Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning

Abstract Differentiating pseudoprogression from true tumor progression has become a significant challenge in follow-up of diffuse infiltrating gliomas, particularly high grade, which leads to a potential treatment delay for patients with early glioma recurrence. In this study, we proposed to use a m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Joonsang Lee, Nicholas Wang, Sevcan Turk, Shariq Mohammed, Remy Lobo, John Kim, Eric Liao, Sandra Camelo-Piragua, Michelle Kim, Larry Junck, Jayapalli Bapuraj, Ashok Srinivasan, Arvind Rao
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/e85fa579f6ac4d8b9c5da0ebcab2a767
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e85fa579f6ac4d8b9c5da0ebcab2a767
record_format	dspace
spelling	oai:doaj.org-article:e85fa579f6ac4d8b9c5da0ebcab2a7672021-12-02T16:08:46ZDiscriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning10.1038/s41598-020-77389-02045-2322https://doaj.org/article/e85fa579f6ac4d8b9c5da0ebcab2a7672020-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-77389-0https://doaj.org/toc/2045-2322Abstract Differentiating pseudoprogression from true tumor progression has become a significant challenge in follow-up of diffuse infiltrating gliomas, particularly high grade, which leads to a potential treatment delay for patients with early glioma recurrence. In this study, we proposed to use a multiparametric MRI data as a sequence input for the convolutional neural network with the recurrent neural network based deep learning structure to discriminate between pseudoprogression and true tumor progression. In this study, 43 biopsy-proven patient data identified as diffuse infiltrating glioma patients whose disease progressed/recurred were used. The dataset consists of five original MRI sequences; pre-contrast T1-weighted, post-contrast T1-weighted, T2-weighted, FLAIR, and ADC images as well as two engineered sequences; T1post–T1pre and T2–FLAIR. Next, we used three CNN-LSTM models with a different set of sequences as input sequences to pass through CNN-LSTM layers. We performed threefold cross-validation in the training dataset and generated the boxplot, accuracy, and ROC curve, AUC from each trained model with the test dataset to evaluate models. The mean accuracy for VGG16 models ranged from 0.44 to 0.60 and the mean AUC ranged from 0.47 to 0.59. For CNN-LSTM model, the mean accuracy ranged from 0.62 to 0.75 and the mean AUC ranged from 0.64 to 0.81. The performance of the proposed CNN-LSTM with multiparametric sequence data was found to outperform the popular convolutional CNN with a single MRI sequence. In conclusion, incorporating all available MRI sequences into a sequence input for a CNN-LSTM model improved diagnostic performance for discriminating between pseudoprogression and true tumor progression.Joonsang LeeNicholas WangSevcan TurkShariq MohammedRemy LoboJohn KimEric LiaoSandra Camelo-PiraguaMichelle KimLarry JunckJayapalli BapurajAshok SrinivasanArvind RaoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-10 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Joonsang Lee Nicholas Wang Sevcan Turk Shariq Mohammed Remy Lobo John Kim Eric Liao Sandra Camelo-Piragua Michelle Kim Larry Junck Jayapalli Bapuraj Ashok Srinivasan Arvind Rao Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning
description	Abstract Differentiating pseudoprogression from true tumor progression has become a significant challenge in follow-up of diffuse infiltrating gliomas, particularly high grade, which leads to a potential treatment delay for patients with early glioma recurrence. In this study, we proposed to use a multiparametric MRI data as a sequence input for the convolutional neural network with the recurrent neural network based deep learning structure to discriminate between pseudoprogression and true tumor progression. In this study, 43 biopsy-proven patient data identified as diffuse infiltrating glioma patients whose disease progressed/recurred were used. The dataset consists of five original MRI sequences; pre-contrast T1-weighted, post-contrast T1-weighted, T2-weighted, FLAIR, and ADC images as well as two engineered sequences; T1post–T1pre and T2–FLAIR. Next, we used three CNN-LSTM models with a different set of sequences as input sequences to pass through CNN-LSTM layers. We performed threefold cross-validation in the training dataset and generated the boxplot, accuracy, and ROC curve, AUC from each trained model with the test dataset to evaluate models. The mean accuracy for VGG16 models ranged from 0.44 to 0.60 and the mean AUC ranged from 0.47 to 0.59. For CNN-LSTM model, the mean accuracy ranged from 0.62 to 0.75 and the mean AUC ranged from 0.64 to 0.81. The performance of the proposed CNN-LSTM with multiparametric sequence data was found to outperform the popular convolutional CNN with a single MRI sequence. In conclusion, incorporating all available MRI sequences into a sequence input for a CNN-LSTM model improved diagnostic performance for discriminating between pseudoprogression and true tumor progression.
format	article
author	Joonsang Lee Nicholas Wang Sevcan Turk Shariq Mohammed Remy Lobo John Kim Eric Liao Sandra Camelo-Piragua Michelle Kim Larry Junck Jayapalli Bapuraj Ashok Srinivasan Arvind Rao
author_facet	Joonsang Lee Nicholas Wang Sevcan Turk Shariq Mohammed Remy Lobo John Kim Eric Liao Sandra Camelo-Piragua Michelle Kim Larry Junck Jayapalli Bapuraj Ashok Srinivasan Arvind Rao
author_sort	Joonsang Lee
title	Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning
title_short	Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning
title_full	Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning
title_fullStr	Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning
title_full_unstemmed	Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning
title_sort	discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric mri data through deep learning
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/e85fa579f6ac4d8b9c5da0ebcab2a767
work_keys_str_mv	AT joonsanglee discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT nicholaswang discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT sevcanturk discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT shariqmohammed discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT remylobo discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT johnkim discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT ericliao discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT sandracamelopiragua discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT michellekim discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT larryjunck discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT jayapallibapuraj discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT ashoksrinivasan discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning AT arvindrao discriminatingpseudoprogressionandtrueprogressionindiffuseinfiltratinggliomausingmultiparametricmridatathroughdeeplearning
_version_	1718384505661685760

Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning

Ejemplares similares