-class classification, the F1 scores for various pairs of medical diagnoses ranged from 0.706 to 0.902 without thresholding. With thresholding implemented, the F1 scores improved and ranged from 0.919 to 0.952. Our results are comparable to, and in some cases, exceed the results published in other work applying 3D CNN to CT or magnetic resonance imaging (MRI) brain scan classification. This work represents a direct application of a 3D CNN to a real hospital scenario involving a medically emergent CT brain diagnosisen
dc.format.extent12 p.en
dc.language.isoenen
dc.relation.ispartofseriesSensorsen
dc.rights© 2019 The Authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).en
dc.subjectMachine Learningen
dc.subject3D Convolutional Neural Networksen
dc.subjectDRNTU::Engineering::Electrical and electronic engineeringen
dc.titleImage thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scansen
dc.typeJournal Articleen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen
dc.identifier.doi10.3390/s19092167en
dc.description.versionPublished versionen
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:EEE Journal Articles

SCOPUSTM   
Citations 5

142
Updated on Mar 21, 2024

Web of ScienceTM
Citations 5

92
Updated on Oct 27, 2023

Page view(s)

239
Updated on Mar 27, 2024

Download(s) 50

86
Updated on Mar 27, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.