Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features

Objectives: To develop and validate the model for distinguishing brain abscess from cystic glioma by combining deep transfer learning (DTL) features and hand-crafted radiomics (HCR) features in conventional T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI).Methods: This single-center retrosp...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Linlin Bo, Zijian Zhang, Zekun Jiang, Chao Yang, Pu Huang, Tingyin Chen, Yifan Wang, Gang Yu, Xiao Tan, Quan Cheng, Dengwang Li, Zhixiong Liu
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/2ed773cb17e643c5b45cf997504cd66f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:2ed773cb17e643c5b45cf997504cd66f
record_format dspace
spelling oai:doaj.org-article:2ed773cb17e643c5b45cf997504cd66f2021-11-17T12:08:08ZDifferentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features2296-858X10.3389/fmed.2021.748144https://doaj.org/article/2ed773cb17e643c5b45cf997504cd66f2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fmed.2021.748144/fullhttps://doaj.org/toc/2296-858XObjectives: To develop and validate the model for distinguishing brain abscess from cystic glioma by combining deep transfer learning (DTL) features and hand-crafted radiomics (HCR) features in conventional T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI).Methods: This single-center retrospective analysis involved 188 patients with pathologically proven brain abscess (102) or cystic glioma (86). One thousand DTL and 105 HCR features were extracted from the T1WI and T2WI of the patients. Three feature selection methods and four classifiers, such as k-nearest neighbors (KNN), random forest classifier (RFC), logistic regression (LR), and support vector machine (SVM), for distinguishing brain abscess from cystic glioma were compared. The best feature combination and classifier were chosen according to the quantitative metrics including area under the curve (AUC), Youden Index, and accuracy.Results: In most cases, deep learning-based radiomics (DLR) features, i.e., DTL features combined with HCR features, contributed to a higher accuracy than HCR and DTL features alone for distinguishing brain abscesses from cystic gliomas. The AUC values of the model established, based on the DLR features in T2WI, were 0.86 (95% CI: 0.81, 0.91) in the training cohort and 0.85 (95% CI: 0.75, 0.95) in the test cohort, respectively.Conclusions: The model established with the DLR features can distinguish brain abscess from cystic glioma efficiently, providing a useful, inexpensive, convenient, and non-invasive method for differential diagnosis. This is the first time that conventional MRI radiomics is applied to identify these diseases. Also, the combination of HCR and DTL features can lead to get impressive performance.Linlin BoZijian ZhangZekun JiangChao YangPu HuangTingyin ChenYifan WangGang YuXiao TanQuan ChengQuan ChengDengwang LiZhixiong LiuZhixiong LiuFrontiers Media S.A.articlebrain abscessdeep transfer learningradiomicsconvolutional neural networkcystic gliomaMedicine (General)R5-920ENFrontiers in Medicine, Vol 8 (2021)
institution DOAJ
collection DOAJ
language EN
topic brain abscess
deep transfer learning
radiomics
convolutional neural network
cystic glioma
Medicine (General)
R5-920
spellingShingle brain abscess
deep transfer learning
radiomics
convolutional neural network
cystic glioma
Medicine (General)
R5-920
Linlin Bo
Zijian Zhang
Zekun Jiang
Chao Yang
Pu Huang
Tingyin Chen
Yifan Wang
Gang Yu
Xiao Tan
Quan Cheng
Quan Cheng
Dengwang Li
Zhixiong Liu
Zhixiong Liu
Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features
description Objectives: To develop and validate the model for distinguishing brain abscess from cystic glioma by combining deep transfer learning (DTL) features and hand-crafted radiomics (HCR) features in conventional T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI).Methods: This single-center retrospective analysis involved 188 patients with pathologically proven brain abscess (102) or cystic glioma (86). One thousand DTL and 105 HCR features were extracted from the T1WI and T2WI of the patients. Three feature selection methods and four classifiers, such as k-nearest neighbors (KNN), random forest classifier (RFC), logistic regression (LR), and support vector machine (SVM), for distinguishing brain abscess from cystic glioma were compared. The best feature combination and classifier were chosen according to the quantitative metrics including area under the curve (AUC), Youden Index, and accuracy.Results: In most cases, deep learning-based radiomics (DLR) features, i.e., DTL features combined with HCR features, contributed to a higher accuracy than HCR and DTL features alone for distinguishing brain abscesses from cystic gliomas. The AUC values of the model established, based on the DLR features in T2WI, were 0.86 (95% CI: 0.81, 0.91) in the training cohort and 0.85 (95% CI: 0.75, 0.95) in the test cohort, respectively.Conclusions: The model established with the DLR features can distinguish brain abscess from cystic glioma efficiently, providing a useful, inexpensive, convenient, and non-invasive method for differential diagnosis. This is the first time that conventional MRI radiomics is applied to identify these diseases. Also, the combination of HCR and DTL features can lead to get impressive performance.
format article
author Linlin Bo
Zijian Zhang
Zekun Jiang
Chao Yang
Pu Huang
Tingyin Chen
Yifan Wang
Gang Yu
Xiao Tan
Quan Cheng
Quan Cheng
Dengwang Li
Zhixiong Liu
Zhixiong Liu
author_facet Linlin Bo
Zijian Zhang
Zekun Jiang
Chao Yang
Pu Huang
Tingyin Chen
Yifan Wang
Gang Yu
Xiao Tan
Quan Cheng
Quan Cheng
Dengwang Li
Zhixiong Liu
Zhixiong Liu
author_sort Linlin Bo
title Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features
title_short Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features
title_full Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features
title_fullStr Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features
title_full_unstemmed Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features
title_sort differentiation of brain abscess from cystic glioma using conventional mri based on deep transfer learning features and hand-crafted radiomics features
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/2ed773cb17e643c5b45cf997504cd66f
work_keys_str_mv AT linlinbo differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT zijianzhang differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT zekunjiang differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT chaoyang differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT puhuang differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT tingyinchen differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT yifanwang differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT gangyu differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT xiaotan differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT quancheng differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT quancheng differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT dengwangli differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT zhixiongliu differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
AT zhixiongliu differentiationofbrainabscessfromcysticgliomausingconventionalmribasedondeeptransferlearningfeaturesandhandcraftedradiomicsfeatures
_version_ 1718425599691718656