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

Linlin Bo; Zijian Zhang; Zekun Jiang; Chao Yang; Pu Huang; Tingyin Chen; Yifan Wang; Gang Yu; Xiao Tan; Quan Cheng; Dengwang Li; Zhixiong Liu

doi:10.3389/fmed.2021.748144

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

Front Med (Lausanne). 2021 Nov 12:8:748144. doi: 10.3389/fmed.2021.748144. eCollection 2021.

Authors

Linlin Bo¹, Zijian Zhang², Zekun Jiang¹, Chao Yang¹, Pu Huang¹, Tingyin Chen³, Yifan Wang³, Gang Yu¹, Xiao Tan², Quan Cheng^{4

5}, Dengwang Li¹, Zhixiong Liu^{4

5}

Affiliations

¹ Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Institute of Industrial Technology for Health Sciences and Precision Medicine, School of Physics and Electronics, Shandong Normal University, Jinan, China.
² Department of Oncology, Xiangya Hospital, Central South University, Changsha, China.
³ Department of Network Information Center, Xiangya Hospital, Centra South University, Changsha, China.
⁴ Department of Neurosurgery, Xiangya Hospital, Central South University, Changsha, China.
⁵ National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha, China.

Abstract

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.

Keywords: brain abscess; convolutional neural network; cystic glioma; deep transfer learning; radiomics.