Image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans

Intracranial 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-dimensio...

Full description

Saved in:
Bibliographic Details
Main Authors: Ker, Justin, Bai, Yeqi, Rao, Jai, Lim, Tchoyoson, Singh, Satya Prakash, Wang, Lipo
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2019
Subjects:
Online Access:https://hdl.handle.net/10356/105923
http://hdl.handle.net/10220/48796
http://dx.doi.org/10.3390/s19092167
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-105923
record_format dspace
spelling sg-ntu-dr.10356-1059232019-12-06T22:00:44Z Image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans Ker, Justin Bai, Yeqi Rao, Jai Lim, Tchoyoson Singh, Satya Prakash Wang, Lipo School of Electrical and Electronic Engineering Machine Learning 3D Convolutional Neural Networks DRNTU::Engineering::Electrical and electronic engineering Intracranial 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 diagnosis Published version 2019-06-18T04:35:37Z 2019-12-06T22:00:44Z 2019-06-18T04:35:37Z 2019-12-06T22:00:44Z 2019 Journal Article Ker, 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/s19092167 1424-8220 https://hdl.handle.net/10356/105923 http://hdl.handle.net/10220/48796 http://dx.doi.org/10.3390/s19092167 en Sensors © 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/). 12 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Machine Learning
3D Convolutional Neural Networks
DRNTU::Engineering::Electrical and electronic engineering
spellingShingle Machine Learning
3D Convolutional Neural Networks
DRNTU::Engineering::Electrical and electronic engineering
Ker, Justin
Bai, Yeqi
Rao, Jai
Lim, Tchoyoson
Singh, Satya Prakash
Wang, Lipo
Image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans
description Intracranial 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 diagnosis
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Ker, Justin
Bai, Yeqi
Rao, Jai
Lim, Tchoyoson
Singh, Satya Prakash
Wang, Lipo
format Article
author Ker, Justin
Bai, Yeqi
Rao, Jai
Lim, Tchoyoson
Singh, Satya Prakash
Wang, Lipo
author_sort Ker, Justin
title Image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans
title_short Image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans
title_full Image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans
title_fullStr Image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans
title_full_unstemmed Image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans
title_sort image thresholding improves 3-dimensional convolutional neural network diagnosis of different acute brain hemorrhages on computed tomography scans
publishDate 2019
url https://hdl.handle.net/10356/105923
http://hdl.handle.net/10220/48796
http://dx.doi.org/10.3390/s19092167
_version_ 1681039362427453440