A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database

We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on complete 3D MRI scans. Our approach detects the presence of meniscal tears in three anato...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Alexander Tack, Alexey Shestakov, David Lüdke, Stefan Zachow
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	knee joint meniscal lesions convolutional neural networks–CNN residual learning explainable AI (XAI) multi-task deep learning Biotechnology TP248.13-248.65
Acceso en línea:	https://doaj.org/article/0bea2fc65095403d91d3f17e8fee91aa
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0bea2fc65095403d91d3f17e8fee91aa
record_format	dspace
spelling	oai:doaj.org-article:0bea2fc65095403d91d3f17e8fee91aa2021-12-02T11:22:15ZA Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database2296-418510.3389/fbioe.2021.747217https://doaj.org/article/0bea2fc65095403d91d3f17e8fee91aa2021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fbioe.2021.747217/fullhttps://doaj.org/toc/2296-4185We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on complete 3D MRI scans. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually. For optimal performance of our method, we investigate how to preprocess the MRI data and how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection. We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci. We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences. For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM. In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. Furthermore, our method can be easily trained and applied to other MRI sequences.Alexander TackAlexey ShestakovDavid LüdkeStefan ZachowStefan ZachowFrontiers Media S.A.articleknee jointmeniscal lesionsconvolutional neural networks–CNNresidual learningexplainable AI (XAI)multi-task deep learningBiotechnologyTP248.13-248.65ENFrontiers in Bioengineering and Biotechnology, Vol 9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	knee joint meniscal lesions convolutional neural networks–CNN residual learning explainable AI (XAI) multi-task deep learning Biotechnology TP248.13-248.65
spellingShingle	knee joint meniscal lesions convolutional neural networks–CNN residual learning explainable AI (XAI) multi-task deep learning Biotechnology TP248.13-248.65 Alexander Tack Alexey Shestakov David Lüdke Stefan Zachow Stefan Zachow A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database
description	We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on complete 3D MRI scans. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually. For optimal performance of our method, we investigate how to preprocess the MRI data and how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection. We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci. We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences. For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM. In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. Furthermore, our method can be easily trained and applied to other MRI sequences.
format	article
author	Alexander Tack Alexey Shestakov David Lüdke Stefan Zachow Stefan Zachow
author_facet	Alexander Tack Alexey Shestakov David Lüdke Stefan Zachow Stefan Zachow
author_sort	Alexander Tack
title	A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database
title_short	A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database
title_full	A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database
title_fullStr	A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database
title_full_unstemmed	A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database
title_sort	multi-task deep learning method for detection of meniscal tears in mri data from the osteoarthritis initiative database
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/0bea2fc65095403d91d3f17e8fee91aa
work_keys_str_mv	AT alexandertack amultitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase AT alexeyshestakov amultitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase AT davidludke amultitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase AT stefanzachow amultitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase AT stefanzachow amultitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase AT alexandertack multitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase AT alexeyshestakov multitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase AT davidludke multitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase AT stefanzachow multitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase AT stefanzachow multitaskdeeplearningmethodfordetectionofmeniscaltearsinmridatafromtheosteoarthritisinitiativedatabase
_version_	1718395920705388544

A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database

Ejemplares similares