Classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks

Abstract A subset of primary central nervous system lymphomas (PCNSL) are difficult to distinguish from glioblastoma multiforme (GBM) on magnetic resonance imaging (MRI). We developed a convolutional neural network (CNN) to distinguish these tumors on contrast-enhanced T1-weighted images. Preoperati...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Malia McAvoy, Paola Calvachi Prieto, Jakub R. Kaczmarzyk, Iván Sánchez Fernández, Jack McNulty, Timothy Smith, Kun-Hsing Yu, William B. Gormley, Omar Arnaout
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/da2c5c71d6d94a5cb919d989bc06e0db
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:da2c5c71d6d94a5cb919d989bc06e0db
record_format	dspace
spelling	oai:doaj.org-article:da2c5c71d6d94a5cb919d989bc06e0db2021-12-02T16:06:41ZClassification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks10.1038/s41598-021-94733-02045-2322https://doaj.org/article/da2c5c71d6d94a5cb919d989bc06e0db2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-94733-0https://doaj.org/toc/2045-2322Abstract A subset of primary central nervous system lymphomas (PCNSL) are difficult to distinguish from glioblastoma multiforme (GBM) on magnetic resonance imaging (MRI). We developed a convolutional neural network (CNN) to distinguish these tumors on contrast-enhanced T1-weighted images. Preoperative brain tumor MRIs were retrospectively collected among 320 patients with either GBM (n = 160) and PCNSL (n = 160) from two academic institutions. The individual images from these MRIs consisted of a training set (n = 1894 GBM and 1245 PCNSL), a validation set (n = 339 GBM; 202 PCNSL), and a testing set (99 GBM and 108 PCNSL). Three CNNs using the EfficientNetB4 architecture were evaluated. To increase the size of the training set and minimize overfitting, random flips and changes to color were performed on the training set. Our transfer learning approach (with image augmentation and 292 epochs) yielded an AUC of 0.94 (95% CI: 0.91–0.97) for GBM and an AUC of 0.95 (95% CI: 0.92–0.98) for PCNL. In the second case (not augmented and 137 epochs), the images were augmented prior to training. The area under the curve for GBM was 0.92 (95% CI: 0.88–0.96) for GBM and an AUC of 0.94 (95% CI: 0.91–0.97) for PCNSL. For the last case (augmented, Gaussian noise and 238 epochs) the AUC for GBM was 0.93 (95% CI: 0.89–0.96) and an AUC 0.93 (95% CI = 0.89–0.96) for PCNSL. Even with a relatively small dataset, our transfer learning approach demonstrated CNNs may provide accurate diagnostic information to assist radiologists in distinguishing PCNSL and GBM.Malia McAvoyPaola Calvachi PrietoJakub R. KaczmarzykIván Sánchez FernándezJack McNultyTimothy SmithKun-Hsing YuWilliam B. GormleyOmar ArnaoutNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-7 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Malia McAvoy Paola Calvachi Prieto Jakub R. Kaczmarzyk Iván Sánchez Fernández Jack McNulty Timothy Smith Kun-Hsing Yu William B. Gormley Omar Arnaout Classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks
description	Abstract A subset of primary central nervous system lymphomas (PCNSL) are difficult to distinguish from glioblastoma multiforme (GBM) on magnetic resonance imaging (MRI). We developed a convolutional neural network (CNN) to distinguish these tumors on contrast-enhanced T1-weighted images. Preoperative brain tumor MRIs were retrospectively collected among 320 patients with either GBM (n = 160) and PCNSL (n = 160) from two academic institutions. The individual images from these MRIs consisted of a training set (n = 1894 GBM and 1245 PCNSL), a validation set (n = 339 GBM; 202 PCNSL), and a testing set (99 GBM and 108 PCNSL). Three CNNs using the EfficientNetB4 architecture were evaluated. To increase the size of the training set and minimize overfitting, random flips and changes to color were performed on the training set. Our transfer learning approach (with image augmentation and 292 epochs) yielded an AUC of 0.94 (95% CI: 0.91–0.97) for GBM and an AUC of 0.95 (95% CI: 0.92–0.98) for PCNL. In the second case (not augmented and 137 epochs), the images were augmented prior to training. The area under the curve for GBM was 0.92 (95% CI: 0.88–0.96) for GBM and an AUC of 0.94 (95% CI: 0.91–0.97) for PCNSL. For the last case (augmented, Gaussian noise and 238 epochs) the AUC for GBM was 0.93 (95% CI: 0.89–0.96) and an AUC 0.93 (95% CI = 0.89–0.96) for PCNSL. Even with a relatively small dataset, our transfer learning approach demonstrated CNNs may provide accurate diagnostic information to assist radiologists in distinguishing PCNSL and GBM.
format	article
author	Malia McAvoy Paola Calvachi Prieto Jakub R. Kaczmarzyk Iván Sánchez Fernández Jack McNulty Timothy Smith Kun-Hsing Yu William B. Gormley Omar Arnaout
author_facet	Malia McAvoy Paola Calvachi Prieto Jakub R. Kaczmarzyk Iván Sánchez Fernández Jack McNulty Timothy Smith Kun-Hsing Yu William B. Gormley Omar Arnaout
author_sort	Malia McAvoy
title	Classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks
title_short	Classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks
title_full	Classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks
title_fullStr	Classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks
title_full_unstemmed	Classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks
title_sort	classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/da2c5c71d6d94a5cb919d989bc06e0db
work_keys_str_mv	AT maliamcavoy classificationofglioblastomaversusprimarycentralnervoussystemlymphomausingconvolutionalneuralnetworks AT paolacalvachiprieto classificationofglioblastomaversusprimarycentralnervoussystemlymphomausingconvolutionalneuralnetworks AT jakubrkaczmarzyk classificationofglioblastomaversusprimarycentralnervoussystemlymphomausingconvolutionalneuralnetworks AT ivansanchezfernandez classificationofglioblastomaversusprimarycentralnervoussystemlymphomausingconvolutionalneuralnetworks AT jackmcnulty classificationofglioblastomaversusprimarycentralnervoussystemlymphomausingconvolutionalneuralnetworks AT timothysmith classificationofglioblastomaversusprimarycentralnervoussystemlymphomausingconvolutionalneuralnetworks AT kunhsingyu classificationofglioblastomaversusprimarycentralnervoussystemlymphomausingconvolutionalneuralnetworks AT williambgormley classificationofglioblastomaversusprimarycentralnervoussystemlymphomausingconvolutionalneuralnetworks AT omararnaout classificationofglioblastomaversusprimarycentralnervoussystemlymphomausingconvolutionalneuralnetworks
_version_	1718384935492911104

Classification of glioblastoma versus primary central nervous system lymphoma using convolutional neural networks

Ejemplares similares