Transfer learning based histopathologic image classification for burns recognition

Ahmad Musa; Aliyu Abubakar; Hassan Ugail; Ali Maina Bukar; Ali Ahmad Aminu

doi:10.1109/ICECCO48375.2019.9043205

Transfer learning based histopathologic image classification for burns recognition

Ahmad Musa
, Aliyu Abubakar
, Hassan Ugail
, Ali Maina Bukar
, Ali Ahmad Aminu

Research output: Chapter in Book/Report/Conference proceeding › Chapter

4 Citations (Scopus)

Abstract

Burn is one of the most leading devastating
injuries affecting people worldwide with high impact rate in
low-and middle-income countries subjecting hundreds of
thousands to loss of lives and physical deformities. Both
affected individuals and health institutions are faced with
challenges such as inadequate experience/well trained
workforce and high diagnostics cost. The demand of having
efficient, cost-effective and user-friendly technique to aid in addressing the problem is on the rise. Deep neural networks have recently attracted the attention of many researchers and achieved impressive results in many applications. Therefore, this paper proposed the use of off-the-shelf Convolutional Neural Network features from two ImageNet pre-trained models (GoogleNet and ResNet152), VGG-Face. The features are used to train Support Vector Machine (SVM) and Decision Tree (DT). 100% identification accuracy was recorded using ImageNet model and SVM.

Original language	English
Title of host publication	2019 15th International Conference on Electronics, Computer and Computation (ICECCO)
Publisher	IEEE
ISBN (Print)	9781728151601, 9781728151595, 9781728151618
DOIs	https://doi.org/10.1109/ICECCO48375.2019.9043205
Publication status	Published - 2019

Keywords

Bruises
Burns
Classification
Convolutional neural network
Decision tree
Support vector machine

Access to Document

10.1109/ICECCO48375.2019.9043205

Cite this

@inbook{328e4439983940c6a0659368e49f298d,

title = "Transfer learning based histopathologic image classification for burns recognition",

abstract = "Burn is one of the most leading devastating injuries affecting people worldwide with high impact rate in low-and middle-income countries subjecting hundreds of thousands to loss of lives and physical deformities. Both affected individuals and health institutions are faced with challenges such as inadequate experience/well trained workforce and high diagnostics cost. The demand of having efficient, cost-effective and user-friendly technique to aid in addressing the problem is on the rise. Deep neural networks have recently attracted the attention of many researchers and achieved impressive results in many applications. Therefore, this paper proposed the use of off-the-shelf Convolutional Neural Network features from two ImageNet pre-trained models (GoogleNet and ResNet152), VGG-Face. The features are used to train Support Vector Machine (SVM) and Decision Tree (DT). 100\% identification accuracy was recorded using ImageNet model and SVM.",

keywords = "Bruises, Burns, Classification, Convolutional neural network, Decision tree, Support vector machine",

author = "Ahmad Musa and Aliyu Abubakar and Hassan Ugail and Bukar, \{Ali Maina\} and Aminu, \{Ali Ahmad\}",

year = "2019",

doi = "10.1109/ICECCO48375.2019.9043205",

language = "English",

isbn = "9781728151601",

booktitle = "2019 15th International Conference on Electronics, Computer and Computation (ICECCO)",

publisher = "IEEE",

}

TY - CHAP

T1 - Transfer learning based histopathologic image classification for burns recognition

AU - Musa, Ahmad

AU - Abubakar, Aliyu

AU - Ugail, Hassan

AU - Bukar, Ali Maina

AU - Aminu, Ali Ahmad

PY - 2019

Y1 - 2019

N2 - Burn is one of the most leading devastating injuries affecting people worldwide with high impact rate in low-and middle-income countries subjecting hundreds of thousands to loss of lives and physical deformities. Both affected individuals and health institutions are faced with challenges such as inadequate experience/well trained workforce and high diagnostics cost. The demand of having efficient, cost-effective and user-friendly technique to aid in addressing the problem is on the rise. Deep neural networks have recently attracted the attention of many researchers and achieved impressive results in many applications. Therefore, this paper proposed the use of off-the-shelf Convolutional Neural Network features from two ImageNet pre-trained models (GoogleNet and ResNet152), VGG-Face. The features are used to train Support Vector Machine (SVM) and Decision Tree (DT). 100% identification accuracy was recorded using ImageNet model and SVM.

AB - Burn is one of the most leading devastating injuries affecting people worldwide with high impact rate in low-and middle-income countries subjecting hundreds of thousands to loss of lives and physical deformities. Both affected individuals and health institutions are faced with challenges such as inadequate experience/well trained workforce and high diagnostics cost. The demand of having efficient, cost-effective and user-friendly technique to aid in addressing the problem is on the rise. Deep neural networks have recently attracted the attention of many researchers and achieved impressive results in many applications. Therefore, this paper proposed the use of off-the-shelf Convolutional Neural Network features from two ImageNet pre-trained models (GoogleNet and ResNet152), VGG-Face. The features are used to train Support Vector Machine (SVM) and Decision Tree (DT). 100% identification accuracy was recorded using ImageNet model and SVM.

KW - Bruises

KW - Burns

KW - Classification

KW - Convolutional neural network

KW - Decision tree

KW - Support vector machine

U2 - 10.1109/ICECCO48375.2019.9043205

DO - 10.1109/ICECCO48375.2019.9043205

M3 - Chapter

SN - 9781728151601

SN - 9781728151595

SN - 9781728151618

BT - 2019 15th International Conference on Electronics, Computer and Computation (ICECCO)

PB - IEEE

ER -

Transfer learning based histopathologic image classification for burns recognition

Abstract

Keywords

Access to Document

Fingerprint

Cite this