Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging

Anterior cruciate ligament (ACL) tear is caused by partially or completely torn ACL ligament in the knee, especially in sportsmen. There is a need to classify the ACL tear before it fully ruptures to avoid osteoarthritis. This research aims to identify ACL tears automatically and efficiently with a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mazhar Javed Awan, Mohd Shafry Mohd Rahim, Naomie Salim, Amjad Rehman, Haitham Nobanee, Hassan Shabir
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	anterior cruciate ligament osteoarthritis deep learning classification public health healthcare Medicine R
Acceso en línea:	https://doaj.org/article/77d36e6c342c44668933ba7df4bbe965
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:77d36e6c342c44668933ba7df4bbe965
record_format	dspace
spelling	oai:doaj.org-article:77d36e6c342c44668933ba7df4bbe9652021-11-25T18:07:40ZImproved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging10.3390/jpm111111632075-4426https://doaj.org/article/77d36e6c342c44668933ba7df4bbe9652021-11-01T00:00:00Zhttps://www.mdpi.com/2075-4426/11/11/1163https://doaj.org/toc/2075-4426Anterior cruciate ligament (ACL) tear is caused by partially or completely torn ACL ligament in the knee, especially in sportsmen. There is a need to classify the ACL tear before it fully ruptures to avoid osteoarthritis. This research aims to identify ACL tears automatically and efficiently with a deep learning approach. A dataset was gathered, consisting of 917 knee magnetic resonance images (MRI) from Clinical Hospital Centre Rijeka, Croatia. The dataset we used consists of three classes: non-injured, partial tears, and fully ruptured knee MRI. The study compares and evaluates two variants of convolutional neural networks (CNN). We first tested the standard CNN model of five layers and then a customized CNN model of eleven layers. Eight different hyper-parameters were adjusted and tested on both variants. Our customized CNN model showed good results after a 25% random split using RMSprop and a learning rate of 0.001. The average evaluations are measured by accuracy, precision, sensitivity, specificity, and F1-score in the case of the standard CNN using the Adam optimizer with a learning rate of 0.001, i.e., 96.3%, 95%, 96%, 96.9%, and 95.6%, respectively. In the case of the customized CNN model, using the same evaluation measures, the model performed at 98.6%, 98%, 98%, 98.5%, and 98%, respectively, using an RMSprop optimizer with a learning rate of 0.001. Moreover, we also present our results on the receiver operating curve and area under the curve (ROC AUC). The customized CNN model with the Adam optimizer and a learning rate of 0.001 achieved 0.99 over three classes was highest among all. The model showed good results overall, and in the future, we can improve it to apply other CNN architectures to detect and segment other ligament parts like meniscus and cartilages.Mazhar Javed AwanMohd Shafry Mohd RahimNaomie SalimAmjad RehmanHaitham NobaneeHassan ShabirMDPI AGarticleanterior cruciate ligamentosteoarthritisdeep learningclassificationpublic healthhealthcareMedicineRENJournal of Personalized Medicine, Vol 11, Iss 1163, p 1163 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	anterior cruciate ligament osteoarthritis deep learning classification public health healthcare Medicine R
spellingShingle	anterior cruciate ligament osteoarthritis deep learning classification public health healthcare Medicine R Mazhar Javed Awan Mohd Shafry Mohd Rahim Naomie Salim Amjad Rehman Haitham Nobanee Hassan Shabir Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging
description	Anterior cruciate ligament (ACL) tear is caused by partially or completely torn ACL ligament in the knee, especially in sportsmen. There is a need to classify the ACL tear before it fully ruptures to avoid osteoarthritis. This research aims to identify ACL tears automatically and efficiently with a deep learning approach. A dataset was gathered, consisting of 917 knee magnetic resonance images (MRI) from Clinical Hospital Centre Rijeka, Croatia. The dataset we used consists of three classes: non-injured, partial tears, and fully ruptured knee MRI. The study compares and evaluates two variants of convolutional neural networks (CNN). We first tested the standard CNN model of five layers and then a customized CNN model of eleven layers. Eight different hyper-parameters were adjusted and tested on both variants. Our customized CNN model showed good results after a 25% random split using RMSprop and a learning rate of 0.001. The average evaluations are measured by accuracy, precision, sensitivity, specificity, and F1-score in the case of the standard CNN using the Adam optimizer with a learning rate of 0.001, i.e., 96.3%, 95%, 96%, 96.9%, and 95.6%, respectively. In the case of the customized CNN model, using the same evaluation measures, the model performed at 98.6%, 98%, 98%, 98.5%, and 98%, respectively, using an RMSprop optimizer with a learning rate of 0.001. Moreover, we also present our results on the receiver operating curve and area under the curve (ROC AUC). The customized CNN model with the Adam optimizer and a learning rate of 0.001 achieved 0.99 over three classes was highest among all. The model showed good results overall, and in the future, we can improve it to apply other CNN architectures to detect and segment other ligament parts like meniscus and cartilages.
format	article
author	Mazhar Javed Awan Mohd Shafry Mohd Rahim Naomie Salim Amjad Rehman Haitham Nobanee Hassan Shabir
author_facet	Mazhar Javed Awan Mohd Shafry Mohd Rahim Naomie Salim Amjad Rehman Haitham Nobanee Hassan Shabir
author_sort	Mazhar Javed Awan
title	Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging
title_short	Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging
title_full	Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging
title_fullStr	Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging
title_full_unstemmed	Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging
title_sort	improved deep convolutional neural network to classify osteoarthritis from anterior cruciate ligament tear using magnetic resonance imaging
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/77d36e6c342c44668933ba7df4bbe965
work_keys_str_mv	AT mazharjavedawan improveddeepconvolutionalneuralnetworktoclassifyosteoarthritisfromanteriorcruciateligamenttearusingmagneticresonanceimaging AT mohdshafrymohdrahim improveddeepconvolutionalneuralnetworktoclassifyosteoarthritisfromanteriorcruciateligamenttearusingmagneticresonanceimaging AT naomiesalim improveddeepconvolutionalneuralnetworktoclassifyosteoarthritisfromanteriorcruciateligamenttearusingmagneticresonanceimaging AT amjadrehman improveddeepconvolutionalneuralnetworktoclassifyosteoarthritisfromanteriorcruciateligamenttearusingmagneticresonanceimaging AT haithamnobanee improveddeepconvolutionalneuralnetworktoclassifyosteoarthritisfromanteriorcruciateligamenttearusingmagneticresonanceimaging AT hassanshabir improveddeepconvolutionalneuralnetworktoclassifyosteoarthritisfromanteriorcruciateligamenttearusingmagneticresonanceimaging
_version_	1718411623700365312

Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging

Ejemplares similares